DETAILED ACTION
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 Claims
This Final Office Action is in response to the Amendment and Remarks filed 07/08/2026. Claims 1-20 are pending and considered herein.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date.
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosure of the prior-filed application, Application No. 16/905,155 fails to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph for one or more claims of this application.
Regarding the independent claims, the Specification of the instant application and the parent application 16/905,155 are silent as to the machine learning model as having the rare disease and provide a treatment course of action for treating the rare disease for the additional patient. The “treatment course of action for a rare disease” is not included anywhere in the Specification, and the claims are thus subject to a 112(a) rejection. Therefore, the priority date for the amended claims is the filing date for the instant application of 12/22/2025.
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.
Claim 1-20 are 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 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, at the time the application was filed, had possession of the claimed invention.
Regarding claims 1, 8 and 15, the independent claims recite “the first snapshot is for a particular patient diagnosed as having a rare disease […] the instructions further cause the system to output information associated with an additional patient identified by the machine learning model as having the rare disease and provide a treatment course of action for treating the rare disease for the additional patient.” However, the Specification is silent with regard to defining a “rare disease,” and is also silent as to a machine learning model and providing a treatment for a rare disease for any patient. There is no support for these limitations in the Specification. The claims are therefore rejected under 35 U.S.C. 112(a) for failing to comply with the written description requirement. The dependent claims inherit the deficiencies of the independent claims. Thus claims 1-20 are rejected.
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 1-20 are 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.
The term “rare disease” in the independent claims is a relative term which renders the claim indefinite. The term “rare disease” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Regarding claims 1, 8 and 15, the independent claims recite “the first snapshot is for a particular patient diagnosed as having a rare disease […] the instructions further cause the system to output information associated with an additional patient identified by the machine learning model as having the rare disease and provide a treatment course of action for treating the rare disease for the additional patient.” However, the Specification is silent with regard to defining a “rare disease,” and there are no bounds or limits to what the scope of “rare” means for a disease. There is no support for the limitations in the Specification. The dependent claims inherit the deficiencies of the independent claims. The claims are therefore rejected under 35 U.S.C. 112(b) as being indefinite.
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 they recite an abstract idea without significantly more.
Claim 1 recites, wherein the abstract idea is not emboldened:
A system comprising: one or more processors; and one or more hardware-based non-transitory computer-readable memory devices storing instructions which, when executed by the one or more processors, cause the system to:
create a timeline from medical histories of patients in a dataset, in which data for past events of interest for a plurality of patients is included on the timeline; implement a rolling timebound window into which a portion of the data for the past events is selectively captured as a snapshot of the medical histories of the plurality of patients; transform the snapshot by rolling the window along the timeline to selectively capture data at different points along the timeline to thereby generate multiple snapshots of the patient medical histories, wherein each snapshot comprises a prediction window and a lookback window preceding the prediction window; create a training set using data from the lookback window and the prediction window of a first snapshot of the multiple snapshots of the patient medical histories; train a machine learning model using the training set; and validate the machine learning model utilizing data from the prediction window of a second snapshot of the multiple snapshots of the patient medical histories, wherein: the first snapshot is for a particular patient diagnosed as having a rare disease; the training set is created using the first snapshot and subsequent snapshots for the particular patient to enable analysis of the particular patient at multiple different points along the timeline; and the instructions further cause the system to output information associated with an additional patient identified by the machine learning model as having the rare disease and provide a treatment course of action for treating the rare disease for the additional patient.
Independent claims 8 and 15 recite substantially similar limitations. The claimed invention is broadly directed to the abstract idea of collecting patient information, analyzing the information, and determining a timeline and predictions related to the patient based on the analyses.
