DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application is being examined under the pre-AIA first to invent provisions.
Response to Arguments
Applicant’s arguments, see Remarks, filed 12/29/25, with respect to the 103 rejection(s) of claim(s) 1-2, 5-8 under Cohen in view of Lee have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Cohen in view of Lee and Takeuchi. Due to the new rejections, this action is non-final.
Applicant’s previous arguments regarding the rejections under 35 USC 101 have been fully considered, but are not found convincing. Upon further review, the present claim language does not presently show why the claimed invention is more than an abstract idea, i.e., analysis techniques that may be performed by a person or well-known computer components. Further the output instructing a doctor or physician to perform an x-ray or a CT scan is done through a generic output and is recited at a high level of generality (i.e., as generic devices, a “computer-implemented” method, performing generic computer functions like sending, receiving, and visually displaying data) is insignificant extra-solution activity (i.e., data output). Examiner maintains the rejections under 35 USC 101. Further it is noted that the performing of the x-ray or CT scan is not based on the selected test from the system and is not necessarily performed and is not integrated into a practical application.
It is further noted that further analysis of the claims have introduced new 112 issues that are detailed below.
Claims 1-2, 5-8 are active.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-2 and 5-8 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AlA), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AllA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. The claims are directed toward processor that runs a program and performs an x-ray or CT scan. The specification fails to include support for a processor that selects between diagnostic imaging tests and further that selects only between an x-ray or CT scan. Table 2 includes the language of an x-ray or ct scan but fails to show selecting a diagnostic image test that includes only and x-ray or CT scan. It is noted that the originally filed written description fails to describe diagnostic image testing and further choosing only between an x-ray or CT scan. The fact that table 2 shows an example that includes x-ray or ct scan along with other tests, fails to provide support for the use of only the two tests. Further, the specification is silent as to a method that actually performs the test.
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, 2 and 5-8 are rejected under 35 U.S.C. 101 because the claimed inventions are directed to non-statutory subject matter.
Step 1
Independent claim 1 recites a method and program instructions (process) comprising a computer-readable storage medium and executable instructions. Thus, they are directed to statutory categories of invention.
Step 2A, Prong One
Claim 1 recites the following claim limitations:
Obtaining a plurality of physiological values
Determining a first model
Determining a first risk value
Weighting the first risk value based on a second physiological value
Determine a total risk value
Comparing each of the total risk values
Identifying a plurality of possible diagnostic imaging tests
Selecting a diagnostic imaging test
These limitations, under their broadest reasonable interpretation, cover concepts that can be practically performed in the human mind, i.e., using pen and paper. A human could reasonably collect physiological data of a patient, visually observe the physiological data, and perform a mathematical formula or calculation of identifying a subset of data and determining probabilities, including risk values. The processing and weighting are merely analysis techniques for finding patterns and translating in the data, which may be performed in the human mind, or using pen and paper. The claims are drawn to a physician’s mental process of evaluating a patient. Thus, the claims recite limitations which fall within the 'mental processes' grouping of abstract ideas. See MPEP 2106.04(a)(2)(III).
Additionally, reciting converting and visualizing data with little detail of what is being done, also fall within the 'mathematical concepts' grouping of abstract ideas.
Step 2A, Prong Two
Claim 1 recites the following additional elements:
Obtaining, from the patient, a plurality of physiological values
Implementing a first model to determine risk values for at least one medical condition
Obtaining a first risk value for the at least one medical condition based on a first physiological value
Weighting the first risk value based on a second physiological value
Determine a total risk value of the medical condition
Comparing each of the total risk values with a selected threshold
Selecting a diagnostic imaging test out of a plurality of possible diagnostic imaging tests based on a plurality of sets of pathway parameter values
Outputting data
performing the selected diagnosis
Electronically receiving a plurality of measurements is merely insignificant pre-solution activity (See MPEP 2106.05(g)).
