Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on July 24, 2026 has been entered.
Status of Claims
This office action for the 18/710169 application is in response to the communications filed July 24, 2026.
Claims 1, 2, 7, 22 and 23 were amended July 24, 2026.
Claims 12 and 20 were cancelled July 24, 2026.
Claims 1-5, 7, 9-11, 13, 14, 17-19, 22 and 23 are currently pending and considered below.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-5, 7, 9-11, 13, 14, 17-19, 22 and 23 rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
As per claim 1,
Step 1: The claim recites subject matter within a statutory category as a process.
Step 2A is a two-prong inquiry, in which Prong 1 determines whether a claim recites a judicial exception. Prong 2 determines if the additional limitations of the claim integrates the recited judicial exception into a practical application. If the additional elements of the claim fail to integrate the judicial exception into a practical application, claim is directed to the recited judicial exception, see MPEP 2106.04(II)(A).
Step 2A Prong 1: The claim contains subject matter that recites an abstract idea, with the steps of a method for diagnostics, the method comprising: receiving first input data relating to a speech or text input signal originating from a user device, the first input data indicating at least one problem; processing the first input data using a model, to generate a representation of the first input data and to generate a first input pre-processing output based at least in part on the representation of the first input data; processing the first input pre-processing output comprising the embedding using a preliminary diagnosis model to determine a preliminary diagnosis output comprising at least one preliminary diagnosis of the problem; determining and based at least in part on the preliminary diagnosis output, at least one dialogue system output, wherein determining that at least one dialogue system output comprises selecting one or more questions based on the preliminary diagnosis output; receiving additional input data responsive to the dialogue system output; processing the additional input data to determine one or more further diagnoses, further comprising: causing, responsive to the one or more further diagnoses, an action to be taken or scheduled, wherein the action comprises at least one of: allocating a user of the user device to a treatment pathway for treatment by a clinician; scheduling an appointment with a clinician; establishing a communication channel with an emergency service; and generate and/or output one or more instructions and/or treatment plan actions for the user. These steps, as drafted, under the broadest reasonable interpretation recite:
certain methods of organizing human activity (e.g., fundamental economic principles or practices including: hedging; insurance; mitigating risk; etc., commercial or legal interactions including: agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations; etc., managing personal behavior or relationships or interactions between people including: social activities; teaching; following rules or instructions; etc.) but for recitation of generic computer components. That is, other than reciting steps as performed by the generic computer components, nothing in the claim element precludes the step from being directed to certain methods of organizing human activity. The identified abstract idea, law of nature, or natural phenomenon identified above, in the context of this claim, encompasses a certain method of organizing human activity, namely managing personal behavior or relationships or interactions between people. This is because each of the limitations of the abstract idea recites a list of rules or instructions that a human person can follow. If a claim limitation, under its broadest reasonable interpretation, covers at least the recited methods of organizing human activity above, but for the recitation of generic computer components, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. See MPEP 2106.04(a).
Step 2A Prong 2: The claim does not recite additional elements that integrate the judicial exception into a practical application. In particular, the additional elements do not integrate the abstract idea into a practical application, other than the abstract idea per se, because the additional elements amount to no more than limitations which:
amount to mere instructions to apply an exception, see MPEP 2106.05(f), such as:
“computer-implemented”, “automated”, “at one or more processors”, “a first input pre-processing module comprising a first input pre-processing machine learning”, “at the one or more processors”, “module” and “machine learning” which corresponds to merely using a computer as a tool to perform an abstract idea. Page 5, Lines 1-4 of the as-filed specification describes that the hardware that is implementing the steps of the abstract idea amount to a generic computer. Implementing an abstract idea on a generic computer, does not integrate the abstract idea into a practical application in Step 2A Prong Two or add significantly more in Step 2B, similar to how the recitation of the computer in the claim in Alice amounted to mere instructions to apply the abstract idea of intermediated settlement on a generic computer.
add insignificant extra-solution activity to the abstract idea, see MPEP 2106.05(g), such as:
“at an input of a diagnostics system comprising a client device and a server device”, “outputting, by way of an output of the diagnostics system, the dialogue system output;” , “at the input of the diagnostics system” and “outputting, by the output of the diagnostics system, an indication of the one or more further diagnoses” which corresponds to mere data gathering and/or output.
“wherein the first input pre-processing machine learning model comprises an embedding machine learning model configured to generate an embedding of the first input data, the embedding having lower dimensionality than the first input data, and wherein the first input pre-processing module output comprises the embedding” which corresponds to insignificant application.
Accordingly, this claim is directed to an abstract idea.
Step 2B: The claim does not recite additional elements that amount to significantly more than the judicial exception. As discussed above with respect to discussion of integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply an exception, add insignificant extra-solution activity to the abstract idea, and/or generally link the abstract idea to a particular technological environment or field of use. Additionally, the additional limitations, identified as insignificant extra-solution activity to the abstract idea, amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields such as:
computer functions that have been identified by the courts as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity, see MPEP 2106.05(d)(II), such as:
“at an input of a diagnostics system comprising a client device and a server device”, “outputting, by way of an output of the diagnostics system, the dialogue system output;” , “at the input of the diagnostics system” and “outputting, by the output of the diagnostics system, an indication of the one or more further diagnoses” which corresponds to receiving or transmitting data over a network.
computer functions that have been identified by the examiner as being well‐understood, routine, and conventional functions in light of the prior art, wherein the examiner has provided multiple references as evidence as required by Berkheimer v. HP, Inc., 881 F.3d 1360, 1368, 125 USPQ2d 1649, 1654 (Fed. Cir. 2018), see MPEP 2106.05(d)(I), such as:
“wherein the first input pre-processing machine learning model comprises an embedding machine learning model configured to generate an embedding of the first input data, the embedding having lower dimensionality than the first input data, and wherein the first input pre-processing module output comprises the embedding” which is taught by:
Molony et al. (US 2022/0093252; herein referred to as Molony): (Paragraphs [0029] and [0087]-[0090] of Molony. The teaching describes a predictive model that low rate of individuals with a rare disease in the general population, datasets that can be used in training machine-learned models to diagnose the rare disease are often noisy and/or unbalanced. This specification describes methods of generating a reduced noise and/or balanced dataset that, when used to train a machine-learned model, results in a more accurate model (i.e. a model with fewer false positives and/or false negatives). additional features may be identified from the literature 614 using natural language processing (NLP). Vocabulary/tokens representing clinical terms is identified in medical literature (e.g. on a selection of medical publications from PubMED). The medical literature may be selected to include publications related to the rare disease and a selection of disease with similar symptoms. Natural language processing is used to create a mathematical representation of the clinical terms that is based on the context in which those terms are used in the literature. For example, each term may be represented as an embedding vector in a vector space, with words that occur in a similar context occupying close positions in the vector space, i.e. clinical terms occurring in similar contexts have similar embedding vector representations. An example of a natural language processing algorithm that can be used to generate such embedding vectors is Word2Vec (see, for example, “Distributed Representations of Words and Phrases and their Compositionality”, Mikolov et al. 2013, Adv. Neural Inf. Process. Syst, Volume 26). By translating the words to a vector representation this reduces the dimensionality of the data. Furthermore, the identified word/term embeddings can be used to generate a vectorisation of each individual in the training dataset. For each individual, a vector representation of that individual can be created, for example by averaging (e.g. taking the mean of) the embedding vectors of the features associated with the individual. In some embodiments, the embedding of the rare disease term may also be subtracted from this representation to create a final vector representation for the individual. Where a control individual has none of the features of the rare disease, they may be represented by a zero vector. Such vector representations may be used as an additional or alternative input to the machine-learned model.)
Sirbulescu et al. (US 2023/0306761; herein referred to as Sirbulescu): (Paragraph [0005] of Sirbulescu. The teaching describes step (a) includes dimensionality reduction for each of the two or more data sets. In some embodiments, the dimensionality reduction is performed by uniform manifold approximation and projection (UMAP), isometric mapping (Isomap), t-distributed stochastic neighbor embedding (t-SNE), potential of heat diffusion for affinity-based transition embedding (PHATE), principal component analysis (PCA), diffusion maps, or non-negative matrix factorization (NMF). In some embodiments, the dimensionality reduction is performed by uniform manifold approximation and projection (UMAP). In some embodiments, step (a) includes optimizing global spatial alignment in the aligned feature image. In some embodiments, step (a) includes optimizing local alignment in the aligned feature image.)
