DETAILED ACTION
The Applicant’s filing, received 14 September 2023, has been fully considered. The following rejections and/or objections constitute the complete set presently being applied to the instant application.
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 .
Status of the Claims
The preliminary amendment received 14 September 2023 has been entered. Claims 19 and 20 have been amended; the title of the specification has been amended; and the abstract has been amended.
Claims 1-20 are pending.
Claims 1-20 are rejected.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
This application is a 371 of PCT/CN2023/070403, filed 04 January 2023
which claims benefit of foreign application
CHINA 202210190188.5, filed 28 February 2022.
Information Disclosure Statement
The information disclosure statement (IDS) received 11 March 2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement has been considered by the examiner.
Drawings
The drawings received 14 September 2023 have been accepted.
Specification
The amendment to the abstract received 14 September 2023 has been entered.
The amendment to the specification received 14 September 2023 has been entered.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite: (a) mathematical concepts, (e.g., mathematical relationships, formulas or equations, mathematical calculations); and (b) mental processes, i.e., concepts performed in the human mind, (e.g., observation, evaluation, judgement, opinion).
Claim Interpretation
Claims 1-5, 7, 9, 11, and 15-19 recite the term “datum.” This term is interpreted to mean “a single piece of information” such as a subject’s medical history report (e.g., see the specification at para. [0090]; and Fig. 2).
Subject matter eligibility evaluation in accordance with MPEP 2106.
Eligibility Step 1: Step 1 of the eligibility analysis asks: Is the claim to a process, machine, manufacture or composition of matter?
Claims 1-18 recite a method (i.e., a process); claim 19 recites an apparatus comprising a processor and a memory (i.e., a machine and/or a manufacture); and claim 20 recites a non-transitory computer-readable storage medium (i.e., a machine and/or a manufacture).
Therefore, these claims are encompassed by the categories of statutory subject matter, and thus satisfy the subject matter eligibility requirements under step 1.
[Step 1: YES]
Eligibility Step 2A: First it is determined in Prong One whether a claim recites a judicial exception, and if so, then it is determined in Prong Two whether the recited judicial exception is integrated into a practical application of that exception.
Eligibility Step 2A Prong One: In determining whether a claim is directed to a judicial exception, examination is performed that analyzes whether the claim recites a judicial exception, i.e., whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim.
Independent claim 1 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
performing a target process to obtain a disease-analysis vector corresponding to the case-history datum, wherein the target process comprises:
generating a case-history semantic vector of the case-history datum (i.e., mental processes, e.g., creating an array of numbers; and mathematical concepts, e.g., each number in the array corresponds to a specific dimension or feature);
for each of preset diseases in a preset-disease set determining a first possibility weight of the case-history datum caused by the preset disease according to the case-history semantic vector, to obtain a first weight vector (i.e., mental processes, e.g., determine the importance of each feature; and mathematical concepts, e.g., a weight vector can be created by defining a list of numerical values that assign the importance or coefficients to different features or inputs, and can be done as simply as manual assignment based on known importance or domain rules (e.g., [0.5, 0.3, 0.2]));
according to case-history symptoms and case-history diseases in the case-history datum, determining from a predetermined knowledge graph a candidate disease that is capable of generating the case-history datum, wherein the predetermined knowledge graph comprises entities and relations that are relevant to the preset disease, and the candidate disease belongs to the preset-disease set (i.e., mental processes, e.g., to connect, organize, and query related pieces of data across different sources);
determining a second possibility weight of the case-history datum caused by the candidate disease, to obtain a second weight vector (i.e., mental processes, e.g., determine the importance of each feature; and mathematical concepts, e.g., a weight vector can be created by defining a list of numerical values that assign the importance or coefficients to different features or inputs, and can be done as simply as manual assignment based on known importance or domain rules (e.g., [0.5, 0.3, 0.2])); and
fusing the first weight vector and the second weight vector, to obtain the disease-analysis vector corresponding to the case-history datum (i.e., mental processes, e.g., organizing data values; and mathematical concepts, e.g., to fuse two vectors together, you combine them mathematically into a single representation, e.g., the right method depends entirely on whether you want to keep all the original information (called concatenation, i.e., place the second vector at the end of the first vector) or blend the features together using mathematical operations (e.g., addition, multiplication, or averaging)).
Independent claim 19 recites an apparatus comprising a processor, a memory and a program stored in the memory and executable in the processor, and the program, when executed by the processor, implements the mental processes and/or mathematical concepts groupings of abstract ideas recited by independent claim 1, as noted above, and further recites:
wherein the preset-disease set comprises one or more diabetes complications, and each of components of the disease-analysis vector represents an illness probability corresponding to each of the diabetes complications (i.e., mental processes, e.g., evaluating the features in the vector; and mathematical concepts, a probability that corresponds to features in the vector is a mathematical representation).