The limitations to “create a timeline from medical histories of patients in a dataset, in which data for past events of interest for patients are included on the timeline; implement a rolling timebound window into which a portion of the data for the past events is selectively captured as a snapshot of the medical histories of the plurality of patients; transform the snapshot by rolling the window along the timeline to selectively capture data at different points along the timeline to thereby generate multiple snapshots of the patient medical histories, wherein each snapshot comprises a prediction window and a lookback window preceding the prediction window; create a training set using data from the lookback window and the prediction window of a first snapshot of the multiple snapshots of the patient medical histories; and validate the model utilizing data from the prediction window of a second snapshot of the multiple snapshots of the patient medical histories, wherein: the first snapshot is for a particular patient diagnosed as having a rare disease; the training set is created using the first snapshot and subsequent snapshots for the particular patient to enable analysis of the particular patient at multiple different points along the timeline; and the instructions further cause the system to output information associated with an additional patient identified as having the rare disease and provide a treatment course of action for treating the rare disease for the additional patient,” as drafted, is a process that, under its broadest reasonable interpretation, is an abstract idea that covers performance of the limitation as certain methods of organizing human activity. For example, but for the generic computer system, processor, memory and machine learning model, in the context of this claim, the judicial exception is found that covers performance of the limitation as organizing human activity including following rules or instructions. These recited limitations fall within certain methods of organizing human activity grouping of abstract ideas because the limitations allowing users to access patient data, analyze the data, and generate predictions based on the analyses. This is a method of managing interactions between people. Under its broadest reasonable interpretation, the limitations are categorized as methods of organizing human activity, specifically associated with managing personal behavior or relationships or interactions between people including a patient and caregiver. Therefore, the limitation falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. See MPEP § 2106.04(a). The mere nominal recitation of a generic computer system, processors, memory, IoT devices and computer devices does not remove the claims from the method of organizing human interactions grouping. Thus, the claims recite an abstract idea.
The claims also recited an abstract idea including mental processes. But for the generic reciting of a computer system, processor, memory and training a machine learning model, nothing in the claims is precluded from being performed in the mind. For example, a physician can collect the patient data and analyze the medical history and events and determine/predict if there is some risk or need or not for the patient based on the analyses. Thus, the claims recite an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of being implemented by a generic computer system, processor, memory and machine learning model. The devices in these steps are recited at a high-level of generality (i.e., as a generic processor/server/storage/display performing a generic computer function of receiving inputs, analyzing the inputs, and displaying or sending selected information) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, these additional elements, alone or in combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The limitations appear to monopolize the abstract idea of patient analysis and general diagnostic techniques between a clinician and her patient. Furthermore, there is no clear improvement to the underlying computer technology in the claim. The claim is thus directed to an abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of being implemented by a generic computer system, processor, memory and machine learning model amounts to no more than mere instructions to apply the exception using a computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Therefore, when considering the additional elements alone, and in combination, there is no inventive concept in the claim, and thus the claim is not patent eligible.
The dependent claims do not remedy the deficiencies of the independent claims with respect to patent eligible subject matter. The dependent claims further limit the abstract idea and do not overcome the rejection under 35 U.S.C. §101. Claim 2 describes events and further narrows the abstract idea. Claims 3-5, 7 and 20 further detail the machine learning model, which is recited at a high level of generality such that it amounts to no more than mere instructions to apply the judicial exception using a generic computer component and cannot provide an inventive concept. Even in combination, the machine learning model does not integrate the abstract idea into a practical application and does not amount to significantly more than the abstract idea itself. Claim 6 describes a user interface at a high level of generality such that it amounts to no more than mere instructions to apply the judicial exception using a generic computer component and cannot provide an inventive concept. Even in combination, the user interface does not integrate the abstract idea into a practical application and does not amount to significantly more than the abstract idea itself. Claims 9-14 and 16-18 describe the timeline windows and sampling bias and further limit the abstract idea. Claim 19 describes events of interest and limits the abstract idea.
Therefore, the claims are not patent eligible.
Claims 1-10 and 13-20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. 2016/0328526 A1 to Park et al., hereinafter “Park,” in view of U.S. 2014/0278547 A1 to Wickert et al., hereinafter “Wickert,” in view of U.S. 11,043,289 B2 to Thomas et al., hereinafter “Thomas,” in view of U.S. 2019/0139643 A1 to Li et al., hereinafter “Li” and further in view of U.S. 2021/0155695 A1 to Chinnaiyan et al., hereinafter “Chinnaiyan.”