The examiner understands the step of processing physiological data (obtained by some means) and performing the processing (by means of a first model) according to a parameter (based on a medical condition) as referring to the mere use of a computer to carry out data processing of the physiological data. In other words, the limitation refers to using a computer to translate physiological data to more easily sort or rank said data. From there, the steps do not appear to be significantly more than the data processing and weighting steps recited in the claims. Furthermore, the data processing steps do not appear to be used to perform any treatment. The steps are merely pattern recognition and ranking of said pattern recognition. Applicant’s disclosure at paras. [0048]-[0051] describes running a computer program on a computer to perform the recited invention, with the computer program, data, and data processing parameters stored on the computer processing means or provided to the processor [0052]-[0054], [0058]-[0064], and the process simply repeated by the computer processing means [0055-0056]. Applicant’s disclosure at para. [0070]-[0090] describes using a mathematical approach to classify the computer processed data to identify patterns and use machine learning to teach the computer system to process the given data and estimate a medical condition risk of a patient. This step is not extra-solution activity, but rather is the, albeit broad, solution related to the computer-implemented process of the claim. However, the requirement to assign this task to a generic computer process or algorithm is neither particular enough to meaningfully limit the recited exception nor does it have more than a nominal relationship to the exception. In other words, the breadth of the recited “physiological values” and “medical condition” used as the basis for processing the data by implemental a computer model, or the recited “weighting” to sort the data for a “total risk value” is such that it substantially encompasses all applications of the recited exception, while basing the data on a particular patient or medical condition for correlation purposes represents a merely nominal relationship with the exception as it associates the implementing/weighting to all resultant likelihoods without condition. In fact, the claimed step effectively constitutes mere instructions to apply the exception in a generic manner using a computer. Further, there is no evidence of record that would support the assertion that this step is an improvement to a computer or a technological solution to a technological problem. Rather, Applicant’s [0094]-[0095] ultimately describes that the process may be performed by any data processing apparatus necessary to perform the method steps, and [0046] and [0084] ultimately describe that the improvement of the claim relates to storing and processing patient data to assign a value of risk for a medical condition based on continued processing and using patterns from the data analysis steps (predictive capabilities) rather than how the claim is using that analysis and/or its results to practically apply the analysis to treat a disease or solve any problem. Although the claims recite determining a total risk value of at least one medical condition, according to patterns of risk values of obtained physiological data, the claims do not recite that the determination causes any transformation to a device, so that the claims are merely reciting data processing and outputting the result. The outputting is merely pattern recognition and sorting the patterns for storing the processed data in the computer. (See MPEP 2106.04(d)(2), 2106.05(a), and 2106.05(f)). The output and implementation steps are recited at a high level of generality (i.e., as generic devices, a “computer-implemented” method, performing generic computer functions like sending, receiving, and visually displaying data) is insignificant extra-solution activity (i.e., data output).
Claim 1 does not recite any particular structure aside from a processor to implement the method steps (of claim 1), with Applicant’s disclosure reciting that the method steps may be implemented in computer programs or hardware with controller and processing means [0093-0094]. Claim 1 method reliance on a processing module and computing device to execute processing of physiological data, which is a high-level of generality, with no converting algorithm being recited, and with little detail of what is happening. The recitation merely refers to instructing processors or a computer to carry out the steps of identifying patterns and visualizing said patterns. In other words, the computer components are being used as a tool to carry out the method (See MPEP 2106.05(f)).
Thus, the abstract idea is not integrated into a practical application. The combination of these additional elements is no more than insignificant extra solution activity, and mere instructions to apply the exception using generic computer components (the processors and computer readable storage media). Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application. The claim is directed to an abstract idea.
Step 2B
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to Step 2A, Prong 2, integration of the abstract idea into a practical application, the additional elements in the claim amount to no more than insignificant extra-solution activity of data gathering and mere instructions to apply the exception using generic computer component(s). The same analysis applies here in 2B and does not provide an inventive concept. Therefore, the claims are not patent eligible. Even when viewed as a whole, nothing in the claim adds significantly more to the abstract idea. Further it is noted that the performing of the x-ray or CT scan is not based on the selected test from the system and is not necessarily performed and is not integrated into a practical application.