Independent claim 20 recites a non-transitory computer-readable storage medium, wherein an instruction in the storage medium, when executed by a processor of an electronic device, enables the electronic device to implement the mental processes and/or mathematical concepts groupings of abstract ideas recited by independent claim 1, as noted above.
Dependent claims 2-18 further recite the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas, as noted below.
Dependent claim 2 further recites:
the case-history datum comprises a text datum and a numerical-value datum (i.e., mental processes and mathematical concepts), and the step of generating the case-history semantic vector of the case-history datum comprises:
encoding the text datum into a text semantic vector (i.e., mental processes, e.g., using a lookup table where each word or sentence get a small row of numbers; and mathematical concepts, e.g., passing raw text through a trained machine learning model);
converting the numerical-value datum into a vector, to obtain a numerical-value vector (i.e., mental processes, e.g., grouping feature values into an ordered list or array; and mathematical concepts, e.g., normalization, i.e., scaling values to be in a range between 0 and 1);
stitching the text semantic vector and the numerical-value vector, to obtain a stitched vector (i.e., mental processes and mathematical concepts, e.g., two vectors can be stitched together by concatenation, which joins them end-to-end to form a single, longer vector, or by stacking, which combines them into a multi-dimensional matrix); and
by using a multihead self-attention mechanism, encoding the stitched vector, to obtain the case-history semantic vector of the case-history datum (i.e., mathematical concepts, e.g., multihead self-attention splits an input sequence’s embedding dimensions into smaller, parallel ‘heads’ to compute multiple scaled dot-product attentions).
Dependent claim 3 further recites:
for each of the case-history symptoms in the case-history datum, determining a graph disease subset corresponding to the case-history symptom in the predetermined knowledge graph, to form a graph-disease set (i.e., mental processes, e.g., to connect, organize, and query related pieces of data across different sources); and
according to a case-history-disease set formed by the case-history diseases in the case-history datum, and the graph-disease set, determining a candidate-disease set that is capable of generating the case-history datum (i.e., mental processes, e.g., to connect, organize, and query related pieces of data across different sources).
Dependent claim 4 further recites:
for each of the case-history diseases in the case-history-disease set, if a negative-factor coefficient of the case-history disease is a preset minimum value, deleting the case-history disease from the case-history-disease set, wherein the case-history-disease set obtained after the case-history disease is deleted forms a target-case-history-disease set (i.e., mental processes, e.g., to organizing data within datasets; and mathematical concepts, e.g., comparing values to preset values);
for each of the case-history diseases in the case-history-disease set, if the negative-factor coefficient of the case-history disease is the preset minimum value, and the case-history disease exists in the graph-disease set, deleting the case-history disease from the graph-disease set, wherein the graph-disease set obtained after the case-history disease is deleted forms an initial candidate-disease set (i.e., mental processes, e.g., to organizing data within datasets; and mathematical concepts, e.g., comparing values to preset values); and
for each of target case-history diseases comprised by the target-case-history-disease set, if the target case-history disease does not exist in the initial candidate-disease set, adding the target case-history disease into the initial candidate-disease set, to form the candidate-disease set that is capable of generating the case-history datum (i.e., mental processes, e.g., to organizing data within datasets).
Dependent claim 5 further recites:
according to the negative-factor coefficient of each of the case-history symptoms, a probability of joint occurrence of each of the case-history symptoms and the candidate disease, a quantity of diseases in the graph disease subset to which the candidate disease belongs, and a quantity of diseases in the candidate-disease set, determining an initial second possibility weight of the case-history datum caused by the candidate disease (i.e., mental processes and mathematical concepts, e.g., determining a possibility weight comprises assigning a numerical value that corresponds to a feature);
if the candidate disease satisfies a preset condition, determining the initial second possibility weight corresponding to the candidate disease to be the second possibility weight corresponding to the candidate disease, wherein the preset condition refers to that the candidate disease exists in the initial candidate-disease set but does not exist in the case-history-disease set (i.e., mental processes, e.g., evaluating whether preset conditions are met; and mathematical concepts, e.g., determining a possibility weight comprises assigning a numerical value that corresponds to a feature); and
if the candidate disease does not satisfy the preset condition, correcting the initial second possibility weight corresponding to the candidate disease, to obtain the second possibility weight corresponding to the candidate disease (i.e., mental processes, e.g., evaluating whether preset conditions are met; and mathematical concepts, e.g., determining a possibility weight comprises assigning a numerical value that corresponds to a feature).
