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 .
DETAILED ACTION
Claims 1-20 are pending. Claims 1, 5, and 20 are independent.
This Application was published as US 20230307115.
Apparent priority is 22 March 2022.
The instant Application is directed to a method of diagnosing and treating depression based on training a machine learning model with Electronic Health Records.
Applicant’s amendments and arguments are considered but are either unpersuasive or moot in view of the new grounds of rejection that, if presented, were necessitated by the amendments to the Claims.
This action is Final.
Response to Amendments
Amendments to claim 5 introduced issues under 35 USC 112 (a) and (b) which are discussed below. For the purposes of prosecution, “second user” (claim 5, last line) will be interpreted to mean “first user.”
Response to Arguments
35 USC 103
Applicant's arguments have been fully considered but they are either moot or unpersuasive.
Applicant argues that the cited references do not teach: “based on the risk score, automatically initiating prophylactic intervention for the second user, the prophylactic intervention including at least one prophylactic media component," wherein initiating the prophylactic intervention includes "selecting the prophylactic media component based on a resident profile of the second user, wherein the prophylactic media component is linked with the resident profile and personalized to the second user."
Arguments regarding “automatically initiating prophylactic intervention” are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Arguments regarding "selecting the prophylactic media component based on a resident profile of the second user, wherein the prophylactic media component is linked with the resident profile and personalized to the second user" are not persuasive.
Hasselberg discloses “[0051] … In other cases, the mental-health-treatment-delivery-server may provide additional features such as other modules with customizable content (e.g., visual or audio cues) based on preferences of the patient. For instance, a patient that has provided responses indicating to the mental-health-treatment-delivery-server that the patient is moving to an elevated stress level, such as a higher than an average stress level of the user, the mental-health-treatment-delivery-server may prompt that patient to view a calming module of content presented by the client device.” Providing customized content based on patient preferences and responses reads on selecting a prophylactic media component based on the user and personalized to the user. [0021] further details the customization. See also [0024] and [0026] which discloses storing electronic health records.
Hasselberg also discloses: “[0030]… In some cases, the user device may adjust the menu of options based on a particular user that has been authenticated or a previous session of use. For instance, the user device may modify the presented menu of options based on previously completed modules, additional modules unlocked by past session completion (e.g., a usage streak, a completion percentage, etc.), or other factors relating to the authenticated user. In one aspect, a user device may have multiple user profiles associated with corresponding mental therapy treatments. In a configuration with multiple users associated with a user device, the user device may use authentication credentials unique to each user of the user device.” This clearly shows that modules are linked with the user’s profile.
Therefore, the rejection is maintained.
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 5-19 rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), 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-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 5 includes outputting media to a second user (last line) based on a resident profile of a first user. This is not supported by the originally filed application.
Claims 6-19 rejected as depending on claim 5.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 5-19 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 5 recites the limitation "the second user" in the last line. There is insufficient antecedent basis for this limitation in the claim.
Claims 6-19 rejected as dependent on claim 5.
Claim Rejections - 35 USC § 103
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.
Claim(s) 1-2, 4-6, and 8-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (US 20210375468 A1) in view of Dibari et al. (US 11581093 B2), Heruth et al. (US 20050209644 A1), Hasselberg et al. (US 20200402642 A1), and Lisic et al. (US 20230238019 A1).