Dependent claims
Claims 2 and 5-8 recite the same limitations of collecting physiological data and related parameters, applying computer analysis on said data, identifying patterns or mismatch of the data, and outputting the patterns or mismatch in the form of a risk value and weighting the risk value. The pre-solution activity of data gathering and outputting data are well-understood, routine, and conventional in the field of art. The extra-solution and post-solution activity of further collecting and converting data using computer components, and weighting the data based on data parameters are also well-understood, routine, and conventional in the field of art. (See MPEP 2106.05(d) II. OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014). Even when viewed as a whole in combination with the independent claims 1 and 9, the BRI of claims reciting further analysis and update fail to add significantly more to the abstract idea. See also Elec. Power Grp., LLC v. Alstom S.A. (Fed. Cir. 2016) which contains the following analysis: Information as such is an intangible. See Microsoft Corp. v. AT & T Corp., 550 U.S. 437, 451 n.12 (2007). Accordingly, we have treated collecting information, including when limited to particular content (which does not change its character as information), as within the realm of abstract ideas. See, e.g., Internet Patents, 790 F.3d at 1349; OIP Techs., Inc. v. Amazon. com, Inc., 788 F.3d 1359, 1363 (Fed. Cir. 2015). In a similar vein, we have treated analyzing information by steps people go through in their minds, or by mathematical algorithms, without more, as essentially mental processes within the abstract-idea category. See, e.g., TLI Commc’ns, 823 F.3d at 613; Digitech, 758 F.3d at 1351; SmartGene, Inc. v. Advanced Biological Labs., SA, 555 F. App’x 950, 955 (Fed. Cir. 2014); Bancorp Servs., L.L.C. v. Sun Life Assurance Co. of Canada (U.S.), 687 F.3d 1266, 1278 (Fed. Cir. 2012); CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372 (Fed. Cir. 2011); SiRF Tech., Inc. v. Int’l Trade Comm’n, 601 F.3d 1319, 1333 (Fed. Cir. 2010); see also Mayo, 132 S. Ct. at 1301; Parker v. Flook, 437 U.S. 584, 589–90 (1978); Gottschalk v. Benson, 409 U.S. 63, 67 (1972); Diamond v. Diehr, 450 U.S. 175 (1981).
Claims 2 and 5-8 are also concepts practically performable in the human mind (collecting additional data and comparing against further patterns or classification categories), as well as mathematical concepts (determine risk and weight the risk), and as such, the claims are not patent eligible for the same reasons provided for claims 1 and 9 above. Claims 2 and 5-8, which identify patterns as risk values from collected physiological data and output the patterns or mismatch for risk of a medical condition, merely directed to classification and sorting of data, is well-understood, routine, and conventional in the field of art. We have recognized that merely presenting the results of abstract processes of collecting and analyzing information, without more (such as identifying a particular tool for presentation), is abstract as an ancillary part of such collection and analysis. See, e.g., Content Extraction, 776 F.3d at 1347; Ultramercial, Inc. v. Hulu, LLC, 772 F.3d 709, 715 (Fed. Cir. 2014). Here, the claims are clearly focused on the combination of those abstract-idea processes. The advance they purport to make is a process of gathering and analyzing information of a specified content, then providing the results, and not any particular assertedly inventive technology for performing those functions. They are therefore directed to an abstract idea.
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 pre-AIA 35 U.S.C. 103(a) which forms the basis for all obviousness rejections set forth in this Office action:
(a) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter 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 pre-AIA 35 U.S.C. 103(a) 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.
Claims 1, 2 and 5-8 are rejected under pre-AIA 35 U.S.C. 103(a) as being unpatentable over Cohen et al (US 2018/0068083 A1, hereinafter “Cohen”, previously cited) in view of Lee et al. (US 2019/0065688 hereinafter “Lee”, previously cited) and further in view of Takeuchi et al. (US 2019/0221311, hereinafter “Takeuchi”, previously cited).