Dependent claim 6 further recites:
if the candidate disease exists in both of the case-history-disease set and the initial candidate-disease set, according to a probability of occurrence of the candidate disease, correcting the initial second possibility weight corresponding to the candidate disease, to obtain the second possibility weight corresponding to the candidate disease (i.e., mental processes, e.g., evaluating whether conditions are met; and mathematical concepts, e.g., probability of occurrence and determining a possibility weight comprises assigning a numerical value that corresponds to a feature);
if the candidate disease exists in the case-history-disease set but does not exist in the initial candidate-disease set, according to the negative-factor coefficient of the candidate disease, a preset hyper-parameter and the quantity of the diseases in the candidate-disease set, correcting the initial second possibility weight corresponding to the candidate disease, to obtain the second possibility weight corresponding to the candidate disease (i.e., mental processes, e.g., evaluating whether conditions are met; and mathematical concepts, e.g., correcting a possibility weight comprises assigning a numerical value that corresponds to a feature).
Dependent claim 7 further recites:
according to a degree of negation to the case-history symptom by a first neighboring word located at a position preceding the case-history symptom in the case-history datum, determining the negative-factor coefficient of the case-history symptom, wherein the negative-factor coefficient of the case-history symptom is negatively correlated with the degree of negation to the case-history symptom by the first neighboring word (i.e., mental processes and mathematical concepts, e.g., a negative-factor coefficient is a numeral multiplier that shows an inverse relationship between an input feature and the predicted output); and
according to a degree of negation to the case-history disease by a second neighboring word located at a position preceding the case-history disease in the case-history datum, determining the negative-factor coefficient of the case-history disease, wherein the negative-factor coefficient of the case-history disease is negatively correlated with the degree of negation to the case-history disease by the second neighboring word (i.e., mental processes and mathematical concepts, e.g., a negative-factor coefficient is a numeral multiplier that shows an inverse relationship between an input feature and the predicted output).
Dependent claim 8 further recites:
for a preset disease that does not belong to the candidate-disease set, determining the second possibility weight corresponding to the preset disease to be 0 (i.e., mental processes, e.g., evaluating whether conditions are met; and mathematical concepts, e.g., normalization, i.e., scaling values to be in a range between 0 and 1); and
performing normalization processing to the second possibility weight corresponding to each of the preset diseases, to obtain the second weight vector (i.e., mental processes, e.g., evaluating whether conditions are met; and mathematical concepts, e.g., normalization, i.e., scaling values to be in a range between 0 and 1).
Dependent claim 9 further recites:
acquiring from the predetermined knowledge graph a probability of joint occurrence of each of the case-history symptoms and the candidate disease (i.e., mental processes and mathematical concepts, e.g., utilizing a structured network of information with defined relationships between entities to determine a probability).
Dependent claim 10 further recites:
acquiring from the predetermined knowledge graph a probability of occurrence of each of the candidate diseases (i.e., mental processes and mathematical concepts, e.g., utilizing a structured network of information with defined relationships between entities to determine a probability).
Dependent claim 11 further recites:
performing entity identification to the case-history datum, to obtain entity references in the case-history datum (i.e., mental processes, e.g., detecting, extracting, and disambiguating data);
performing entity linking to the entity references in the predetermined knowledge graph, to obtain matched entities in the predetermined knowledge graph of the entity references (i.e., mental processes, e.g., anchoring ambiguous ‘mentions’ to their unique, correct identifier in the reference knowledge graph);
screening out from the matched entities symptom entities that characterize symptoms, to obtain the case-history symptoms of the case-history datum (i.e., mental processes, e.g., filtering data); and
screening out from the matched entities disease entities that characterize diseases, to obtain the case-history diseases of the case-history datum (i.e., mental processes, e.g., filtering data).
Dependent claim 12 further recites:
for each of the entities comprised by the predetermined knowledge graph, calculating similarities between the entity references and each of the entities (i.e., mental processes and mathematical concepts, e.g., converting graph structures, names, or attributers into mathematical formats and comparing them); and
linking the entity references to a target entity corresponding to a largest similarity of the similarities, to use the target entity as the matched entity in the predetermined knowledge graph of the entity references (i.e., mental processes and mathematical concepts, e.g., converting entity data into vector embeddings and measuring how close they are).
Dependent claim 13 further recites:
for any one of the entities, calculating initial similarities between the entity references and the entity by using at least two similarity calculating modes (i.e., mental processes and mathematical concepts, e.g., converting entity data into vector embeddings and measuring how close they are); and
calculating an average value of the initial similarities that are obtained by calculation, to obtain a similarity between the entity references and the entity (i.e., mental processes and mathematical concepts, e.g., converting entity data into vector embeddings and measuring how close they are).
Dependent claim 14 further recites:
the initial similarities comprise at least two of an edit-distance similarity, a Jaccard similarity, a longest-common-substring similarity, a cosine similarity, an explicit-semantic-analysis similarity and a deep-learning similarity (i.e., mental processes and mathematical concepts, e.g., statistical measures used to quantify how similar two entities are).