Regarding claim 1, Zhang discloses: 1. A method, comprising:
receiving user data describing a first user; (Fig. 1, 120 shows various patient data; see also “One general aspect includes a computer implemented method including, in a processor including a memory, performing the steps of: receiving health data for a patient;” [0009])
extracting, from the user data, a first set of user attributes corresponding to a defined set of features, (Fig. 1, Variable extraction 140)
wherein at least a first attribute of the first set of user attributes is generated by processing unstructured text using a first trained machine learning model, ("Extraction of features using natural language processing techniques may facilitate higher performance in some embodiments." [0067]; “An end-to-end framework extracts features from EHR data for processing, including demographics, clinical diagnoses, medication prescriptions, laboratory results, and unstructured clinical notes. These data can be sent to an optimization process to select important features and incorporated in multiple machine learning algorithms” [0055])
comprising: generating a set of scores by, for each respective note of a plurality of notes in the user data, processing the respective note using the first trained machine learning model to generate a respective score of the set of scores; and aggregating the set of scores to generate the first attribute, comprising determining a percentage of the plurality of notes having a respective score exceeding a defined threshold; (not explicitly disclosed)
training a second machine learning model to generate risk scores based on the first set of user attributes, (Fig. 1, Model Training 191; see following limitation regarding risk score)
wherein the risk scores indicate probability that users have or will develop depression; ("based on the health data for the patient, computing a risk score of the patient's risk of developing postpartum depression as a function of features selected from the health data for the patient;" [0009])
deploying the second trained machine learning model; (See Fig. 1, After Clinical Validation 192, if the criteria is met, the model training proceeds to complete. Further, Fig. 7 shows an example of deploying the trained model for an individual.)
generating, based on processing user data of a second user using the second trained machine learning model, a risk score indicating a probability that the second user has or will develop depression; (The example of Fig. 7 implies that the user is a new user since the data must be pulled from the EHR. Fig. 1 indicates multiple users in the training data, so any of those users reads on a first user even if the second user’s data is also used for training. Additionally, at least [0084] discloses that the model can be used for multiple patients.)
and based on the risk score, automatically initiating prophylactic intervention for the second user, (Fig. 6 shows possible interventions but they are not automatically initiated)
the prophylactic intervention including at least one prophylactic media component, comprising: selecting the prophylactic media component based on a resident profile of the second user, wherein the prophylactic media component is linked with the resident profile and personalized to the second user; and outputting the prophylactic media component to the second user. (not explicitly disclosed)
Zhang does not disclose: a first trained machine learning model (for generating the first attribute by processing unstructured text), and generating a set of scores by, for each respective note of a plurality of notes in the user data, processing the respective note using the first trained machine learning model to generate a respective score of the set of scores; and aggregating the set of scores to generate the first attribute, comprising determining a percentage of the plurality of notes having a respective score exceeding a defined threshold; and selecting and outputting media based on and customized to a user. Zhang does not disclose the intervention is automatically initiated.
Dibari discloses: wherein at least a first attribute of the first set of user attributes is generated by processing unstructured text using a first trained machine learning model; (“In some aspects, a Naïve Bayes classifier algorithm may be used to score text and calculate the probability of aggregate data being an emergency vs a non-emergency.” Col 9; 8-11 – a Naïve Bayes classifier algorithm is a trained machine learning model; see also “The structured and unstructured text may be analyzed by a machine learning based system including patient information extraction engine 115. A trained extraction engine may extract medical information from a corpus of data using continuous NPL scanning and analysis of information. In some aspects, the machine learning system comprises a support vector machine 315, which may perform classification based on a separating hyperplane, when trained with labeled training data.” Col 7; 39-48)
and generating a set of scores by, for each respective note of a plurality of notes in the user data, processing the respective note using the first trained machine learning model to generate a respective score of the set of scores; (“At operation 425, NPL sentiment analyzer engine 125 may generate a sentiment analysis score based upon extracted text.” Col 8; 57-59; see also “For example, a sentiment score may be generated to cover a period of a week, a month, a quarter, half a year, or more. In some aspects, this information can be used to monitor patient progress.” Col 9; 19-22 – this shows that a plurality of notes over time are scored.)
and aggregating the set of scores to generate the first attribute; (“In some aspects, the sentiment score reflects an aggregate score, in which each word is scored for a positive, neutral or negative value, and the individual values are summed to form an aggregate score for the content being considered.” Col 9; 12-15)
Zhang and Dibari are considered analogous art to the claimed invention because they discuss methods of processing patient health data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Zhang with a machine learning model to process score the notes and aggregate the scores. Doing so would have been beneficial in order to “calculate the probability of aggregate data being an emergency vs a non-emergency.” (Dibari Col 9; 10-11)
Dibari does not disclose: determining a percentage of the plurality of notes having a respective score exceeding a defined threshold; and selecting media based on the first user; and selecting and outputting media based on and customized to a user. Dibari does not disclose the intervention is automatically initiated.