Regarding claim 1, Cohen shows a method for diagnosing a medical condition in a patient (para. 0002 – [using an artificial intelligence/machine learning system for analyzing data and making predictions based upon the data, and more specifically, to predicting the likelihood or risk for having a disease such as cancer]), the method comprising using a processor (para. 0018, 0027, 0193): obtaining a plurality of physiological values from the patient (para. 0028 – [measuring the values of a panel of biomarkers in a sample from a patient and obtaining clinical parameters from the patient]; Fig. 11, step 2005; para. 0111 – [measuring the values of a panel of biomarkers in a sample from a patient]); determining total risk values for a plurality of cancers using the plurality of physiological values (para. 29) and a first neural network; wherein each of the total risk values is indicative of a risk that the patient has a respective cancer of the plurality of cancers, the determining comprising (para. 0028 – [utilizing a classifier generated by a machine learning system to classify the patient into a category indicative of a likelihood of having cancer or into another category indicative of a likelihood of not having cancer]; para. 0029 – [risk of having a type of cancer determines follow-up testing]); determining, using a first physiological value of the plurality of physiological values, a first risk value indicative of a risk that the patient has a cancer of the plurality of cancers (para. 0029 – risk of a specific cancer; para. 0096 –[ the presence of the biomarkers are not individually quantified as an absolute value to indicate the presence of a cancer, but the measured values are normalized and the normalized value is aggregated (e.g., summed or weighted and summed, etc.) for inclusion within a biomarker composite score]); and weighting the first risk value using a either factor associated with a second physiological value of the obtained physiological values, associated with at least one weighting value, to determine a total risk value of the at least one medical condition for the patient (para. 0096 – [each marker in the panel may be given a weight of 1, or some other value that is either a fraction of 1 or a multiple of 1, depending on the contribution of the marker to the cancer being screened and the overall composition of the panel]).
Cohen further shows comparing each of the total risk values with a selected threshold (para. 0224 – [may then send a notification to the user (e.g., a physician) recommending additional diagnostic testing (e.g., a CT scan, a chest x-ray or biopsy) when the patient is classified into the category indicative of a likelihood of having cancer]; para. 0034 – [Instead of simply making a determination of the risk of cancer based upon a single marker or multiple biomarkers, wherein the concentrations of the biomarker(s) are evaluated with respect to fixed threshold concentration(s), the machine learning system may also optionally consider a plurality of different types of data]); identifying a plurality of possible diagnostic imaging tests using one or more cancers of the plurality of cancers associated with the one or more of the total risk values; and selecting at least one diagnostic imaging test of the (paras. 0029, 0035, 0111; [determining follow-up testing]), in the event that one or more of the total risk values exceeds the corresponding threshold, selecting at least one diagnostic imaging test for diagnosing the the one or more cancers of the plurality of cancers (para. 0029), wherein each of the plurality of sets of pathway parameter values comprises values of parameters related to implementing a respective diagnostic imaging test (paras. 0029, 0035, 0096, 0224) and then outputting the recommendation to be implemented by a doctor, the one diagnostic imaging test being a CT or an X-ray (para. 0224 – [recommending additional diagnostic testing (e.g., a CT scan, a chest x-ray or biopsy) when the patient is classified into the category indicative of a likelihood of having cancer]).
Cohen shows that selection of the diagnostic imaging test comprises selecting at least one of a plurality of possible diagnostic imaging tests, based on a plurality of sets of pathway parameter values, wherein each set is associated with one of the diagnostic imaging tests (para. 0267-0270 describes that the machine learning method includes additional models of the network to further receive a plurality of additional physiological values associated with at least one medical condition, to further analyze the data according to additional diagnostic imaging tests associated with the physiological values and medical conditions, to be integrated with the machine learning network). Cohen lacks expressly showing implementing a second neural network trained by the same processor to select the diagnostic imaging test out of a plurality of possible diagnostic imaging tests.