Dependent claim 15 further recites:
performing entity identification to the case-history datum according to a predetermined dictionary comprising a plurality of entity names, to obtain the entity references in the case-history datum (i.e., mental processes, e.g., extracting text mentions, performing disambiguation to resolve context, and entity resolution).
Dependent claim 16 further recites:
according to the predetermined dictionary comprising the plurality of entity names, performing entity identification to the case-history datum by using a bidirectional maximum matching algorithm, to obtain the entity references in the case-history datum (i.e., mental processes, e.g., map entities and relations in the graph to a lookup dictionary and run a matching algorithm from both ends of text string to accurately extract entities).
Dependent claim 17 further recites:
the first weight vector and the second weight vector have equal dimensionalities (i.e., mental processes, e.g., evaluating whether two weight vectors contain the exact same number of elements or components);
the dimensionalities are a quantity of diseases in the preset-disease set (i.e., mental processes, e.g., evaluating the type of data in a data set);
weighting the first possibility weight and the second possibility weight with the equal dimensionalities by using different preset importance coefficients, to obtain weighted parameters, wherein a preset importance coefficient corresponding to the first possibility weight and a preset importance coefficient corresponding to the second possibility weight are negatively correlated (i.e., mental processes and mathematical concepts, e.g., assigning weights to a weight vector means setting specific numerical values for each position in the vector using manual input, equal splitting, or mathematical formulas); and
calculating the weighted parameters by using a linear function or a nonlinear function, to obtain fused weights, wherein the fused weights form the disease-analysis vector corresponding to the case-history datum, and the disease-analysis vector has a dimensionality equal to the dimensionalities of the first weight vector and the second weight vector (i.e., mental processes and mathematical concepts, e.g., in machine learning and data processing, assigning fused weights to a weight vector involves calculating context-dependent or optimized importance scores across multiple inputs, models, or data modalities, and mapping them into a unified vector format).
Dependent claim 18 further recites:
inputting the case-history datum into a predetermined analyzing model, so that the predetermined analyzing model performs the target process (i.e., mental processes and mathematical concepts, e.g., inputting data to a model that utilizes mathematical functions to compute the most probable output), and outputs the disease-analysis vector corresponding to the case-history datum (i.e., mental processes and mathematical concepts, e.g., inputting data to a model that utilizes mathematical functions to compute the most probable output); and
before the step of acquiring the case-history datum, the method further comprises:
according to the case-history-datum training set and a predetermined loss function, training an original analyzing model, to obtain an intermediate analyzing model (i.e., mathematical concepts, e.g., training a machine learning model relies on four main mathematical pillars: linear algebra (multiplying feature matrices by weight matrices maps input data into different spaces to separate classes), calculus (measures how changing a model’s internal weights affects its prediction error), probability (computing the probability that a given input belongs to a specific class), and optimization(find the weights that minimize the loss function)); and
testing the intermediate analyzing model according to the case-history-datum test set, to obtain the predetermined analyzing model (i.e., mathematical concepts, e.g., evaluate probability outputs using accuracy, precision, recall, and F1-score on the validation subset).
The abstract ideas recited in the claims are evaluated under the broadest reasonable interpretation (BRI) of the claim limitations when read in light of and consistent with the specification. As noted in the foregoing section, the claims are determined to contain limitations that can practically be performed in the human mind with the aid of a pen and paper (e.g., generating a case-history semantic vector of the case-history datum), and therefore recite judicial exceptions from the mental process grouping of abstract ideas. Additionally, the recited limitations that are identified as judicial exceptions from the mathematical concepts grouping of abstract ideas (e.g., determining a first possibility weight of the case-history datum caused by the preset disease according to the case-history semantic vector, to obtain a first weight vector) are abstract ideas irrespective of whether or not the limitations are practical to perform in the human mind.
Therefore, claims 1-20 recite an abstract idea.
[Step 2A Prong One: YES]
Eligibility Step 2A Prong Two: In determining whether a claim is directed to a judicial exception, further examination is performed that analyzes if the claim recites additional elements that when examined as a whole integrates the judicial exception(s) into a practical application (MPEP 2106.04(d)). A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception. The claimed additional elements are analyzed to determine if the abstract idea is integrated into a practical application (MPEP 2106.04(d)(I); MPEP 2106.05(a-h)). If the claim contains no additional elements beyond the abstract idea, the claim fails to integrate the abstract idea into a practical application (MPEP 2106.04(d)(III)).
The judicial exceptions identified in Eligibility Step 2A Prong One are not integrated into a practical application because of the reasons noted below.