Williams et al. (US 2020/00104738; herein referred to as Williams): (Paragraphs [0044]-[0046] of Williams. The teaching describes a visualization of the internet generated by a technique that includes embedding websites in a p-dimensional space, according to an embodiment. FIG. 8 is a flow chart of a method for clustering and/or mapping internet locations (also referred to as URLs or websites), according to an embodiment. Meaningful distances between websites can be established by defining an embedding. An embedding is a relatively low-dimensional, learned continuous vector representation of a group of relatively high-dimensional vectors. Generating an embedding allows for the reduction of dimensionality while meaningfully representing the high-dimensional vectors in the embedding space.)
Accordingly, it can be seen that the implementation of embeddings to achieve a lower dimensionality in data was well-known, routine and conventional before the time of filing based on the plurality of references provided that describes these functions at such a high level of generality.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 2,
Claim 2 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 2 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising: receiving second input data at the input, the second input data comprising a plurality of answers responsive to predetermined questions output by the diagnostics system; processing the second input data at a second … model to generate a second input pre-processing … output, the second input pre-processing … output comprising a prediction of at least one problem; and wherein determining the preliminary diagnosis output comprises processing the second input pre-processing … output at the preliminary diagnosis … model and the preliminary diagnosis output is based at least in part on the second input pre-processing … output.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“input pre-processing module comprising a second input pre-processing machine learning”, “module” and “machine learning” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 3,
Claim 3 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 3 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising: receiving third input data from one or more sensors, the third input data comprising a plurality of sensor signals measuring a characteristic of a user; processing the third input data … generate a third input pre-processing … output comprising one or more principal components of the third input data; wherein determining the preliminary diagnosis output comprises processing the third input pre-processing … output at the preliminary diagnosis … model and the preliminary diagnosis … model is configured to determine the preliminary diagnosis output based at least in part on the third input pre-processing … output.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“at a third input pre-processing module configured”, “module” and “machine learning” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 4,
Claim 4 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 4 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising: receiving fourth input data from one or more sensors, the fourth input data comprising a plurality of sensor signals measuring a response time of a user when answering each of a plurality of questions output by the dialogue system; processing the fourth input data … to generate a fourth input pre-processing … output comprising at least one of: an average response time, variation between one or more response times, a minimum response time and a maximum response time; wherein determining the preliminary diagnosis output comprises processing the fourth input pre-processing … output at the preliminary diagnosis … model and the preliminary diagnosis … model is configured to determine the preliminary diagnosis output based at least in part on the fourth input pre-processing … output.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“at a fourth input pre-processing module configured”, “module” and “machine learning” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 5,
Claim 5 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 5 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein determining one or more further diagnoses of the problem comprises providing fifth input data … to determine the one or more further diagnoses of the problem based upon the fifth input data.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“to a machine learning classifier trained” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 7,
Claim 7 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 7 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising determining, responsive to the one or more further diagnoses, a priority; and wherein the action is determined responsive to the priority.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 9,
Claim 9 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 9 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the preliminary diagnosis … model comprises a gradient boosting decision tree classifier.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“machine learning” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 10,
Claim 10 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 10 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the preliminary diagnosis model was trained using a multi-class objective function defined by a combination of a micro averaged accuracy score and a macro averaged accuracy score, wherein the micro averaged accuracy score was defined by an overall accuracy diagnoses output by the preliminary diagnosis model independent of an accuracy of individual diagnosis categories and the macro averaged accuracy score were defined by accuracies of individual diagnosis categories output by the preliminary diagnosis model and averaged with equal weight.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 11,
Claim 11 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 11 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the first input pre-processing … comprises a plurality of first input pre-processing … models each configured to generate a respective representation of the first input data having a lower dimensionality than the first input data and each trained on a different dataset; and the method comprises generating the first input pre-processing … output based at least in part on the plurality of representations of the first input data.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“module” and “machine learning” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 13,
Claim 13 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 13 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the first input pre-processing … comprises a classifier … model configured to determine, based on the first input data, one or more categories of problem indicated in the first input data.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“module” and “machine learning” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 14,
Claim 14 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 14 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the preliminary diagnosis model is configured to determine a respective probability value for each of a plurality of categories, each respective probability value indicating a confidence that category is associated with the input data; and wherein the method further comprises: determining one or more of the plurality of categories based on the respective probability values; and determining the at least one dialogue system output by determining at least one dialogue system output associated with each of the determined one or more of the plurality of categories.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 17,
Claim 17 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 17 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
wherein at least a part of the first input pre-processing module is operated on a client device; and the preliminary diagnosis model is operated on a server device. further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 18,
Claim 18 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 18 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the input data is one of a plurality of user inputs each having a different data modality; the method comprises: providing respective ones of the plurality of user inputs to respective input pre-processing …, each input pre-processing … configured to generate a respective input pre-processing … output for inputting to the preliminary diagnosis model; and wherein determining the preliminary diagnosis output comprises: processing each of the respective input pre-processing … outputs at the preliminary diagnosis … model to provide the preliminary diagnosis output based at least in part on each of the respective input pre-processing … outputs.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“modules”, “module” and “machine learning” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 19,
Claim 19 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 19 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the input data relates to mental health, the preliminary diagnosis output comprises at least one diagnosis of one or more mental health conditions and the one or more dialogue system outputs comprise questions for confirming or disconfirming the at least one diagnosis of one or more mental health conditions.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 22,
Claim 22 is substantially similar to claim 1. Accordingly, claim 22 is rejected for the same reasons as claim 1.
As per claim 23,
Claim 23 is substantially similar to claim 1. Accordingly, claim 23 is rejected for the same reasons as claim 1.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 2, 5, 7, 9, 11, 13, 14, 17, 22 and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Ghanbari et al. (US 2014/0122109; herein referred to as Ghanbari) in view of Molony et al. (US 2022/0093252; herein referred to as Molony).
As per claim 1,
Ghanbari teaches a computer-implemented method for automated diagnostics:
(Paragraph [0007] of Ghanbari. The teaching describes a method for diagnosing a patient using a computer system including a processor and memory storing a plurality of instructions to be executed on the processor.)
Ghanbari further teaches receiving, at an input of a diagnostics system comprising a client device and a server device, first input data relating to a speech or text input signal originating from a user device, the first input data indicating at least one problem and processing, at one or more processors, the first input data using a first input pre-processing module comprising a first input pre-processing machine learning model, to generate a representation of the first input data and to generate a first input pre-processing module output based at least in part on the representation of the first input data:
(Paragraphs [0007] and [0048] of Ghanbari. The teaching describes a method for diagnosing a patient using a computer system including a processor and memory storing a plurality of instructions to be executed on the processor. In operation 206, the server 10 analyzes the patient's response using a natural language processing (NLP) system to extract key symptoms and aspects of those symptoms such as severity, frequency, duration, type, etc. while the patient speaks and/or types. For example, if a patient entered: “severe headache that started 3 days ago,” then in one embodiment, the NLP system would identify the word “headache” to classify one symptom as being a headache, detect “severe” as being near “headache” and apply the “severe” aspect to the diagnosis and create a temporal map identifying the headache as having started 3 days ago.)
Ghanbari further teaches processing, at the one or more processors, the first input pre-processing module output using a preliminary diagnosis machine learning model to determine a preliminary diagnosis output comprising at least one preliminary diagnosis of the problem, determining, at the one or more processors and based at least in part on the preliminary diagnosis output, at least one dialogue system output and outputting, by way of an output of the diagnostics system, the dialogue system output, wherein determining the at least one dialogue system output comprises selecting one or more questions based on the preliminary diagnosis output:
(Paragraphs [0050]-[0055] of Ghanbari. The teaching describes that server 10 analyzes the data in operation 206 to identify likely potential diagnoses and determines if additional information is needed in operation 208. The analysis may use any of a variety of well-known pattern matching systems for associating a given input with a particular result. In embodiments of the present invention, these systems may implement a machine learning algorithm such as a neural network, a Bayesian network, or an expert system. For example, based on the symptoms and details about the symptoms, embodiments of the present invention perform statistical analysis (such as statistical inference) to compare against the diagnostic “fingerprint” of all the disease objects in the system. The system may present the relevant history and symptoms, along with a dynamic differential diagnosis of the patient's condition based on their history and inputs (see, e.g., FIG. 3D), which may also include a rating of the system's confidence in any particular diagnosis. This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. Accordingly, on the most relevant clarifying questions would be presented to the patient and questions that would be less useful in differentiating between the identified likely diagnoses would not be presented, thereby reducing the number of questions that will be asked of the patient. These clarifying questions can then be presented to the patient.)