Lee teaches that it is known to use machine learning to predict a diagnosis and treatment pathway (e.g. Abstract, paragraphs 2-5) based on ranking data (e.g. para. 0060) using weights assigned to data (e.g. para. 60) to convince a doctor how to proceed (e.g. para. 0021). Lee teaches training and retraining the machine learning model to obtain predictions based on different targets and purposes of a particular model (e.g. Figs. 1 and 3, paras. 39, 43), then using a second particular model to analyze the results of the first model (e.g. para. 45, 51) to output the predicted result and why that prediction is important (e.g. para. 54). Lee is relied upon to teach using multiple models of a system (e.g. para. 39, 43) trained to obtain data and process the data to rearrange and further process the data (e.g. Figs. 1, 3) for a particular diagnostic imaging test, wherein further data and prediction targets may be added to train predicting the diagnostic imaging test (e.g. paras. 39, 43) that leads to predicting a particular one out of a possible plurality of diagnosis or treatment for medical care based on obtained patient physiological parameters (e.g. para. 54). Lee’s machine learning system also teaches ranking importance of what diagnostic imaging test to select (para. 0037) based on sensitivity, specificity and cost to treat a progression of a particular medical condition (e.g. Paras. 45, 51; Fig. 6).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Cohen in view of Lee to provide the benefit of implementing multiple neural networks that basically analyze the analysis (second model assessing results of the first model) to sort through and find possible diagnostic imaging tests and prioritize a selection of one particular diagnostic imaging test for a medical condition based on at least one the parameters comprising at least one of cost, time to completion, time to diagnosis, time to treatment, sensitivity, or specificity, of a given one of the plurality of possible diagnostic imaging tests, as taught by Lee. It would have been obvious to apply Lee’s known neural network system with Cohen’s teaching, above, to implement a second neural network that assesses Cohen’s prediction or likelihood for a cancer and selects a suitable diagnostic imaging test out of a plurality of possible diagnostic imaging tests for the prediction or likelihood of the cancer. The motivation for modification would have been to provide Lee’s beneficial teaching of prioritizing a diagnostic imaging test based on the corresponding medical condition. Furthermore, since the combination of Cohen and Lee renders obvious determining risk values for cancer and selecting a diagnostic imaging test corresponding to cancer, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination to include data and analysis for a plurality of cancers, so that the combination may be beneficially used to assess for different types of cancer and provide a diagnostic imaging test corresponding to one of the plurality of cancers, to more beneficially provide risk assessment and a diagnostic imaging test for different types of cancer to the patient. Cohen in view of Lee teaches the claimed invention but fails to explicitly state that the two machine learning models are neural networks.
However, Takeuchi teaches that it is known to use machine learning to predict a diagnosis and treatment pathway (para. 0042) based on ranking data (para. 0054) using weights assigned to data (paras. 0013, 0019) to convince a doctor how to proceed (para. 0054). Takeuchi teaches training and retraining neural networks of a neural network system to obtain predictions based on different targets and purposes of a particular model (Fig. 1, para. 0039-0040), then using a second particular model to analyze the results of the first model (para. 0040) to output the predicted result and why that prediction is important (Fig. 1, para. 0041). Takeuchi is relied upon to teach using multiple neural networks of a system (para. 0066-0068) trained to obtain data and process the data to rearrange and further process the data (Fig. 2) for a particular diagnostic imaging test, wherein further data and prediction targets may be added to train predicting the diagnostic imaging test (para. 0044-0045, 0051) that leads to predicting a particular one out of a possible plurality of diagnosis or treatment for medical care based on obtained patient physiological parameters (para. 0017, 0019). Takeuchi’s machine learning system also teaches ranking importance of what diagnostic imaging test to select (para. 0037) to treat a progression of a particular medical condition.
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Cohen in view of Lee and further in view of Takeuchi to provide the benefit of implementing multiple neural networks that analyze the analysis (second model assessing results of the first model) to sort through and find possible diagnostic imaging tests and prioritize a selection of one particular diagnostic imaging test for a medical condition, as taught by Takeuchi. It would have been obvious to apply Takeuchi’s known neural network system with Cohen’s teaching, above, to implement a second neural network that assesses Cohen’s prediction or likelihood for a cancer and selects a suitable diagnostic imaging test out of a plurality of possible diagnostic imaging tests for the prediction or likelihood of the cancer. The motivation for modification would have been to provide Takeuchi’s beneficial teaching of prioritizing a diagnostic imaging test based on the corresponding medical condition. Furthermore, since the combination of Cohen, Lee and Takeuchi renders obvious determining risk values for cancer and selecting a diagnostic imaging test corresponding to cancer, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination to include data and analysis for a plurality of cancers, so that the combination may be beneficially used to assess for different types of cancer and provide a diagnostic imaging test corresponding to one of the plurality of cancers, to more beneficially provide risk assessment and a diagnostic imaging test for different types of cancer to the patient.