In the instant application, independent claims 1, 19 and 20 provide additional elements to acquire data and analyze the data. However, once the data is acquired, the subsequent steps only perform analysis and/or calculations using the data, e.g., to create a fused weighted data vector (claims 1 and 20) wherein the preset-disease set comprises one or more diabetes complications, and each of components of the disease-analysis vector represents an illness probability corresponding to each of the diabetes complications (claim 19). Thus, the claims do not recite any limitations to which the fused weighted data vector result is practically applied.
Dependent claims 2-17 do not further recite any elements in addition to the judicial exception, and thus are part of the judicial exception.
The additional elements in independent claim 1 include:
acquiring a case-history datum.
The additional elements in independent claim 19 include:
an apparatus comprising a processor, a memory, and a program stored in the memory; and
acquiring a case-history datum.
The additional elements in independent claim 20 include:
a non-transitory computer-readable storage medium;
a processor of an electronic device; and
acquiring a case-history datum.
The additional element in dependent claim 18 includes:
acquiring a case-history-datum training set and a case-history-datum test set.
The additional elements of an apparatus comprising a processor, a memory, and a program stored in the memory (claim 19); a non-transitory computer-readable storage medium (claim 20); and a processor of an electronic device (claim 20); invoke a computer and/or computer-related components merely as tools for use in the claimed process, such that they amount to no more than mere instructions to apply the exceptions using a generic computer (MPEP 2106.05(f)), and therefore are not an improvement to computer functionality itself, or an improvement to any other technology or technical field, and thus, do not integrate the judicial exceptions into a practical application (MPEP 2106.04(d)(1)).
The additional elements of acquiring a case-history datum (claims 1, 19 and 20); and acquiring a case-history-datum training set and a case-history-datum test set (claim 18); are merely pre-solution activities of gathering data for use in the claimed process – a nominal or tangential addition to the claims that does not meaningfully limit the claims, and therefore does not add more than insignificant extra-solution activity to the judicial exceptions (MPEP 2106.05(g)).
Thus, the additionally recited elements merely invoke a computer and/or computer related components as tools; and/or amount to insignificant extra-solution activity; and/or a field of use in which to apply a judicial exception; and as such, when all limitations in claims 1-20 have been considered as a whole (i.e., the analysis takes into consideration all the claim limitations and how those limitations interact and impact each other when evaluating whether the exception is integrated into a practical application), the claims are deemed to not recite any additional elements that would integrate a judicial exception into a practical application, and therefore claims 1-20 are directed to an abstract idea (MPEP 2106.04(d)).
[Step 2A Prong Two: NO]
Eligibility Step 2B: Because the claims recite an abstract idea, and do not integrate that abstract idea into a practical application, the claims are probed for a specific inventive concept. The judicial exception alone cannot provide that inventive concept or practical application (MPEP 2106.05). Identifying whether the additional elements beyond the abstract idea amount to such an inventive concept requires considering the additional elements individually and in combination to determine if they amount to significantly more than the judicial exception (MPEP 2106.05A i-vi).
The claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception(s) because of the reasons noted below.
Dependent claims 2-17 do not further recite any elements in addition to the judicial exception(s).
The additional elements recited in independent claims 1, 19 and 20 and dependent claim 18 are identified above, and carried over from Step 2A Prong Two along with their conclusions for analysis at Step 2B. Any additional element or combination of elements that was considered to be insignificant extra-solution activity at Step 2A Prong Two was re-evaluated at Step 2B, because if such re-evaluation finds that the element is unconventional or otherwise more than what is well-understood, routine, conventional activity in the field, this finding may indicate that the additional element is no longer considered to be insignificant; and all additional elements and combination of elements were evaluated to determine whether any additional elements or combination of elements are other than what is well-understood, routine, conventional activity in the field, or simply append well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, per MPEP 2106.05(d).
The additional elements of an apparatus comprising a processor, a memory, and a program stored in the memory (claim 19); a non-transitory computer-readable storage medium (claim 20); a processor of an electronic device (claim 20); and acquiring data (claims 1, 18, 19 and 20) are conventional computer components and/or functions (see MPEP at 2106.05(b) and 2106.05(d)(II) regarding conventionality of computer components and computer processes).
Therefore, when taken alone (i.e., individually), all additional elements in claims 1-20 do not amount to significantly more than the above-identified judicial exception(s). Even when evaluated as an ordered combination, the additional elements fail to transform the exception(s) into a patent-eligible application of that exception. Thus, claims 1-20 are deemed to not contribute an inventive concept, i.e., amount to significantly more than the judicial exception(s) (MPEP 2106.05(II)).
[Step 2B: NO]
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.
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.
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.