Ghanbari further teaches receiving, at the input of the diagnostics system, additional input data responsive to the dialogue system output, processing, at the one or more processors, the additional input data to determine one or more further diagnoses and outputting, by the output of the diagnostics system, an indication of the one or more further diagnoses:
(Paragraphs [0055] of Ghanbari. The teaching describes This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. For example, the patient may modify their representations of their symptoms such as the order in which symptoms appeared or the time at which the pain changed in character (e.g., from dull to sharp). In some embodiments, sliders and other graphical interfaces may be displayed and manipulated for entering and updating answers to questions (e.g., a colored slider for pain scale).)
Ghanbari further teaches further comprising: causing, responsive to the one or more further diagnoses, an action to be taken or scheduled, wherein the action comprises at least one of: allocating a user of the user device to a treatment pathway for treatment by a clinician; scheduling an appointment with a clinician; establishing a communication channel with an emergency service; and generate and/or output one or more instructions and/or treatment plan actions for the user:
(Paragraph [0060] of Ghanbari. The teaching describes that the system may present a list of likely diagnoses along with a summary of the data entered by the patient and a list of recommended actions. For example, if the patient is using the system from home, the list of recommended actions may include calling an emergency line, going in to urgent care, making an appointment to see a physician, and/or options and steps for self-administered diagnostics or treatment. Alternatively, if the patient is using the system from a hospital waiting room, the list of recommended actions may include immediately contacting a nurse in a priority line, continuing to wait in the regular line, or purchasing over-the-counter treatments.)
Ghanbari does not explicitly teach wherein the first input pre-processing machine learning model comprises an embedding machine learning model configured to generate an embedding of the first input, the embedding having a lower dimensionality than the first input data, and wherein the first input pre-processing module output comprises the embedding.
However, Molony teaches a first input pre-processing machine learning model comprises an embedding machine learning model configured to generate an embedding of the first input, the embedding having a lower dimensionality than the first input data, and wherein the first input pre-processing module output comprises the embedding:
(Paragraphs [0029] and [0087]-[0090] of Molony. The teaching describes a predictive model that low rate of individuals with a rare disease in the general population, datasets that can be used in training machine-learned models to diagnose the rare disease are often noisy and/or unbalanced. This specification describes methods of generating a reduced noise and/or balanced dataset that, when used to train a machine-learned model, results in a more accurate model (i.e. a model with fewer false positives and/or false negatives). additional features may be identified from the literature 614 using natural language processing (NLP). Vocabulary/tokens representing clinical terms is identified in medical literature (e.g. on a selection of medical publications from PubMED). The medical literature may be selected to include publications related to the rare disease and a selection of disease with similar symptoms. Natural language processing is used to create a mathematical representation of the clinical terms that is based on the context in which those terms are used in the literature. For example, each term may be represented as an embedding vector in a vector space, with words that occur in a similar context occupying close positions in the vector space, i.e. clinical terms occurring in similar contexts have similar embedding vector representations. An example of a natural language processing algorithm that can be used to generate such embedding vectors is Word2Vec (see, for example, “Distributed Representations of Words and Phrases and their Compositionality”, Mikolov et al. 2013, Adv. Neural Inf. Process. Syst, Volume 26). By translating the words to a vector representation this reduces the dimensionality of the data. Furthermore, the identified word/term embeddings can be used to generate a vectorisation of each individual in the training dataset. For each individual, a vector representation of that individual can be created, for example by averaging (e.g. taking the mean of) the embedding vectors of the features associated with the individual. In some embodiments, the embedding of the rare disease term may also be subtracted from this representation to create a final vector representation for the individual. Where a control individual has none of the features of the rare disease, they may be represented by a zero vector. Such vector representations may be used as an additional or alternative input to the machine-learned model.)
It would have been obvious to one of ordinary skill to add to the machine learning based predictive diagnoses of Ghanbari, the machine learning based predictive diagnosis techniques of Molony. Paragraph [0087] of Molony teaches that clinical terms are replaced by vector values for analysis. It is apparent that this vectorization is used to improve the processing functions of the machine learning model in that vector data is more ready to be read by machine means than raw text. One of ordinary skill in the art in possession of Ghanbari would have looked to Molony to achieve this incentive in addition to being in the same field of endeavor. One of ordinary skill in the art would have added to the teaching of Ghanbari, the teaching of Molony based on this incentive without yielding unpredictable results.
The combined teaching of Ghanbari and Molony would have then taught processing, at one or more processors, the first input data using a first input pre-processing module comprising a first input pre-processing machine learning model, to generate a representation of the first input data and to generate a first input pre-processing module output based at least in part on the representation of the first input data, wherein the first input pre-processing machine learning model comprises an embedding machine learning model configured to generate an embedding of the first input, the embedding having a lower dimensionality than the first input data, and wherein the first input pre-processing module output comprises the embedding, processing, at the one or more processors, the first input pre-processing module output comprising the embedding using a preliminary diagnosis machine learning model to determine a preliminary diagnosis output:
(Paragraphs [0007] and [0048] of Ghanbari. The teaching describes a method for diagnosing a patient using a computer system including a processor and memory storing a plurality of instructions to be executed on the processor. In operation 206, the server 10 analyzes the patient's response using a natural language processing (NLP) system to extract key symptoms and aspects of those symptoms such as severity, frequency, duration, type, etc. while the patient speaks and/or types. For example, if a patient entered: “severe headache that started 3 days ago,” then in one embodiment, the NLP system would identify the word “headache” to classify one symptom as being a headache, detect “severe” as being near “headache” and apply the “severe” aspect to the diagnosis and create a temporal map identifying the headache as having started 3 days ago.)
(Paragraphs [0050]-[0055] of Ghanbari. The teaching describes that server 10 analyzes the data in operation 206 to identify likely potential diagnoses and determines if additional information is needed in operation 208. The analysis may use any of a variety of well-known pattern matching systems for associating a given input with a particular result. In embodiments of the present invention, these systems may implement a machine learning algorithm such as a neural network, a Bayesian network, or an expert system. For example, based on the symptoms and details about the symptoms, embodiments of the present invention perform statistical analysis (such as statistical inference) to compare against the diagnostic “fingerprint” of all the disease objects in the system. The system may present the relevant history and symptoms, along with a dynamic differential diagnosis of the patient's condition based on their history and inputs (see, e.g., FIG. 3D), which may also include a rating of the system's confidence in any particular diagnosis. This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. Accordingly, on the most relevant clarifying questions would be presented to the patient and questions that would be less useful in differentiating between the identified likely diagnoses would not be presented, thereby reducing the number of questions that will be asked of the patient. These clarifying questions can then be presented to the patient.)
(Paragraphs [0029] and [0087]-[0090] of Molony. The teaching describes a predictive model that low rate of individuals with a rare disease in the general population, datasets that can be used in training machine-learned models to diagnose the rare disease are often noisy and/or unbalanced. This specification describes methods of generating a reduced noise and/or balanced dataset that, when used to train a machine-learned model, results in a more accurate model (i.e. a model with fewer false positives and/or false negatives). additional features may be identified from the literature 614 using natural language processing (NLP). Vocabulary/tokens representing clinical terms is identified in medical literature (e.g. on a selection of medical publications from PubMED). The medical literature may be selected to include publications related to the rare disease and a selection of disease with similar symptoms. Natural language processing is used to create a mathematical representation of the clinical terms that is based on the context in which those terms are used in the literature. For example, each term may be represented as an embedding vector in a vector space, with words that occur in a similar context occupying close positions in the vector space, i.e. clinical terms occurring in similar contexts have similar embedding vector representations. An example of a natural language processing algorithm that can be used to generate such embedding vectors is Word2Vec (see, for example, “Distributed Representations of Words and Phrases and their Compositionality”, Mikolov et al. 2013, Adv. Neural Inf. Process. Syst, Volume 26). By translating the words to a vector representation this reduces the dimensionality of the data. Furthermore, the identified word/term embeddings can be used to generate a vectorisation of each individual in the training dataset. For each individual, a vector representation of that individual can be created, for example by averaging (e.g. taking the mean of) the embedding vectors of the features associated with the individual. In some embodiments, the embedding of the rare disease term may also be subtracted from this representation to create a final vector representation for the individual. Where a control individual has none of the features of the rare disease, they may be represented by a zero vector. Such vector representations may be used as an additional or alternative input to the machine-learned model.)