Regarding claim 1, Park discloses A system comprising: one or more processors; and one or more hardware-based non-transitory computer-readable memory devices storing instructions which, when executed by the one or more processors (See Park at least at Paras. [0038]-[0040], [0074], [0087]; Claim 17; Figs. 1, 2) , cause the system to: create a timeline from medical histories of patients in a dataset, in which data for past events of interest for patients are included on the timeline (See id. at least at Paras. [0039]-[0042] (medical histories, events and timeline); Figs. 6, 13-23); implement a rolling timebound window into which a portion of the data for the past events is selectively captured as a snapshot of the medical histories of the plurality of patients (See id. at least at Paras. [0005]-[0008] (“an aggregated snapshot of data, e.g., claims from a certain time period of time”), [0047]-[0050], [0057]-[0059] (rolling window); Figs. 6, 13, 15, 18-23); transform the snapshot by rolling the window along the timeline to selectively capture data at different points along the timeline to thereby generate multiple snapshots of the patient medical histories, wherein each snapshot comprises a prediction window and a lookback window preceding the prediction window (See id. at least at Paras. [0005]-[0008] (medical events, future predictions), [0040]-[0042] (“To address this issues, the data transformer 212 merges such multiple sources to construct a member-level view of the data, preferably by using a flexible data representation (such as a JSON format), together with the notion of an “episode” that combines multiple claim items into one.”), [0047]-[0050], [0057]-[0069] (rolling windows, future and previous history/data); Figs. 6-8, 13-23).
Park may not specifically describe but Wickert teaches to create a training set using data from the lookback window and the prediction window of a first snapshot of the multiple snapshots of the patient medical histories (See Wickert at least at Abstract; Paras. [0016], [0022]-[0025], [0030]-[0031] (“[A] fixed time window extending from the date of a given type of medical event until 14 days after it. For each instance of that type of medical event in the training data, all of the ICD9 diagnostic codes (and/or all categorical data, such as all relevant patient categorical data in the relevant high-level construct) in the data that fall within the fixed-length window (e.g., defined, fixed variable, etc.) would be included in the WoE table.”); Claims 4, 5; Figs. 1-4).
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 disclosure of Park to incorporate the teachings of Wickert and provide certain training data and timelines. Wickert is directed to a system for healthcare predictions using medical history. Incorporating the healthcare prediction techniques of Wickert with the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of the claimed system for timed medical event prediction
The references may not specifically describe but Thomas teaches to train a machine learning model using the training set (See Thomas at least at Col. 9, ln. 10 – Col. 10, ln. 31; Col. 13, ln. 9-62; Col. 16, ln. 1 – Col. 8, ln. 57; Figs. 1-10); and validate the machine learning model utilizing data from the prediction window of a second snapshot of the multiple snapshots of the patient medical histories (See Thomas at least at Col. 9, ln. 10 – Col. 10, ln. 31; Col. 13, ln. 9-62; Col. 16, ln. 1 – Col. 8, ln. 57; Col. 18, ln. 8-56 (“[T]he feature engineering process 708 can employ a training phase of a machine learning process to generate the training data 704. Additionally or alternatively, the feature engineering process 708 can employ a prediction phase of a machine learning process to generate the validation data set 706. In certain embodiments, transformed data 710 (e.g., transformed data 710 stored in a machine learning database) can be employed by a feature selection process 712. The transformed data 710 can be, for example, a transformed version of real-time data and/or a transformed version of patient flow data.”); Figs. 1-10).
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 disclosure of Park and Wickert to incorporate the teachings of Thomas and provide certain training data and timelines and machine learning and validation. Thomas is directed to monitoring and alerting census periods for medical inpatient units. Incorporating the healthcare prediction techniques of Wickert with the monitoring and alerting events of Thomas and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of the claimed system for timed medical event prediction.
The references may not specifically describe but Li teaches wherein: the first snapshot is for a particular patient diagnosed as having a rare disease (See Li at least at Paras. [0037]-[0045] (snapshot images, predict a cancer probability – cancer considered the rare disease); Figs. 1-8); the training set is created using the first snapshot and subsequent snapshots for the particular patient to enable analysis of the particular patient at multiple different points along the timeline (See id. at least at Paras. [0025], [0037]-[0045] (using snapshot image data over a period of time in reference to training a prediction model; the training set is created using numerous snapshots for a particular patients and requires more than one snapshot image over a period of time; using the data of previous patients that was determined to have cancer to train the model – This is interpreted as “the particular patient.”); Figs. 1-8); and the instructions further cause the system to output information associated with an additional patient identified by the machine learning model as having the rare disease (See Li at least at Paras. [0025], [0037]-[0045] (Using snapshot image data over a period of time in reference to training a prediction model; the training set is created using numerous snapshots for a particular patients. There is outputting of a prediction of a new patient (i.e. additional patient) using the model.); Figs. 1-8).