Heruth discloses: determining a percentage of the plurality of notes having a respective score exceeding a defined threshold (“[0083]… As illustrated in FIG. 9, IMD 14 or programmer 20 may also compare each activity level for the therapy parameter set to an additional, "high activity" threshold, and determine a percentage of activity levels 62 above that threshold.”
Zhang, Dibari, and Heruth are considered analogous art to the claimed invention because they discuss methods of processing patient health data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Zhang in view of Dibari to aggregate the scores by determining a threshold exceedance rate as disclosed by Heruth. This combination falls under combining prior art elements according to known methods to yield predictable results or use of known technique to improve similar devices (methods, or products) in the same way. See MPEP 2141, KSR, 550 U.S. at 418, 82 USPQ2d at 1396.
Heruth does not disclose: selecting and outputting media based on and customized to a user. Heruth does not disclose the intervention is automatically initiated.
Hasselberg discloses: the prophylactic intervention including at least one prophylactic media component, (“[0005] ... The system includes a user device that outputs a module with video content in connection with a mental health treatment protocol for a user...”)
comprising: selecting the prophylactic media component based on a resident profile of the second user, (“[0051] … In other cases, the mental-health-treatment-delivery-server may provide additional features such as other modules with customizable content (e.g., visual or audio cues) based on preferences of the patient. For instance, a patient that has provided responses indicating to the mental-health-treatment-delivery-server that the patient is moving to an elevated stress level, such as a higher than an average stress level of the user, the mental-health-treatment-delivery-server may prompt that patient to view a calming module of content presented by the client device.” See also [0024] and [0026] which disclose storing electronic health records.)
wherein the prophylactic media component is linked with the resident profile (“[0030]… In some cases, the user device may adjust the menu of options based on a particular user that has been authenticated or a previous session of use. For instance, the user device may modify the presented menu of options based on previously completed modules, additional modules unlocked by past session completion (e.g., a usage streak, a completion percentage, etc.), or other factors relating to the authenticated user. In one aspect, a user device may have multiple user profiles associated with corresponding mental therapy treatments. In a configuration with multiple users associated with a user device, the user device may use authentication credentials unique to each user of the user device.”)
and personalized to the second user; (“[0021]… The module engine 120 may provide the client device with a module that includes parameters for a virtual therapist office, a customizable environment (e.g., location, ambient sounds, etc.) or other environment that the user may perform various interactions within as described in some aspects of the disclosure.”)
and outputting the prophylactic media component to the second user. (“[0005] ... The system outputs the information to an interface of the user device.”)
Zhang, Dibari, Heruth, and Hasselberg are considered analogous art to the claimed invention because they discuss methods of processing patient health data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Zhang in view of Dibari and Hasselberg to identify and output customized video modules to treat mental health as taught by Hasselberg. This would have been beneficial in order to overcome issues due to lack of trained therapists, stigma, cost, and geographic barriers. (Hasselberg [0003])
Hasselberg does not disclose the intervention is automatically initiated.
Lisic discloses based on the risk score, automatically initiating prophylactic intervention for the user (“[0098] In various implementations, outputs of the model may be supplied to other healthcare systems, such as Cigna's Health Connect 360 system. This may allow condition predictions to be supplied to healthcare providers so they can offer better medical care for patients. The condition prediction outputs may be supplied to a system that provides automated interventions, such as communicating with the patient to seek treatment or communicating with a healthcare provider to check on possible medical issues with a patient.”)
Zhang, Dibari, Heruth, Hasselberg, and Lisic are considered analogous art to the claimed invention because they discuss methods of processing patient health data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of combination to automatically initiate intervention as taught by Lisic. This would have been beneficial in order to provide the timeliest intervention. (Zhang discloses “[0048] … The importance of PPD prevention and timely intervention cannot be overstated…”)
Regarding claim 2, Zhang does not disclose the additional limitations.