Claims 1-18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Gazzotti et al. (“Extending electronic medical records vector models with knowledge graphs to improve hospitalization prediction.” Journal of Biomedical Semantics, 2022, vol. 13:6, pp. 1-20) and Kwak et al. (“Interpretable disease prediction using heterogeneous patient records with self-attentive fusion encoder.” Journal of the American Medical Informatics Association, 2021, vol. 28(10), pp. 2155-2164).
Independent claim 1 encompasses a method for processing medical data to obtain a disease-analysis vector corresponding to a case-history datum, comprising steps of acquiring a case-history datum; generating a case-history semantic vector of the case-history datum; for each of preset diseases in a preset-disease set determining a first possibility weight of the case-history datum caused by the preset disease according to the case-history semantic vector, to obtain a first weight vector; according to case-history symptoms and case-history diseases in the case-history datum, determining from a predetermined knowledge graph a candidate disease that is capable of generating the case-history datum, wherein the predetermined knowledge graph comprises entities and relations that are relevant to the preset disease, and the candidate disease belongs to the preset-disease set; determining a second possibility weight of the case-history datum caused by the candidate disease, to obtain a second weight vector; and fusing the first weight vector and the second weight vector, to obtain the disease-analysis vector corresponding to the case-history datum.
Independent claim 20 encompasses a non-transitory computer-readable storage medium, wherein an instruction in the storage medium, when executed by a processor of an electronic device, enables the electronic device to implement the method for processing medical data according to claim 1.
Dependent claims 2-18 further define the steps for processing medical data to obtain a disease-analysis vector corresponding to a case-history datum.
Gazzotti et al. teaches an approach that enriches vector representation of electronic medical records (EMRs) with information extracted from different knowledge graphs before learning and predicting that significantly improves the prediction of medical events.
Kwak et al. teaches an interpretable disease prediction model that efficiently fuses multiple types of patient records using a self-attentive fusion encoder.
Regarding independent claims 1 and 20, Gazzotti et al. shows performing semantic enrichment of electronic medical records to generate ontology-augmented vector models as representations of the electronic medical records (see for example page 8, col. 2, paras. 2-3) providing for the claim step of ‘acquiring a case-history…’ dataset and the claim step of ‘generating…’ a semantic vector for the data; Gazzotti et al. further shows enriching private data (electronic medical records) with public data (bio-medical knowledge graphs) (page 2, col. 1, para. 2) to enrich the vector representations used by machine learning algorithms (page 2, col. 1, para. 3) to tackle the general research question of ‘which contribution from knowledge graphs can improve the prediction of the occurrence of an event’ (page 2, col. 1, para. 4) providing for the ‘according to case-history…’ step of the claim by showing a step of using known disease data and correlating it to the case history data; and Gazzotti et al. further shows a list of manually selected concepts to determine a hospitalization (e.g., types of diseases) (Table 4) thereby providing generally that certain data represents stronger correlations with disease diagnosis and standard of care treatments.
Regarding independent claims 1 and 20, Gazzotti et al. does not show specifically for each of preset diseases in a preset-disease set determining a first possibility weight of the case-history datum caused by the preset disease according to the case-history semantic vector, to obtain a first weight vector (claims 1 and 20); nor determining a second possibility weight of the case-history datum caused by the candidate disease, to obtain a second weight vector (claims 1 and 20); nor fusing the first weight vector and the second weight vector, to obtain the disease-analysis vector corresponding to the case-history datum (claims 1 and 20).
Regarding independent claims 1 and 20, Kwak et al. shows for disease models that an attention mechanism allows a model to place more attention weights on the parts of the model that are more relevant to the given prediction (page 2156, col. 2, para. 3); given all of the attention weights, the visits with higher attention weights are considered to be more critical to CVD (cardiovascular disease) diagnoses since they had a greater impact on the final prediction results (page 2160, col. 2, para. 2; and Figure 4); an RNN model to process the patient’s visit history given as the sequence of the visit embedding vectors, which is v = (v1, v2, …, vT) (page 2158, col. 1, para. 2); and a model architecture with the representations of the visits and the patient characteristics fused using the feature-based gating and the self-attention (page 2158, col. 2, para. 1; and Figure 1), i.e., a combination of temporal patient records with patient characteristics using a self-attentive fusion mechanism (page 2156, col. 2, para. 3).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method shown by Gazzotti et al. by incorporating methods for an interpretable disease prediction model that efficiently fuses multiple types of patient records using a self-attentive fusion encoder, as shown by Kwak et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the methods of Gazzotti et al. with the methods of Kwak et al., because Kwak et al. shows a model architecture wherein the RNN representations of the patient’s visits and the patient characteristics are fused using feature-based gating and self-attention. This modification would have had a reasonable expectation of success given that both Gazzotti et al. and Kwak et al. disclose methods applying machine learning methods to electronic medical records to make predictions of medical events.