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 disclosure of Park, Wickert and Thomas to incorporate the teachings of Li and snapshots/timelines of a patient with a rare disease and comparing to another patient. Li is directed to medical diagnostics with a prediction model. Incorporating the prediction model of Li with the healthcare prediction techniques of Wickert, the monitoring and alerting events of Thomas and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of the claimed system for timed medical event prediction.
The references may not specifically describe but Chinnaiyan teaches to provide a treatment course of action for treating the rare disease for the additional patient (See Chinnaiyan at least at Abstract (“[C]ompositions, methods, and uses of targeted therapy to treat cancer.”); Paras. [0073]-[0076] (“[T]he data may be used to further optimize the inclusion or elimination of markers as useful indicators of a particular condition or stage of disease or as a companion diagnostic to determine a treatment course of action.”).
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 disclosure of Park, Wickert, Thomas and Li to incorporate the teachings of Chinnaiyan and provide models and timelines for rare disease of a patient and comparing to another patient. Chinnaiyan relates to methods for treating cancer. Incorporating the treatment of Chinnaiyan with the prediction model of Li, the healthcare prediction techniques of Wickert, the monitoring and alerting events of Thomas and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claim 2, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 1, and Park further discloses the past events of interest indicate disease progression or change of therapy and the dataset of selectively captured data comprises positive past events of interest (See Park at least at Paras. [0007]-[0008], [0044], [0048]-[0050] (episodic progression), [0057]-[0059]; Figs. 12-16).
Regarding claim 3, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 1, and Park further discloses wherein: the multiple snapshots of patient medical histories enable analysis of a particular patient at multiple different points along the timeline (See Park at least at Paras. [0005]-[0008] (medical events, future predictions), [0040]-[0050], [0057]-[0069] (rolling windows, future and previous history/data); Figs. 6, 13-23), the particular patient diagnosed as having a rare disease (See id. at least at Paras. [0040], [0057]-[0059], [0068]-[0069]); and the instructions further cause the system to use the machine learning model (See Thomas supra) to identify other patients with the rare disease (See id. at least at Paras. [0040]-[0041], [0045], [0052], [0062]-[0064], [0069]; Figs. 6-8, 17).
Regarding claim 4, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 3, and Park further discloses wherein the transformation comprises utilizing the generated multiple snapshots to increase sample size due to scarcity of other patients diagnosed as having the rare disease (See id. at least at Paras. Paras. [0005]-[0008] (“an aggregated snapshot of data, e.g., claims from a certain time period of time”) (medical events, future predictions), [0040]-[0050], [0057]-[0069] (rolling windows, multiple snapshots); Figs. 6-8, 13-23).
Regarding claim 5, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 1, and Thomas further teaches using the multiple snapshots of the patient medical histories in the machine learning model to predict one or more future events of interest (See Thomas at least at Col. 17, ln. 26 – Col. 20, ln. 34 (Prediction phase. “The combined machine learning model 806 can provide one or more weighted predictions 808. For instance, the one or more weighted predictions 808 can be one or more weighted predictions for the patient census data associated with a prediction for a total number of patient identities.”); Figs. 5-10; See also Wickert at least at Paras. [0016] (predictions using medical history data), [0019]-[0026], [0033]-[0039]; Claims 1, 4).
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 disclosure of Park, Wickert, Li and Chinnaiyan to incorporate the teachings of Thomas and provide certain training data and timelines (snapshots) and machine learning and validation. Thomas relates to monitoring and alerting census periods for medical inpatient units. Incorporating the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claim 6, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 5, and Park further discloses storing the predictions in a destination system that includes a user interface configured to enable users to interact with the stored predictions (See Park at least at Paras. [0038], [0043]-[0047], [0066]-[0069]; Figs. 1-2, 18-23).
Regarding claim 7, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 1, and Thomas further teaches wherein past events of interest occurring within the lookback and prediction windows of one or more of the multiple snapshots are utilized for training of the machine learning model (See Thomas at least at Col. 3, ln. 31-65; Col. 5, ln. 41-64 (forecasting component and historical data); Col. 9, ln. 10 – Col. 10, ln. 31; Col. 13, ln. 9-62; Col. 16, ln. 1 – Col. 18, ln. 57 (“[T]he feature engineering process 708 can employ a training phase of a machine learning process to generate the training data 704. Additionally or alternatively, the feature engineering process 708 can employ a prediction phase of a machine learning process to generate the validation data set 706. In certain embodiments, transformed data 710 (e.g., transformed data 710 stored in a machine learning database) can be employed by a feature selection process 712. The transformed data 710 can be, for example, a transformed version of real-time data and/or a transformed version of patient flow data.”); Figs. 1-10).