As per claim 2,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
Ghanbari further teaches further comprising: receiving second input data at the input, the second input data comprising a plurality of answers responsive to predetermined questions output by the diagnostics system; processing the second input data at a second input pre-processing module comprising a second input pre-processing machine learning model to generate a second input pre-processing module output, the second input pre-processing module output comprising a prediction of at least one problem; and wherein determining the preliminary diagnosis output comprises processing the second input pre-processing module output at the preliminary diagnosis machine learning model and the preliminary diagnosis output is based at least in part on the second input pre-processing module output:
(Paragraphs [0055] of Ghanbari. The teaching describes This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. For example, the patient may modify their representations of their symptoms such as the order in which symptoms appeared or the time at which the pain changed in character (e.g., from dull to sharp). In some embodiments, sliders and other graphical interfaces may be displayed and manipulated for entering and updating answers to questions (e.g., a colored slider for pain scale).)
As per claim 5,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
Ghanbari further teaches wherein determining one or more further diagnoses of the problem comprises providing fifth input data to a machine learning classifier trained to determine the one or more further diagnoses of the problem based upon the fifth input data:
(Paragraphs [0050]-[0055] of Ghanbari. The teaching describes that server 10 analyzes the data in operation 206 to identify likely potential diagnoses and determines if additional information is needed in operation 208. The analysis may use any of a variety of well-known pattern matching systems for associating a given input with a particular result. In embodiments of the present invention, these systems may implement a machine learning algorithm such as a neural network, a Bayesian network, or an expert system. For example, based on the symptoms and details about the symptoms, embodiments of the present invention perform statistical analysis (such as statistical inference) to compare against the diagnostic “fingerprint” of all the disease objects in the system. The system may present the relevant history and symptoms, along with a dynamic differential diagnosis of the patient's condition based on their history and inputs (see, e.g., FIG. 3D), which may also include a rating of the system's confidence in any particular diagnosis. This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. For example, the patient may modify their representations of their symptoms such as the order in which symptoms appeared or the time at which the pain changed in character (e.g., from dull to sharp). In some embodiments, sliders and other graphical interfaces may be displayed and manipulated for entering and updating answers to questions (e.g., a colored slider for pain scale).)
As per claim 7,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
Ghanbari further teaches the limitations of claim further comprising determining, responsive to the one or more further diagnoses, a priority; and wherein the action is determined responsive to the priority:
(Paragraph [0060] of Ghanbari. The teaching describes that the system may present a list of likely diagnoses along with a summary of the data entered by the patient and a list of recommended actions. For example, if the patient is using the system from home, the list of recommended actions may include calling an emergency line, going in to urgent care, making an appointment to see a physician, and/or options and steps for self-administered diagnostics or treatment. Alternatively, if the patient is using the system from a hospital waiting room, the list of recommended actions may include immediately contacting a nurse in a priority line, continuing to wait in the regular line, or purchasing over-the-counter treatments.)
As per claim 9,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
Molony further teaches wherein a preliminary diagnosis machine learning model comprises a gradient boosting decision tree classifier:
(Paragraphs [0029], [0038] and [0040] of Molony. The teaching describes a predictive model that once generated, the training dataset 112 may be divided into a first dataset 118 (also referred to herein as the “learning dataset”) that is used to train a machine-learned model 120, and a second dataset 122 (also referred to herein as a “test dataset”) that is used to test the machine-learned model 120 once it has been trained. During the model training operation 104, supervised machine-learning techniques are used to train a machine-learned model 120 (herein also referred to as a “model”) on the learning dataset 118 to classify an individual as either having or not having the rare disease based on medical data associated with said individual input to the model 120. Due to the low rate of individuals with a rare disease in the general population, datasets that can be used in training machine-learned models to diagnose the rare disease are often noisy and/or unbalanced. This specification describes methods of generating a reduced noise and/or balanced dataset that, when used to train a machine-learned model, results in a more accurate model (i.e. a model with fewer false positives and/or false negatives). The model 120 may include a Light Gradient Boosting Model (LGBM). A LGBM seeks to improve the prediction power by training a sequence of weak models (for example decision trees), each compensating the weaknesses of its predecessors. Use of a LGBM allows for feature selection (e.g. via trees), works well with a high number of features, and takes into account groups of symptoms.)
As per claim 11,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
Molony further teaches wherein a preliminary diagnosis machine learning model comprises first input pre-processing module comprises a plurality of first input pre-processing machine learning models each configured to generate a respective representation of the first input data having a lower dimensionality than the first input data and each trained on a different dataset; and the method comprises generating the first input pre-processing module output based at least in part on the plurality of representations of the first input data:
(Paragraphs [0029] and [0087]-[0090] of Molony. The teaching describes a predictive model that low rate of individuals with a rare disease in the general population, datasets that can be used in training machine-learned models to diagnose the rare disease are often noisy and/or unbalanced. This specification describes methods of generating a reduced noise and/or balanced dataset that, when used to train a machine-learned model, results in a more accurate model (i.e. a model with fewer false positives and/or false negatives). additional features may be identified from the literature 614 using natural language processing (NLP). Vocabulary/tokens representing clinical terms is identified in medical literature (e.g. on a selection of medical publications from PubMED). The medical literature may be selected to include publications related to the rare disease and a selection of disease with similar symptoms. Natural language processing is used to create a mathematical representation of the clinical terms that is based on the context in which those terms are used in the literature. For example, each term may be represented as an embedding vector in a vector space, with words that occur in a similar context occupying close positions in the vector space, i.e. clinical terms occurring in similar contexts have similar embedding vector representations. An example of a natural language processing algorithm that can be used to generate such embedding vectors is Word2Vec (see, for example, “Distributed Representations of Words and Phrases and their Compositionality”, Mikolov et al. 2013, Adv. Neural Inf. Process. Syst, Volume 26). By translating the words to a vector representation this reduces the dimensionality of the data. Furthermore, the identified word/term embeddings can be used to generate a vectorisation of each individual in the training dataset. For each individual, a vector representation of that individual can be created, for example by averaging (e.g. taking the mean of) the embedding vectors of the features associated with the individual. In some embodiments, the embedding of the rare disease term may also be subtracted from this representation to create a final vector representation for the individual. Where a control individual has none of the features of the rare disease, they may be represented by a zero vector. Such vector representations may be used as an additional or alternative input to the machine-learned model.)
As per claim 13,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
Ghanbari further teaches wherein the first input pre-processing module comprises a classifier machine learning model configured to determine, based on the first input data, one or more categories of problem indicated in the first input data:
(Paragraphs [0007] and [0048] of Ghanbari. The teaching describes a method for diagnosing a patient using a computer system including a processor and memory storing a plurality of instructions to be executed on the processor. In operation 206, the server 10 analyzes the patient's response using a natural language processing (NLP) system to extract key symptoms and aspects of those symptoms such as severity, frequency, duration, type, etc. while the patient speaks and/or types. For example, if a patient entered: “severe headache that started 3 days ago,” then in one embodiment, the NLP system would identify the word “headache” to classify one symptom as being a headache, detect “severe” as being near “headache” and apply the “severe” aspect to the diagnosis and create a temporal map identifying the headache as having started 3 days ago.)