Regarding dependent claim 2, Kwak et al. further shows using an attention mechanism with recurrent neural networks (RNNs) (e.g., page 2156, col. 1, para. 3; and throughout); obtaining a computable input vector from a patient’s records (page 2157, col. 2, para. 3); fusing heterogeneous patient records using a self-attentive fusion encoder (page 2162, col. 2, para. 2); and further shows a standard machine learning approach to incorporate patient characteristics involves having the RNN features concatenated (i.e., stitched) with the vector encoding of the patient characteristics (Figure 2).
Regarding dependent claim 3, Gazzotti et al. further shows variations and notation of feature sets extracted from knowledge graphs for enriching the vector representations, and generating subsets of the labeled features extracted from the records database (page 13, col. 2, bottom, through page 15, col. 1, para. 1).
Regarding dependent claims 4-7 and 12-14, Gazzotti et al. further shows a table of correlation metric values between experts and machine annotators (its value ranges from 0 to 2, meaning that 0 is a perfect correlation, 1 no correlation and 2 perfect negative correlation) and comparing pairs of vectors in this table and determining if they are relevant, irrelevant or not annotated to study the patient’s hospitalization risks (page 15, col. 1, para. 2; and Table 6) in order to enrich the vector representation of electronic medical records (EMRs) by using selected features extracted from multiple knowledge graphs (page 18, col. 2, paras. 2-4).
Regarding dependent claim 8, Kwak et al. further shows that after features are selected with respect to the patient characteristics, the self-attention mechanism is applied over the updated visit representations using a learnable weight matrix (page 2158, col. 2, para. 2) and subsequently computing the normalized attention score (page 2158, col. 2, para. 3).
Regarding dependent claims 9 and 10, Gazzotti et al. further shows using factors extracted from a knowledge graph that are strongly involved in predicting a patient’s hospitalization and on which a general practitioner (GP) can intervene (page 3, col. 2, Scenario 1; and Fig. 1).
Regarding dependent claim 11, Gazzotti et al. further shows a workflow to link ATC codes, ICPC-2 codes and named entities in the electronic medical records (EMRs) with medical domain ontologies and with the knowledge graphs Wikidata and DBpedia (Fig. 6); and a methodology to select knowledge and inject it in a vector representation of the EMRs (page 3, col. 1, para. 1).
Regarding dependent claims 15 and 16, Gazzotti et al. further shows having identified named entities in free-text fields of electronic medical records (EMRs) by using both a dictionary based approach to handle abbreviations and the semantic annotator DBpedia Spotlight (page 10, col. 2, para. 1; and Table 5).
Regarding dependent claim 17, Kwak et al. further shows using an attention mechanism with recurrent neural networks (RNNs) (e.g., page 2156, col. 1, para. 3; and throughout); obtaining a computable input vector from a patient’s records (page 2157, col. 2, para. 3); and fusing heterogeneous patient records using a self-attentive fusion encoder (page 2162, col. 2, para. 2).
Regarding dependent claim 18, Kwak et al. further shows training a model using pretrained embedding vectors and further shows optimizing hyperparameters and dropout rates (page 2159, col. 2, para. 4); and further shows for each dataset, using 80% of the data for training, 10% for validation, and the remaining 10% for testing (page 2159, col. 2, para. 1).
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Gazzotti et al. (“Extending electronic medical records vector models with knowledge graphs to improve hospitalization prediction.” Journal of Biomedical Semantics, 2022, vol. 13:6, pp. 1-20, as cited above) and Kwak et al. (“Interpretable disease prediction using heterogeneous patient records with self-attentive fusion encoder.” Journal of the American Medical Informatics Association, 2021, vol. 28(10), pp. 2155-2164, as cited above) and Ljubic et al. (“Predicting complications of diabetes mellitus using advanced machine learning algorithms.” Journal of the American Medical Informatics Association, 2020, vol. 27(9), pp. 1343-1351).
Independent claim 19 encompasses an apparatus for predicting a diabetes complication, wherein the apparatus comprises a processor, a memory and a program stored in the memory and executable in the processor, and the program, when executed by the processor, implements the steps of the method for processing medical data according to claim 1, to obtain the disease-analysis vector corresponding to the case-history datum, wherein the preset-disease set comprises one or more diabetes complications, and each of components of the disease-analysis vector represents an illness probability corresponding to each of the diabetes complications.
Gazzotti et al. teaches an approach that enriches vector representation of electronic medical records (EMRs) with information extracted from different knowledge graphs before learning and predicting that significantly improves the prediction of medical events.
Kwak et al. teaches an interpretable disease prediction model that efficiently fuses multiple types of patient records using a self-attentive fusion encoder.