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 disclosure of Park, Wickert, Li and Chinnaiyan to incorporate the teachings of Thomas and provide certain prediction windows and certain times and determinations. Thomas relates to monitoring and alerting census periods for medical inpatient units. Incorporating the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claims 8 and 15, claims 8 and 15 recite substantially the same limitations as recited in independent claim 1. Therefore, the claims are rejected under the same grounds of rejection and for the same reasoning as applied to claim 1, above.
Regarding claim 9, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 8, and Thomas further teaches the future prediction window is an element of a cross-section further comprising a lookback window, the lookback window preceding the future prediction window on the timeline, in which past clinical events occurring within the lookback window preceding the future prediction window are extracted and applied to the machine learning model to predict the occurrence of a future clinical event of interest within the future prediction window (See id. at least at Col. 3, ln. 31-65; Col. 5, ln. 41-64 (forecasting component and historical data); Col. 9, ln. 10 – Col. 10, ln. 31 (“the monitoring engine component 106 can include a prediction component that employs data (e.g., real time data and/or historical data) to monitor a current state of the set of medical inpatient units. Additionally, the monitoring engine component 106 can facilitate prediction of emerging census patterns […] the monitoring engine component 106 can employ other classification techniques associated with Bayesian networks, decision trees and/or probabilistic classification models.”); Col. 13, ln. 9-62; Col. 16, ln. 1 – Col. 18, ln. 57 (“The real-time data 526 can include medical data, sensor data, process data (e.g., process log data), monitoring data, maintenance data, parameter data, measurement data, performance data, textual data, audio data, image data, video data, machine data, asset data, equipment data, medical device data, meter data, real-time data, historical data and/or other data. […] the feature engineering process 708 can employ a training phase of a machine learning process to generate the training data 704. Additionally or alternatively, the feature engineering process 708 can employ a prediction phase of a machine learning process to generate the validation data set 706. In certain embodiments, transformed data 710 (e.g., transformed data 710 stored in a machine learning database) can be employed by a feature selection process 712. The transformed data 710 can be, for example, a transformed version of real-time data and/or a transformed version of patient flow data.”); Figs. 1-10).
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 disclosure of Park, Wickert, Li and Chinnaiyan to incorporate the teachings of Thomas and provide certain prediction windows and certain times and determinations. Thomas relates to monitoring and alerting census periods for medical inpatient units. Incorporating the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claim 10, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 8, and Thomas further teaches each cross-section further comprises an offset window immediately preceding the prediction window on the timeline, each cross-section comprising a section of the timeline having a predetermined length, in which the offset window is chosen to accommodate time lags in data collection from the data sources (See id. at least at Col. 3, ln. 31-65; Col. 5, ln. 41-64 (forecasting component and historical data); Col. 9, ln. 10 – Col. 10, ln. 31 (“the monitoring engine component 106 can include a prediction component that employs data (e.g., real time data and/or historical data) to monitor a current state of the set of medical inpatient units. Additionally, the monitoring engine component 106 can facilitate prediction of emerging census patterns […] the monitoring engine component 106 can employ other classification techniques associated with Bayesian networks, decision trees and/or probabilistic classification models.”); Col. 13, ln. 9-62; Col. 16, ln. 1 – Col. 18, ln. 57; Col. 18, ln. 8-56 (“[T]he feature engineering process 708 can employ a training phase of a machine learning process to generate the training data 704. Additionally or alternatively, the feature engineering process 708 can employ a prediction phase of a machine learning process to generate the validation data set 706. In certain embodiments, transformed data 710 (e.g., transformed data 710 stored in a machine learning database) can be employed by a feature selection process 712. The transformed data 710 can be, for example, a transformed version of real-time data and/or a transformed version of patient flow data.”); Figs. 1-10).