As per claim 14,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
Ghanbari further teaches wherein the preliminary diagnosis model is configured to determine a respective probability value for each of a plurality of categories, each respective probability value indicating a confidence that category is associated with the input data; and wherein the method further comprises: determining one or more of the plurality of categories based on the respective probability values; and determining the at least one dialogue system output by determining at least one dialogue system output associated with each of the determined one or more of the plurality of categories:
(Paragraphs [0050]-[0055] of Ghanbari. The teaching describes that server 10 analyzes the data in operation 206 to identify likely potential diagnoses and determines if additional information is needed in operation 208. The analysis may use any of a variety of well-known pattern matching systems for associating a given input with a particular result. In embodiments of the present invention, these systems may implement a machine learning algorithm such as a neural network, a Bayesian network, or an expert system. For example, based on the symptoms and details about the symptoms, embodiments of the present invention perform statistical analysis (such as statistical inference) to compare against the diagnostic “fingerprint” of all the disease objects in the system. Embodiments of the present invention produce a stacked rank of possible diagnoses based on how closely the symptoms match the fingerprints, with a likelihood score and confidence score for each. Based on the stacked rank, embodiments of the present invention may infer clarifying questions that would most statistically differentiate between the possible diagnoses on the differential diagnosis list. The system may present the relevant history and symptoms, along with a dynamic differential diagnosis of the patient's condition based on their history and inputs (see, e.g., FIG. 3D), which may also include a rating of the system's confidence in any particular diagnosis. This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. For example, the patient may modify their representations of their symptoms such as the order in which symptoms appeared or the time at which the pain changed in character (e.g., from dull to sharp). In some embodiments, sliders and other graphical interfaces may be displayed and manipulated for entering and updating answers to questions (e.g., a colored slider for pain scale).)
As per claim 17,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
Ghanbari further teaches wherein at least a part of the first input pre-processing module is operated on a client device; and the preliminary diagnosis model is operated on a server device:
(Paragraphs [0007] and [0048] and Figure 1A of Ghanbari. The teaching describes a method for diagnosing a patient using a computer system including a processor and memory storing a plurality of instructions to be executed on the processor. In operation 206, the server 10 analyzes the patient's response using a natural language processing (NLP) system to extract key symptoms and aspects of those symptoms such as severity, frequency, duration, type, etc. while the patient speaks and/or types. For example, if a patient entered: “severe headache that started 3 days ago,” then in one embodiment, the NLP system would identify the word “headache” to classify one symptom as being a headache, detect “severe” as being near “headache” and apply the “severe” aspect to the diagnosis and create a temporal map identifying the headache as having started 3 days ago. It is seen in Figure 1A that the input data is received from the client device 12a which is considered to be a function of the first input pre-processing module.)
As per claim 22,
Claim 22 is substantially similar to claim 1. Accordingly, claim 22 is rejected for the same reasons as claim 1.
As per claim 23,
Claim 23 is substantially similar to claim 1. Accordingly, claim 23 is rejected for the same reasons as claim 1.
Claims 3, 4, 18 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Ghanbari and Molony in further view of Jain et al. (US 11,302,448; herein referred to as Jain).
As per claim 3,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
The combined teaching of Ghanbari and Molony does not explicitly teach further comprising: receiving third input data from one or more sensors, the third input data comprising a plurality of sensor signals measuring a characteristic of a user; processing the third input data at a third input pre-processing module configured to generate a third input pre-processing module output comprising one or more principal components of the third input data; wherein determining the preliminary diagnosis output comprises processing the third input pre-processing module output at the preliminary diagnosis machine learning model and the preliminary diagnosis machine learning model is configured to determine the preliminary diagnosis output based at least in part on the third input pre-processing module output.
However, Jain teaches using sensor data and survey data to determine, with machine learning models, a predicted likelihood of an infection:
(Column 11 Lines 34-39, Column 14 Lines 63-67 – Column 15 Lines 1-3, and Column 58, Lines 43-61 of Jain. The teaching describes for each of various types of signs or symptoms, there may be multiple elements, e.g., measurements, types of data, or tracked behaviors, that indicate or confirm that a the sign or symptom is present. For example, to detect a fever, the system can detect an elevated temperature, but may also detect signs like chills, perspiration, fatigue or changes in cognition that may be related and may be used to confirm or verify the presence of a fever. Similarly, difficulty breathing may be detected with respiration rate, heart rate variability, and/or reduction in oxygen, with these measured parameters being compared with baseline values, thresholds, or other reference values to identify difficulty breathing. Other symptoms may be detected using device data (e.g., sensor data, device usage data, etc.) and results from various tests, such as taste and smell tests, blood tests, urine tests, swab collections, and so on. The data sets that can be used include active sensing data, passive sensing data, user inputs (such as user responses to surveys and EMAs, EHR/EMR data, clinical data set, and insurance claims data. In some implementations, the disease status of the first user is determined based on a predicted likelihood of infection with the disease for the first user, wherein the predicted likelihood is determined using one or more machine learning models and input to the one or more machine learning models that is derived from at least one of physiological monitoring data for the first user, behavioral monitoring data for the first user, or user inputs provided by the first user. In some implementations, the method includes collecting, for each of multiple users, (i) physiological data indicating one or more physiological measurements determined for the individuals using the user devices, and (ii) user input data indicating survey responses of the individuals provided using the user devices; and wherein at least one of the location tags or the disease transmission scores are determined based on the collected physiological data or the user input data.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the machine learning based diagnosis teachings of the combined teaching of Ghanbari and Molony, the machine learning based diagnosis teachings of Jain. Column 23 Lines 6-15 describes that the methods disclosed by Jain result in the improvement in patient outcomes when identifying and treating a medical condition. One of ordinary skill in the art in possession of the combined teaching of Ghanbari and Molony would have looked to Jain for this reason in addition to their substantially similar subject matter. One of ordinary skill in the art would have add to the combined teaching of Ghanbari and Molony, the teaching of Jain based on these incentives without yielding unexpected results.
The combined teaching of Ghanbari, Molony and Jain would have then taught further comprising: receiving third input data from one or more sensors, the third input data comprising a plurality of sensor signals measuring a characteristic of a user; processing the third input data at a third input pre-processing module configured to generate a third input pre-processing module output comprising one or more principal components of the third input data; wherein determining the preliminary diagnosis output comprises processing the third input pre-processing module output at the preliminary diagnosis machine learning model and the preliminary diagnosis machine learning model is configured to determine the preliminary diagnosis output based at least in part on the third input pre-processing module output:
(Paragraphs [0007] and [0048] of Ghanbari. The teaching describes a method for diagnosing a patient using a computer system including a processor and memory storing a plurality of instructions to be executed on the processor. In operation 206, the server 10 analyzes the patient's response using a natural language processing (NLP) system to extract key symptoms and aspects of those symptoms such as severity, frequency, duration, type, etc. while the patient speaks and/or types. For example, if a patient entered: “severe headache that started 3 days ago,” then in one embodiment, the NLP system would identify the word “headache” to classify one symptom as being a headache, detect “severe” as being near “headache” and apply the “severe” aspect to the diagnosis and create a temporal map identifying the headache as having started 3 days ago.)
(Paragraphs [0050]-[0055] of Ghanbari. The teaching describes that server 10 analyzes the data in operation 206 to identify likely potential diagnoses and determines if additional information is needed in operation 208. The analysis may use any of a variety of well-known pattern matching systems for associating a given input with a particular result. In embodiments of the present invention, these systems may implement a machine learning algorithm such as a neural network, a Bayesian network, or an expert system. For example, based on the symptoms and details about the symptoms, embodiments of the present invention perform statistical analysis (such as statistical inference) to compare against the diagnostic “fingerprint” of all the disease objects in the system. The system may present the relevant history and symptoms, along with a dynamic differential diagnosis of the patient's condition based on their history and inputs (see, e.g., FIG. 3D), which may also include a rating of the system's confidence in any particular diagnosis. This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system.)
(Paragraphs [0055] of Ghanbari. The teaching describes This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. For example, the patient may modify their representations of their symptoms such as the order in which symptoms appeared or the time at which the pain changed in character (e.g., from dull to sharp). In some embodiments, sliders and other graphical interfaces may be displayed and manipulated for entering and updating answers to questions (e.g., a colored slider for pain scale).)