Dibari discloses: 2. The method of claim 1, wherein aggregating the set of scores further comprises: determining an average value of the set of scores. (“In some aspects, the content may be restricted to a particular time frame, allowing a moving average sentiment to be generated.” Col 9; 16-19)
Zhang and Dibari are considered analogous art to the claimed invention because they discuss methods of processing patient health data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of Zhang with an average value of scores. Doing so would have been beneficial in order to monitor patient progress (Dibari Col 9; 21-22)
Regarding claim 4, Zhang discloses: 4. The method of claim 1, wherein training the second machine learning model further comprises:
generating training data based on prior user data, the prior user data indicating a respective set of user attributes for each respective user of a plurality of users, comprising: ("a machine learning algorithm is trained using EHR data obtained during a population survey. " [0029]; “[0031] Patients' birthdate, race, maternal status, average body mass index (BMI), gestational week, and delivery type as time-independent predictors, and medication prescriptions and diagnoses were considered at each clinical visit as the time-dependent predictors.” ; see following limitations regarding generating the data.)
identifying a set of records, in the prior user data, indicating that a corresponding user has depression, based on searching the prior user data for a defined medical code; and ("Clinical assessment of PPD was used as the outcome in this example. The main outcome was defined based on the Statistics Canada and International Classification of Diseases, 10th Revision (ICD-10-CM) codes O99.3 and O99.34 codes as well as their ICD-9-CM equivalents for a diagnosis of PPD within 12 months after childbirth. " [0031])
for each respective record in the set of records, extracting a respective set of user attributes corresponding to a defined window of time prior to a time associated with the respective record. ("The specific trimester of medication prescription and diagnoses were identified by the time interval between each event and delivery. " [0031])
Claim 5 is a method claim with limitations similar to the limitations of Claim 1 and is rejected under similar rationale.
Claim 6 is a method claim with limitations similar to the limitations of Claim 2 and is rejected under similar rationale.
Regarding claim 8, Zhang discloses: 8. The method of claim 5, further comprising: determining that the first risk score exceeds a defined threshold; ("In step 760, the method determines whether the patient is high risk (e.g., whether a risk score determined by the machine learning algorithm exceeds a threshold value such as 50% or 75%)" [0086])
and generating an alert identifying the first user. ("Rather, the systems and methods disclosed herein are used to predict a likelihood of PPD disease before it occurs, so that interventive actions may be taken or planned to prevent the disease from occurring, or to limit its severity should it occur." [0086]; “[0009] if the risk score exceeds a threshold value, computing treatment recommendations based on the health data for the patient, and providing the treatment recommendations.”)
Zhang discloses providing an individual intervention/treatment, but not specifically an alert.
Dibari discloses: and generating an alert identifying the first user. (“Flagging and alerts engine 140 may send out notification to physicians or other health care professionals, when a change in sentiment exceeds a threshold, to ensure timely intervention” Col 5; 58-61)
Zhang and Dibari are considered analogous art to the claimed invention because they discuss systems for processing patient health data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Zhang in view of Mao to produce an alert if the risk exceeded the threshold. Doing so would have been beneficial so that health care professionals could provide timely intervention. (Dibari Col 5; 58-61)
Regarding claim 9, Zhang discloses: 9. The method of claim 8, further comprising: identifying a most impactful attribute, from the first set of user attributes, that caused the first risk score to exceed the defined threshold; and indicating the most impactful attribute in the generated alert. (Figure 6 shows Risk Factors 670 in the user interface. ; see also [0008] “In some embodiments, the computer implemented method further includes ranking selected elements of the collected data according to their statistical correlation with a patient developing postpartum depression.”; see also Table 5, Weighted PPD risk factors – weighting the risk factors also identifies the most impactful.)