Ljubic et al. teaches using advanced machine learning algorithms for predicting complication of diabetes mellitus electronic medical record types of data.
Regarding independent claim 19, Gazzotti et al. shows performing semantic enrichment of electronic medical records to generate ontology-augmented vector models as representations of the electronic medical records (see for example page 8, col. 2, paras. 2-3) providing for the claim step of ‘acquiring a case-history…’ dataset and the claim step of ‘generating…’ a semantic vector for the data; Gazzotti et al. further shows enriching private data (electronic medical records) with public data (bio-medical knowledge graphs) (page 2, col. 1, para. 2) to enrich the vector representations used by machine learning algorithms (page 2, col. 1, para. 3) to tackle the general research question of ‘which contribution from knowledge graphs can improve the prediction of the occurrence of an event’ (page 2, col. 1, para. 4) providing for the ‘according to case-history…’ step of the claim by showing a step of using known disease data and correlating it to the case history data; and Gazzotti et al. further shows a list of manually selected concepts to determine a hospitalization (e.g., types of diseases) (Table 4) thereby providing generally that certain data represents stronger correlations with disease diagnosis and standard of care treatments.
Regarding independent claim 19, Gazzotti et al. does not show specifically for each of preset diseases in a preset-disease set determining a first possibility weight of the case-history datum caused by the preset disease according to the case-history semantic vector, to obtain a first weight vector; nor determining a second possibility weight of the case-history datum caused by the candidate disease, to obtain a second weight vector; nor fusing the first weight vector and the second weight vector, to obtain the disease-analysis vector corresponding to the case-history datum; nor wherein the preset-disease set comprises one or more diabetes complications, and each of components of the disease-analysis vector represents an illness probability corresponding to each of the diabetes complications.
Regarding independent claim 19, Kwak et al. shows for disease models that an attention mechanism allows a model to place more attention weights on the parts of the model that are more relevant to the given prediction (page 2156, col. 2, para. 3); given all of the attention weights, the visits with higher attention weights are considered to be more critical to CVD (cardiovascular disease) diagnoses since they had a greater impact on the final prediction results (page 2160, col. 2, para. 2; and Figure 4); an RNN model to process the patient’s visit history given as the sequence of the visit embedding vectors, which is v = (v1, v2, …, vT) (page 2158, col. 1, para. 2); and a model architecture with the representations of the visits and the patient characteristics fused using the feature-based gating and the self-attention (page 2158, col. 2, para. 1; and Figure 1), i.e., a combination of temporal patient records with patient characteristics using a self-attentive fusion mechanism (page 2156, col. 2, para. 3).
Regarding independent claim 19, Gazzotti et al. and Kwak et al. do not show wherein the preset-disease set comprises one or more diabetes complications, and each of components of the disease-analysis vector represents an illness probability corresponding to each of the diabetes complications
Regarding independent claim 19, Ljubic et al. shows using a recurrent neural network (RNN) gated recurrent unit (GRU) to predict if patients with type 2 diabetes mellitus (DM2) would develop 10 selected complications by using data from electronic medical records (Abstract).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method shown by Gazzotti et al. by incorporating methods for an interpretable disease prediction model that efficiently fuses multiple types of patient records using a self-attentive fusion encoder, as shown by Kwak et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the methods of Gazzotti et al. with the methods of Kwak et al., because Kwak et al. shows a model architecture wherein the RNN representations of the patient’s visits and the patient characteristics are fused using feature-based gating and self-attention. This modification would have had a reasonable expectation of success given that both Gazzotti et al. and Kwak et al. disclose methods applying machine learning methods to electronic medical records to make predictions of medical events.
It would have been further prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method shown by Gazzotti et al. by incorporating methods for using machine learning algorithms for predicting complications of diabetes mellitus using electronic medical records, as shown by Ljubic et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the methods of Gazzotti et al. with the methods of Ljubic et al., because Ljubic et al. shows methods for using a recurrent neural network (RNN) gated recurrent unit (GRU) to predict if patients with type 2 diabetes mellitus (DM2) would develop 10 selected complications by using data from electronic medical records. This modification would have had a reasonable expectation of success given that both Gazzotti et al. and Ljubic et al. disclose methods for applying machine learning methods to electronic medical records to make predictions of medical events.
Conclusion
No claims are allowed.
This Office action is a Non-Final action. A shortened statutory period for reply to this action is set to expire THREE MONTHS from the mailing date of this application.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to STEVEN W. BAILEY whose telephone number is (571)272-8170. The examiner can normally be reached Mon - Fri. 1000 - 1800.
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, KARLHEINZ SKOWRONEK can be reached at (571) 272-9047. 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.
/STEVEN W. BAILEY/Examiner, Art Unit 1687
Prosecution Insights