(Column 11 Lines 34-39, Column 14 Lines 63-67 – Column 15 Lines 1-3, and Column 58, Lines 43-61 of Jain. The teaching describes for each of various types of signs or symptoms, there may be multiple elements, e.g., measurements, types of data, or tracked behaviors, that indicate or confirm that a the sign or symptom is present. For example, to detect a fever, the system can detect an elevated temperature, but may also detect signs like chills, perspiration, fatigue or changes in cognition that may be related and may be used to confirm or verify the presence of a fever. Similarly, difficulty breathing may be detected with respiration rate, heart rate variability, and/or reduction in oxygen, with these measured parameters being compared with baseline values, thresholds, or other reference values to identify difficulty breathing. Other symptoms may be detected using device data (e.g., sensor data, device usage data, etc.) and results from various tests, such as taste and smell tests, blood tests, urine tests, swab collections, and so on. The data sets that can be used include active sensing data, passive sensing data, user inputs (such as user responses to surveys and EMAs, EHR/EMR data, clinical data set, and insurance claims data. In some implementations, the disease status of the first user is determined based on a predicted likelihood of infection with the disease for the first user, wherein the predicted likelihood is determined using one or more machine learning models and input to the one or more machine learning models that is derived from at least one of physiological monitoring data for the first user, behavioral monitoring data for the first user, or user inputs provided by the first user. In some implementations, the method includes collecting, for each of multiple users, (i) physiological data indicating one or more physiological measurements determined for the individuals using the user devices, and (ii) user input data indicating survey responses of the individuals provided using the user devices; and wherein at least one of the location tags or the disease transmission scores are determined based on the collected physiological data or the user input data.)
As per claim 4,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
The combined teaching of Ghanbari and Molony does not explicitly teach further comprising: receiving fourth input data from one or more sensors, the fourth input data comprising a plurality of sensor signals measuring a response time of a user when answering each of a plurality of questions output by the dialogue system; processing the fourth input data at a fourth input pre-processing module configured to generate a fourth input pre-processing module output comprising at least one of: an average response time, variation between one or more response times, a minimum response time and a maximum response time; wherein determining the preliminary diagnosis output comprises processing the fourth input pre-processing module output at the preliminary diagnosis machine learning model and the preliminary diagnosis machine learning model is configured to determine the preliminary diagnosis output based at least in part on the fourth input pre-processing module output.
However, Jain teaches using sensor data and time-based survey data to determine, with machine learning models, a predicted likelihood of an infection:
(Column 11 Lines 34-39, Column 14 Lines 63-67 – Column 15 Lines 1-3, 11-15, and Column 58, Lines 43-61 of Jain. The teaching describes for each of various types of signs or symptoms, there may be multiple elements, e.g., measurements, types of data, or tracked behaviors, that indicate or confirm that a the sign or symptom is present. For example, to detect a fever, the system can detect an elevated temperature, but may also detect signs like chills, perspiration, fatigue or changes in cognition that may be related and may be used to confirm or verify the presence of a fever. Similarly, difficulty breathing may be detected with respiration rate, heart rate variability, and/or reduction in oxygen, with these measured parameters being compared with baseline values, thresholds, or other reference values to identify difficulty breathing. Other symptoms may be detected using device data (e.g., sensor data, device usage data, etc.) and results from various tests, such as taste and smell tests, blood tests, urine tests, swab collections, and so on. The data sets that can be used include active sensing data, passive sensing data, user inputs (such as user responses to surveys and EMAs, EHR/EMR data, clinical data set, and insurance claims data. In some implementations, the disease status of the first user is determined based on a predicted likelihood of infection with the disease for the first user, wherein the predicted likelihood is determined using one or more machine learning models and input to the one or more machine learning models that is derived from at least one of physiological monitoring data for the first user, behavioral monitoring data for the first user, or user inputs provided by the first user. In some implementations, the method includes collecting, for each of multiple users, (i) physiological data indicating one or more physiological measurements determined for the individuals using the user devices, and (ii) user input data indicating survey responses of the individuals provided using the user devices; and wherein at least one of the location tags or the disease transmission scores are determined based on the collected physiological data or the user input data. In some implementations, a location tag is generated for a location in response to determining, based on the location tracking data, that a user device: remained at the location for at least a minimum amount of time; and/or moved at the location in a pattern characteristic of a particular activity. Because the timing information identifying a minimum amount of time at a location is based in part on survey data, it is reasonable to conclude that a minimum response time to respond to survey questions at these locations is present as well.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the machine learning based diagnosis teachings of the combined teaching of Ghanbari and Molony, the machine learning based diagnosis teachings of Jain. Column 23 Lines 6-15 describes that the methods disclosed by Jain result in the improvement in patient outcomes when identifying and treating a medical condition. One of ordinary skill in the art in possession of the combined teaching of Ghanbari and Molony would have looked to Jain for this reason in addition to their substantially similar subject matter. One of ordinary skill in the art would have add to the combined teaching of Ghanbari and Molony, the teaching of Jain based on these incentives without yielding unexpected results.
The combined teaching of Ghanbari, Molony and Jain would have then taught further comprising: receiving fourth input data from one or more sensors, the fourth input data comprising a plurality of sensor signals measuring a response time of a user when answering each of a plurality of questions output by the dialogue system; processing the fourth input data at a fourth input pre-processing module configured to generate a fourth input pre-processing module output comprising at least one of: an average response time, variation between one or more response times, a minimum response time and a maximum response time; wherein determining the preliminary diagnosis output comprises processing the fourth input pre-processing module output at the preliminary diagnosis machine learning model and the preliminary diagnosis machine learning model is configured to determine the preliminary diagnosis output based at least in part on the fourth input pre-processing module output:
(Paragraphs [0007] and [0048] of Ghanbari. The teaching describes a method for diagnosing a patient using a computer system including a processor and memory storing a plurality of instructions to be executed on the processor. In operation 206, the server 10 analyzes the patient's response using a natural language processing (NLP) system to extract key symptoms and aspects of those symptoms such as severity, frequency, duration, type, etc. while the patient speaks and/or types. For example, if a patient entered: “severe headache that started 3 days ago,” then in one embodiment, the NLP system would identify the word “headache” to classify one symptom as being a headache, detect “severe” as being near “headache” and apply the “severe” aspect to the diagnosis and create a temporal map identifying the headache as having started 3 days ago.)
(Paragraphs [0050]-[0055] of Ghanbari. The teaching describes that server 10 analyzes the data in operation 206 to identify likely potential diagnoses and determines if additional information is needed in operation 208. The analysis may use any of a variety of well-known pattern matching systems for associating a given input with a particular result. In embodiments of the present invention, these systems may implement a machine learning algorithm such as a neural network, a Bayesian network, or an expert system. For example, based on the symptoms and details about the symptoms, embodiments of the present invention perform statistical analysis (such as statistical inference) to compare against the diagnostic “fingerprint” of all the disease objects in the system. The system may present the relevant history and symptoms, along with a dynamic differential diagnosis of the patient's condition based on their history and inputs (see, e.g., FIG. 3D), which may also include a rating of the system's confidence in any particular diagnosis. This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system.)
(Paragraphs [0055] of Ghanbari. The teaching describes This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. For example, the patient may modify their representations of their symptoms such as the order in which symptoms appeared or the time at which the pain changed in character (e.g., from dull to sharp). In some embodiments, sliders and other graphical interfaces may be displayed and manipulated for entering and updating answers to questions (e.g., a colored slider for pain scale).)
(Column 11 Lines 34-39, Column 14 Lines 63-67 – Column 15 Lines 1-3, 11-15, and Column 58, Lines 43-61 of Jain. The teaching describes for each of various types of signs or symptoms, there may be multiple elements, e.g., measurements, types of data, or tracked behaviors, that indicate or confirm that a the sign or symptom is present. For example, to detect a fever, the system can detect an elevated temperature, but may also detect signs like chills, perspiration, fatigue or changes in cognition that may be related and may be used to confirm or verify the presence of a fever. Similarly, difficulty breathing may be detected with respiration rate, heart rate variability, and/or reduction in oxygen, with these measured parameters being compared with baseline values, thresholds, or other reference values to identify difficulty breathing. Other symptoms may be detected using device data (e.g., sensor data, device usage data, etc.) and results from various tests, such as taste and smell tests, blood tests, urine tests, swab collections, and so on. The data sets that can be used include active sensing data, passive sensing data, user inputs (such as user responses to surveys and EMAs, EHR/EMR data, clinical data set, and insurance claims data. In some implementations, the disease status of the first user is determined based on a predicted likelihood of infection with the disease for the first user, wherein the predicted likelihood is determined using one or more machine learning models and input to the one or more machine learning models that is derived from at least one of physiological monitoring data for the first user, behavioral monitoring data for the first user, or user inputs provided by the first user. In some implementations, the method includes collecting, for each of multiple users, (i) physiological data indicating one or more physiological measurements determined for the individuals using the user devices, and (ii) user input data indicating survey responses of the individuals provided using the user devices; and wherein at least one of the location tags or the disease transmission scores are determined based on the collected physiological data or the user input data. In some implementations, a location tag is generated for a location in response to determining, based on the location tracking data, that a user device: remained at the location for at least a minimum amount of time; and/or moved at the location in a pattern characteristic of a particular activity. Because the timing information identifying a minimum amount of time at a location is based in part on survey data, it is reasonable to conclude that a minimum response time to respond to survey questions at these locations is present as well.)