Regarding claim 10, Zhang discloses: 10. The method of claim 5, further comprising: for each respective user of a plurality of users in a healthcare facility: identifying a respective set of user attributes; ("For algorithm development, EHR data including demographics, diagnoses, medication prescriptions, procedures, laboratory measurements, and social determinants of health (SDoH) including the built environment characteristics such as distance to public transportation and green space on eligible patients were obtained at Weill Cornell Medicine (WCM) and NewYork-Presbyterian Hospital in New York City, USA between January 2015 and June 2018. For algorithm validation, EHR data was derived from multiple health systems across New York City affiliated to the Patient-Centered Outcomes Research Institute funded New York City Clinical Data Research Network data (NYCCDRN) between August 2004 and October 2017 (Kaushal et al., 2014)." [0059])
and generating a respective risk score for the respective user by processing the respective set of user attributes using the second trained machine learning model. ("One example randomly selected 80% of the data from WCM as the training set including cross-validation and model tuning, and held the remaining 20% as the test set individually. The NYC-CDRN data was used solely as a validation set." [0059] – the test/validation set have risk scores generated using the trained model during evaluation.)
Regarding claim 11, Zhang discloses: 11. The method of claim 5, wherein the defined set of features comprises: one or more features relating to diagnoses, ("Diagnose 120b" Fig. 1)
one or more features relating to clinical assessments, ("In some embodiments, the computation of either the risk score or the treatment recommendations includes a function of features selected from the health data for the patient, where the features are selected from anxiety history, use of antidepressants, mood disorder history, an indicator of whether there has been depression in pregnancy, an indicator of whether there has been anxiety in pregnancy, an indicator of whether there has been mental disorder in pregnancy, and a history of other disorders." [0010] - The features such as anxiety history and mood disorder history are considered clinical assessments.)
and one or more features relating to medications. ("Medication 120c" Fig. 1)
Regarding claim 12, Zhang discloses: 12. The method of claim 11, wherein: the one or more features relating to diagnoses comprise a defined set of diagnoses, and the first set of user attributes indicates, for each respective diagnosis of the defined set of diagnoses, whether the first user has the respective diagnosis. ("The main outcome was defined based on the Statistics Canada and International Classification of Diseases, 10th Revision (ICD-10-CM) codes O99.3 and O99.34 codes as well as their ICD-9-CM equivalents for a diagnosis of PPD within 12 months after childbirth. " [0031])
Regarding claim 13, Zhang discloses: 13. The method of claim 12, wherein the first set of user attributes further indicates, for each respective diagnosis of the defined set of diagnoses, whether the first user was diagnosed with the respective diagnosis within a defined window of time. ("The main outcome was defined based on the Statistics Canada and International Classification of Diseases, 10th Revision (ICD-10-CM) codes O99.3 and O99.34 codes as well as their ICD-9-CM equivalents for a diagnosis of PPD within 12 months after childbirth. " [0031])
Regarding claim 14, Zhang discloses: 14. The method of claim 11, wherein: the one or more features relating to clinical assessments comprise a defined set of conditions, recorded by one or more caregivers, (See below, “Health data” indicates it is recorded by a caregiver)
relating to functional states of users, (at least mood disorder and anxiety (see below) relate to functional states of the user)
and the first set of user attributes indicates, for each respective condition of the defined set of conditions, whether the first user has the respective condition. ("In some embodiments, the computation of either the risk score or the treatment recommendations includes a function of features selected from the health data for the patient, where the features are selected from anxiety history, use of antidepressants, mood disorder history, an indicator of whether there has been depression in pregnancy, an indicator of whether there has been anxiety in pregnancy, an indicator of whether there has been mental disorder in pregnancy, and a history of other disorders." [0010] – the history or indicator indicates the user has the respective condition.)
Regarding claim 15, Zhang discloses: 15. The method of claim 14, wherein the defined set of conditions comprises at least one of: (i) weight loss, (ii) weight gain, (iii) pain, (iv) increased food intake, (v) decreased food intake, (vi) isolation, or (vii) one or more mood or behavioral issues. ("In some embodiments, the computation of either the risk score or the treatment recommendations includes a function of features selected from the health data for the patient, where the features are selected from anxiety history, use of antidepressants, mood disorder history, an indicator of whether there has been depression in pregnancy, an indicator of whether there has been anxiety in pregnancy, an indicator of whether there has been mental disorder in pregnancy, and a history of other disorders." [0010]; Additionally, [0031] discloses that BMI from a clinical assessment is considered. Table 4 shows weight gain as a predictor.)