Regarding claim 2, meeting the limitations of claim 1 above, Cohen shows wherein implementing the first model comprises weighting the risk value, as cited in the rejection of claim 1 above, wherein the weighting is applied to the data in order to properly classify it, and the weights are adjusted in turn as needed to properly determine the likelihood of the at least one cancer (para. 0021), and the data is weighted in order to properly determine the total risk of the at least one cancer (para. 0093). Cohen shows that a plurality of physiological values are collected and analyzed in turn (para. 0093, the collected sequences; para. 0178-0179, subsequently analyzed data for a total risk value; Fig. 3 shows additional physiological data accessed and analyzed to determine a patient’s total risk value), which trains and optimizes determination of the risk of the at least one cancer (Figs. 4A-4B). Based on Cohen’s process of assessing a plurality of physiological values and continually processing additional and subsequent data to optimize determining the risk values of the medical condition, it would have been obvious to one having ordinary skill in the art at the time of invention to have modified the Cohen’s process to sequentially weight the risk value for the at least one medical condition, by each of the plurality of physiological values in turn, as a predictable mathematical aspect of the analysis shown by Cohen.
Regarding claim 5, meeting the limitations of claim 1 above, Cohen in view of Lee and Takeuchi renders obvious the invention of claim 1 above. Cohen teaches in the event that one of the pathway parameter values meets a threshold value, selecting the associated diagnostic imaging test (para. 28-29, 0266, 0268, 0270 – optimal grouping may change as additional data becomes available and analyzed by the further model of the network, to optimize how the data is grouped according to different risk value and diagnosis according to the different risk value, and using the selected associated diagnostic imaging test to modify and train the machine learning network). It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Cohen’s teaching when implementing the second model to select an appropriate prioritized diagnostic imaging test for the correlating medical condition.
Regarding claim 6, meeting the limitations of claim 1 above, Cohen in view of Lee and Takeuchi renders obvious obtaining a diagnostic imaging test data set for one of a plurality of diagnostic imaging tests, said pathway data set comprising a plurality of pathway parameter values for that diagnostic imaging test; and modifying the second model, based on the pathway data set (see the combined rejections of claims 1 and 5 above, which teach the subject matter of claim 6, wherein the machine learning network is modified based on the additional obtained and subsequently analyzed data, to rank the diagnostic imaging tests and select a prioritized diagnostic imaging test for a correlating medical condition).
Regarding claim 7, meeting the limitations of claim 1 above, Cohen in view of Lee and Takeuchi renders obvious modifying the second model comprises weighting each of the pathway parameter values associated with that diagnostic imaging test in the second model, by the corresponding obtained pathway parameter value (para. 0266, 0268, 0270, wherein the weighting adjusts as additional data becomes available and analyzed by the further model of the network, to optimize how the data is grouped according to different risk value and diagnosis according to the different risk value, and using the selected associated diagnostic imaging test to modify and train the machine learning network; Fig. 3 shows additional physiological data accessed and analyzed to determine a patient’s total risk value; training and modifying the network by using the further model to analyze the additional data to optimize determination of the risk of at least one cancer according to the adjusted weights for the associated diagnostic pathways and their associated parameter values, Figs. 4A-4B). It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Cohen’s teaching when implementing the second model to select an appropriate prioritized diagnostic imaging test for the correlating medical condition.
Regarding claim 8, meeting the limitations of claim 1 above, Cohen further shows obtaining a patient data set comprising: a set of physiological values (Fig. 11, step 2005); and a set of indications each identifying the presence or absence of a diagnosis of one of the plurality of medical conditions (Fig. 12, steps 2120 and 2130; para. 0320 – “a determination is made as to whether the classification of the individual patient is consistent with the additional medical information (e.g., the diagnosis of whether or not the patient has cancer)”), which after the modification discussed in the rejection of claim 1 above comprises assessment of a plurality of cancers; and modifying the first model based on the patient data set (para. 0321 – “neural networks are adaptive systems. Through a process of learning by example, rather than conventional programming by different cases, neural networks are able to evolve in response to new data. It is also noted that algorithms for training artificial neural networks”). As discussed in the rejection of claim 1 above, Takeuchi teaches training and retraining learning models based on obtained data and medical parameters, so it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Takeuchi’s method of retraining the neural networks to the combination, so that the first model is retrainable according to further obtained patient data, in order to provide the benefit of staying updated with patient data and medical conditions, and effectively using the first and second models to determine at least one cancer and select a prioritized diagnostic imaging test correlating with the at least one cancer.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REX R HOLMES whose telephone number is (571)272-8827. The examiner can normally be reached Monday-Thursday 7:00AM-5:30PM.
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, Jennifer McDonald can be reached on (571) 270-3061. 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.
/REX R HOLMES/Primary Examiner, Art Unit 3796