As per claim 18,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
The combined teaching of Ghanbari and Molony does not explicitly teach wherein the input data is one of a plurality of user inputs each having a different data modality; the method comprises: providing respective ones of the plurality of user inputs to respective input pre-processing modules, each input pre-processing module configured to generate a respective input pre-processing module output for inputting to the preliminary diagnosis model; and wherein determining the preliminary diagnosis output comprises: processing each of the respective input pre-processing module outputs at the preliminary diagnosis machine learning model to provide the preliminary diagnosis output based at least in part on each of the respective input pre-processing module outputs.
However, Jain teaches using sensor data and survey data [different data modalities] to determine, with machine learning models, a predicted likelihood of an infection:
(Column 11 Lines 34-39, Column 14 Lines 63-67 – Column 15 Lines 1-3, and Column 58, Lines 43-61 of Jain. The teaching describes for each of various types of signs or symptoms, there may be multiple elements, e.g., measurements, types of data, or tracked behaviors, that indicate or confirm that a the sign or symptom is present. For example, to detect a fever, the system can detect an elevated temperature, but may also detect signs like chills, perspiration, fatigue or changes in cognition that may be related and may be used to confirm or verify the presence of a fever. Similarly, difficulty breathing may be detected with respiration rate, heart rate variability, and/or reduction in oxygen, with these measured parameters being compared with baseline values, thresholds, or other reference values to identify difficulty breathing. Other symptoms may be detected using device data (e.g., sensor data, device usage data, etc.) and results from various tests, such as taste and smell tests, blood tests, urine tests, swab collections, and so on. The data sets that can be used include active sensing data, passive sensing data, user inputs (such as user responses to surveys and EMAs, EHR/EMR data, clinical data set, and insurance claims data. In some implementations, the disease status of the first user is determined based on a predicted likelihood of infection with the disease for the first user, wherein the predicted likelihood is determined using one or more machine learning models and input to the one or more machine learning models that is derived from at least one of physiological monitoring data for the first user, behavioral monitoring data for the first user, or user inputs provided by the first user. In some implementations, the method includes collecting, for each of multiple users, (i) physiological data indicating one or more physiological measurements determined for the individuals using the user devices, and (ii) user input data indicating survey responses of the individuals provided using the user devices; and wherein at least one of the location tags or the disease transmission scores are determined based on the collected physiological data or the user input data.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the machine learning based diagnosis teachings of the combined teaching of Ghanbari and Molony, the machine learning based diagnosis teachings of Jain. Column 23 Lines 6-15 describes that the methods disclosed by Jain result in the improvement in patient outcomes when identifying and treating a medical condition. One of ordinary skill in the art in possession of the combined teaching of Ghanbari and Molony would have looked to Jain for this reason in addition to their substantially similar subject matter. One of ordinary skill in the art would have add to the combined teaching of Ghanbari and Molony, the teaching of Jain based on these incentives without yielding unexpected results.
The combined teaching of Ghanbari, Molony and Jain would have then taught wherein the input data is one of a plurality of user inputs each having a different data modality; the method comprises: providing respective ones of the plurality of user inputs to respective input pre-processing modules, each input pre-processing module configured to generate a respective input pre-processing module output for inputting to the preliminary diagnosis model; and wherein determining the preliminary diagnosis output comprises: processing each of the respective input pre-processing module outputs at the preliminary diagnosis machine learning model to provide the preliminary diagnosis output based at least in part on each of the respective input pre-processing module outputs:
(Paragraphs [0007] and [0048] of Ghanbari. The teaching describes a method for diagnosing a patient using a computer system including a processor and memory storing a plurality of instructions to be executed on the processor. In operation 206, the server 10 analyzes the patient's response using a natural language processing (NLP) system to extract key symptoms and aspects of those symptoms such as severity, frequency, duration, type, etc. while the patient speaks and/or types. For example, if a patient entered: “severe headache that started 3 days ago,” then in one embodiment, the NLP system would identify the word “headache” to classify one symptom as being a headache, detect “severe” as being near “headache” and apply the “severe” aspect to the diagnosis and create a temporal map identifying the headache as having started 3 days ago.)
(Paragraphs [0050]-[0055] of Ghanbari. The teaching describes that server 10 analyzes the data in operation 206 to identify likely potential diagnoses and determines if additional information is needed in operation 208. The analysis may use any of a variety of well-known pattern matching systems for associating a given input with a particular result. In embodiments of the present invention, these systems may implement a machine learning algorithm such as a neural network, a Bayesian network, or an expert system. For example, based on the symptoms and details about the symptoms, embodiments of the present invention perform statistical analysis (such as statistical inference) to compare against the diagnostic “fingerprint” of all the disease objects in the system. The system may present the relevant history and symptoms, along with a dynamic differential diagnosis of the patient's condition based on their history and inputs (see, e.g., FIG. 3D), which may also include a rating of the system's confidence in any particular diagnosis. This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system.)
(Paragraphs [0055] of Ghanbari. The teaching describes This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. For example, the patient may modify their representations of their symptoms such as the order in which symptoms appeared or the time at which the pain changed in character (e.g., from dull to sharp). In some embodiments, sliders and other graphical interfaces may be displayed and manipulated for entering and updating answers to questions (e.g., a colored slider for pain scale).)
(Column 11 Lines 34-39, Column 14 Lines 63-67 – Column 15 Lines 1-3, and Column 58, Lines 43-61 of Jain. The teaching describes for each of various types of signs or symptoms, there may be multiple elements, e.g., measurements, types of data, or tracked behaviors, that indicate or confirm that a the sign or symptom is present. For example, to detect a fever, the system can detect an elevated temperature, but may also detect signs like chills, perspiration, fatigue or changes in cognition that may be related and may be used to confirm or verify the presence of a fever. Similarly, difficulty breathing may be detected with respiration rate, heart rate variability, and/or reduction in oxygen, with these measured parameters being compared with baseline values, thresholds, or other reference values to identify difficulty breathing. Other symptoms may be detected using device data (e.g., sensor data, device usage data, etc.) and results from various tests, such as taste and smell tests, blood tests, urine tests, swab collections, and so on. The data sets that can be used include active sensing data, passive sensing data, user inputs (such as user responses to surveys and EMAs, EHR/EMR data, clinical data set, and insurance claims data. In some implementations, the disease status of the first user is determined based on a predicted likelihood of infection with the disease for the first user, wherein the predicted likelihood is determined using one or more machine learning models and input to the one or more machine learning models that is derived from at least one of physiological monitoring data for the first user, behavioral monitoring data for the first user, or user inputs provided by the first user. In some implementations, the method includes collecting, for each of multiple users, (i) physiological data indicating one or more physiological measurements determined for the individuals using the user devices, and (ii) user input data indicating survey responses of the individuals provided using the user devices; and wherein at least one of the location tags or the disease transmission scores are determined based on the collected physiological data or the user input data.)