Regarding claim 16, Zhang discloses: 16. The method of claim 11, wherein: the one or more features relating to medications comprise a defined set of medications, and the first set of user attributes indicates, for each respective medication of the defined set of medications, whether the first user receives the respective medication. ("The use of antidepressants was defined by Anatomical Therapeutic Chemical (ATC) codes under N06A" [0062])
Regarding claim 17, Zhang discloses: 17. The method of claim 16, wherein the first set of user attributes further indicates, for each respective medication of the defined set of medications, whether the first user was prescribed the respective medication within a defined window of time. ("The specific trimester of medication prescription and diagnoses were identified by the time interval between each event and delivery. Trimester of pregnancy is defined as follows: first trimester (0-12 weeks), second trimester (13-28 weeks), and third trimester (29 weeks—gestation). " [0032])
Regarding claim 18, Zhang discloses: 18. The method of claim 5, wherein the second machine learning model was trained on prior user data for a plurality of users, the prior user data indicating a respective set of user attributes for each respective user of the plurality of users. (See Fig. 1, Model Training 191; the flowchart shows that the model is trained on user data for a plurality of users' attributes. ("2.9 Million EHRs"))
Regarding claim 19, Zhang discloses: 19. The method of claim 18, wherein the training data was generated based on the prior user data, by: ("a machine learning algorithm is trained using EHR data obtained during a population survey. " [0029]; [0031] “Patients' birthdate, race, maternal status, average body mass index (BMI), gestational week, and delivery type as time-independent predictors, and medication prescriptions and diagnoses were considered at each clinical visit as the time-dependent predictors.”)
identifying a set of records, in the prior user data, indicating that a corresponding user has depression, based on searching the prior user data for a defined medical code; ("Clinical assessment of PPD was used as the outcome in this example. The main outcome was defined based on the Statistics Canada and International Classification of Diseases, 10th Revision (ICD-10-CM) codes O99.3 and O99.34 codes as well as their ICD-9-CM equivalents for a diagnosis of PPD within 12 months after childbirth. " [0031])
and for each respective record in the set of records, extracting a respective set of user attributes corresponding to a defined window of time prior to a time associated with the respective record. ("The specific trimester of medication prescription and diagnoses were identified by the time interval between each event and delivery. " [0031])
Claim 20 is a non-transitory computer-readable storage medium claim with limitations corresponding to the limitations of Claim 5 and is rejected under similar rationale. Additionally, a “medium,” “program code,” and “one or more computer processors” of the Claim are taught by Zhang. (Figure 8, Memory 864; Instructions 866; Processor 860)
Claim(s) 3 and 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Dibari, Heruth, Hasselberg, and Lisic as applied in claim 3 above, in further view of Mao et al. (US 20200234801 A1).
Regarding claim 3, Zhang does not disclose the additional limitations. Neither do Dibari, Heruth, Hasselberg, or Lisic.
Mao discloses: 3. The method of claim 2, wherein generating the set of scores by processing the plurality of notes comprises preprocessing at least a first note of the plurality of notes, comprising: normalizing natural language text in the first note; ("The clinical trial data can be structured and/or normalized using an XML parser. " [0093])
and converting the normalized natural language text in the first note to a numerical vector. ("Various embodiments can use a vector space model to combine the weights of multiple terms." [0071])
Zhang, Dibari, Heruth, Hasselberg, Lisic and Mao are considered analogous art to the claimed invention because they discuss methods of processing patient health data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system of combination with a machine learning model to process the notes into a structured mark-up language. Doing so would have been beneficial to allow interoperability between different documents for each patient. (Mao [0094])
Claim 7 is a method claim with limitations similar to the limitations of Claim 3 and is rejected under similar rationale.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JON C MEIS whose telephone number is (703)756-1566. The examiner can normally be reached Monday - Thursday, 8:30 am - 5:30 pm 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, Hai Phan can be reached on 571-272-6338. 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.
/JON CHRISTOPHER MEIS/Examiner, Art Unit 2654
/HAI PHAN/Supervisory Patent Examiner, Art Unit 2654
Prosecution Insights