As per claim 19,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
The combined teaching of Ghanbari and Molony does not explicitly teach wherein the input data relates to mental health, the preliminary diagnosis output comprises at least one diagnosis of one or more mental health conditions and the one or more dialogue system outputs comprise questions for confirming or disconfirming the at least one diagnosis of one or more mental health conditions:
However Jain teaches the use of mental health surveys:
(Column 18 Lines 18-24 of Jain. The teaching describes that in some implementations, collecting user input data provided by one or more individuals in the community comprises collecting user input data regarding physiological attributes, behavior, and/or mental health through surveys that each include one or more prompts for user input regarding physiological attributes, behavior, and/or mental health.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the machine learning based diagnosis teachings of the combined teaching of Ghanbari and Molony, the machine learning based diagnosis teachings of Jain. Column 23 Lines 6-15 describes that the methods disclosed by Jain result in the improvement in patient outcomes when identifying and treating a medical condition. One of ordinary skill in the art in possession of the combined teaching of Ghanbari and Molony would have looked to Jain for this reason in addition to their substantially similar subject matter. One of ordinary skill in the art would have add to the combined teaching of Ghanbari and Molony, the teaching of Jain based on these incentives without yielding unexpected results.
The combined teaching of Ghanbari, Molony and Jain would have then taught wherein the input data relates to mental health, the preliminary diagnosis output comprises at least one diagnosis of one or more mental health conditions and the one or more dialogue system outputs comprise questions for confirming or disconfirming the at least one diagnosis of one or more mental health conditions:
(Paragraphs [0050]-[0055] of Ghanbari. The teaching describes that server 10 analyzes the data in operation 206 to identify likely potential diagnoses and determines if additional information is needed in operation 208. The analysis may use any of a variety of well-known pattern matching systems for associating a given input with a particular result. In embodiments of the present invention, these systems may implement a machine learning algorithm such as a neural network, a Bayesian network, or an expert system. For example, based on the symptoms and details about the symptoms, embodiments of the present invention perform statistical analysis (such as statistical inference) to compare against the diagnostic “fingerprint” of all the disease objects in the system. The system may present the relevant history and symptoms, along with a dynamic differential diagnosis of the patient's condition based on their history and inputs (see, e.g., FIG. 3D), which may also include a rating of the system's confidence in any particular diagnosis. This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system.)
(Paragraphs [0055] of Ghanbari. The teaching describes This rating system and dynamic differential diagnosis can be updated in real time as the patient enters, updates, or changes his or her answers to the questions presented by the system. For example, the patient may modify their representations of their symptoms such as the order in which symptoms appeared or the time at which the pain changed in character (e.g., from dull to sharp). In some embodiments, sliders and other graphical interfaces may be displayed and manipulated for entering and updating answers to questions (e.g., a colored slider for pain scale).)
(Column 18 Lines 18-24 of Jain. The teaching describes that in some implementations, collecting user input data provided by one or more individuals in the community comprises collecting user input data regarding physiological attributes, behavior, and/or mental health through surveys that each include one or more prompts for user input regarding physiological attributes, behavior, and/or mental health.)
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Ghanbari and Molony in further view of Bi et al. (US 2008/0288292; herein referred to as Bi).
As per claim 10,
The combined teaching of Ghanbari and Molony teaches the limitations of claim 1.
The combined teaching of Ghanbari and Molony does not explicitly teach wherein the preliminary diagnosis model was trained using a multi-class objective function defined by a combination of a micro averaged accuracy score and a macro averaged accuracy score, wherein the micro averaged accuracy score was defined by an overall accuracy diagnoses output by the preliminary diagnosis model independent of an accuracy of individual diagnosis categories and the macro averaged accuracy score were defined by accuracies of individual diagnosis categories output by the preliminary diagnosis model and averaged with equal weight.
However, Bi teaches the use of a multi-class objective function defined by a combination of a micro averaged accuracy score and a macro averaged accuracy score, wherein the micro averaged accuracy score was defined by an overall accuracy diagnoses output by the preliminary diagnosis model independent of an accuracy of individual diagnosis categories and the macro averaged accuracy score were defined by accuracies of individual diagnosis categories output by the preliminary diagnosis model and averaged with equal weight:
(Paragraphs [0011] and [0072] of Bi. The teaching describes that recently, he Computation Medicine Center sponsored an international challenge task on this type of text classification task. (See http://www.computationalmedicine.org/challenge/index.php.) About 2,216 documents are carefully extracted, including training and testing, and 45 ICD9 labels, with 94 distinct combinations, were used for these documents. More than 40 groups submitted results, and the best macro and micro F1 [micro averaged accuracy score and a macro averaged accuracy score] measures being 0.89 and 0.77, respectively. The competition is a worthy effort in the sense that it provided a test bed to compare different algorithms. Unfortunately, public datasets are to date much smaller than the patient records in even a small hospital. Moreover, many of the documents are very simple, being only one or two sentences. It is challenging to train good classifiers based on such a small data set (even the most common label 786.2 (for “Cough”) has only 155 reports to train on), and the generalizability of the obtained classifiers is also problematic. Classification results on 50 ICD-9 codes with a weighted ridge regression method according to an embodiment of the invention, the canonical ridge regression and linear SVM, are presented herein. The comparison measures are given by the precision, recall, F1 and AUC. The precision, recall and F1 measures are standard criteria in text classification. The AUC criterion offers an overall performance for a classifier. The SVM light toolkit with a linear kernel and default regularization parameter was used. In the experiment, the cost factor was set as the number of negative training examples over the positive one. FIG. 9 is a table that shows the experiment results for the precision, recall, F1, and AUC over all 50 ICD-9 codes for SVM, the canonical ridge regression and the weighted ridge regression. FIG. 10 is a graph of the F1 curves for the canonical ridge regression 101, the weighted ridge regression 102, and the difference curve 103, for the top 50 ICD-9 codes. The order of the codes is sorted by the frequency of codes with the most frequent ones on the top. The maximum values are highlighted over 3 methods for the F1 and AUC measures. As the data becomes more and more unbalanced, the performance of SVM deteriorates even though the cost factor was set accordingly. The weighted ridge regression achieves better results over the canonical ridge regression. For some codes with extreme unbalance, significant improvements can be seen in the table. For example, a weighted ridge regression according to an embodiment of the invention has a 9% improvement in F1 over a canonical ridge regression for the code 410.41, the most infrequent code in the corpus. These results suggest that a weighted ridge method according to an embodiment of the invention outperforms canonical ridge regression and SVM for unbalanced ICD-9 code classification.)
It would have been obvious to one of ordinary skill to add to the machine learning based predictive diagnoses of the combined teaching of Ghanbari and Molony, the machine learning based predictive diagnosis techniques of Bi. Paragraph [0006] of Bi teaches that the methods disclosed result in a greater improved accuracy of medical data analysis. It is apparent that this vectorization is used to improve the processing functions of the machine learning model in that vector data is more ready to be read by machine means than raw text. One of ordinary skill in the art in possession of the combined teaching of Ghanbari and Molony would have looked to Bi to achieve this incentive in addition to being in the same field of endeavor. One of ordinary skill in the art would have added to the combined teaching of Ghanbari and Molony, the teaching of Bi based on this incentive without yielding unpredictable results.
Response to Arguments
Applicant's arguments filed December 11, 2025 have been fully considered.
Applicant’s arguments pertaining to rejections made under 35 U.S.C. 112 are persuasive. The Applicant has amended the issues previously identified by the Examiner
Applicant’s arguments pertaining to rejections made under 35 U.S.C. 101 are not persuasive.
The Applicant further argues that the lower dimensionality of the embedding data in the pending claims provides an improvement to technology, thereby providing a practical application of the abstract idea and provides something significantly more than the abstract idea.
The Examiner respectfully disagrees. As it can be seen in the rejection above. The usage of embeddings to reduce dimensionality in data was well-known, routine and conventional before the time of filing. The Applicant has merely leveraged this existing technology to their particular usage in the claimed medical space. Accordingly, the Examiner does not find that there is an improvement to technology.
The Applicant further argues that the step of receiving additional input data responsive to system output presents a practical action sequence.
The Examiner respectfully disagrees. This step is merely data gathering.
Applicant’s arguments pertaining to rejections made under 35 U.S.C. 102 are persuasive. Ghanbari does not disclose all of the limitations of the independent claims. Accordingly, these rejections are withdrawn.
Applicant’s arguments pertaining to rejections made under 35 U.S.C. 103 are rendered moot in light of the new combination of references used in the current rejection.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHAD A NEWTON whose telephone number is (313)446-6604. The examiner can normally be reached M-F 8:00AM-4:00PM (EST).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, PETER H. CHOI can be reached at (469) 295-9171. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/CHAD A NEWTON/Primary Examiner, Art Unit 3681
Prosecution Insights