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 disclosure of Park, Wickert, Li and Chinnaiyan to incorporate the teachings of Thomas and provide certain prediction windows and certain times and determinations. Thomas relates to monitoring and alerting census periods for medical inpatient units. Incorporating the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claim 13, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 8, and Thomas further teaches in which the executed instructions further cause the computing device to utilize the final dataset to validate the machine learning model or test the machine learning model (See Thomas at least at Col. 9, ln. 10 – Col. 10, ln. 31; Col. 13, ln. 9-62; Col. 16, ln. 1 – Col. 18, ln. 57; Col. 18, ln. 8-56 (“[T]he feature engineering process 708 can employ a training phase of a machine learning process to generate the training data 704. Additionally or alternatively, the feature engineering process 708 can employ a prediction phase of a machine learning process to generate the validation data set 706. In certain embodiments, transformed data 710 (e.g., transformed data 710 stored in a machine learning database) can be employed by a feature selection process 712. The transformed data 710 can be, for example, a transformed version of real-time data and/or a transformed version of patient flow data.”); Figs. 1-10).
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 disclosure of Park, Wickert, Li and Chinnaiyan to incorporate the teachings of Thomas and provide certain prediction windows and certain times and determinations. Thomas relates to monitoring and alerting census periods for medical inpatient units. Incorporating the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claim 14, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 8, and Thomas further teaches the executed instructions further cause the computing device to use different portions of the final dataset for training to thereby compensate for drift of the machine learning model or bias in the machine learning model (See id.).
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 disclosure of Park, Wickert, Li and Chinnaiyan to incorporate the teachings of Thomas and provide certain prediction windows and certain times and determinations. Thomas relates to monitoring and alerting census periods for medical inpatient units. Incorporating the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claim 16, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 15, and Park further discloses the different windows on the timeline have offset start times and end times on the timeline and the events of interest relate to one of disease progression or change of therapy (See Park at least at Paras. [0005]-[0008] (“an aggregated snapshot of data, e.g., claims from a certain time period of time”), [0047]-[0050], [0057]-[0059] (rolling window); Figs. 6-23).
Regarding claim 17, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 15, and Park further discloses each of the different windows comprise a lookback window and a prediction window, in which the lookback windows precede the respective prediction windows on the timeline (See id.). While Thomas teaches wherein events of interest occurring in the lookback and prediction windows are utilized by the machine learning model for training (See Thomas at least at Col. 9, ln. 10 – Col. 10, ln. 31; Col. 13, ln. 9-62; Col. 16, ln. 1 – Col. 8, ln. 57; Col. 18, ln. 8-56 (“[T]he feature engineering process 708 can employ a training phase of a machine learning process to generate the training data 704. Additionally or alternatively, the feature engineering process 708 can employ a prediction phase of a machine learning process to generate the validation data set 706. In certain embodiments, transformed data 710 (e.g., transformed data 710 stored in a machine learning database) can be employed by a feature selection process 712. The transformed data 710 can be, for example, a transformed version of real-time data and/or a transformed version of patient flow data.”); Figs. 1-10).
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 disclosure of Park, Wickert, Li and Chinnaiyan to incorporate the teachings of Thomas and provide certain prediction windows and certain times and determinations. Thomas relates to monitoring and alerting census periods for medical inpatient units. Incorporating the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claim 18, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 17, and Wickert further teaches each of the different windows further comprises an offset window between the lookback window and the prediction window on the timeline, in which the offset window provides a predetermined time lag to the prediction window such that the machine learning model is enabled to predict an event of interest by an amount of time equal to the size of the offset window (See Wickert at least at Paras. [0016]-[0019], [0022]-[0025]; Figs. 1-7).
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 disclosure of Park, Thomas, Li and Chinnaiyan to incorporate the teachings of Wickert and provide certain prediction windows and certain times, lags and determinations. Wickert is directed to a system for healthcare predictions using medical history. Incorporating the healthcare prediction techniques of Wickert with the monitoring and timelines of Thomas, the prediction model of Li, the treatment of Chinnaiyan and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claim 19, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 15, and Wickert further teaches the events of interest are expressed using positive and negative indicators, and in which a positive indicator comprises one of an initiation or escalation of a therapy, a clinical procedure, a diagnosis, or any medical event captured by the available data, or a combination thereof (See Wickert at least at Paras. [0016]-[0025], [0028], [0030], [0034]; Claim 2).
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 disclosure of Park, Thomas, Li and Chinnaiyan to incorporate the teachings of Wickert and provide certain events of interest and determinations. Wickert is directed to a system for healthcare predictions using medical history. Incorporating the healthcare prediction techniques of Wickert with the monitoring and timelines of Thomas, the prediction model of Li, the treatment of Chinnaiyan and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Regarding claim 20, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 15, and Thomas further teaches storing predictions from operations of the machine learning model in a destination system that is configured to interface with one or more computing device users to enable review and analysis of the predictions (See Thomas at least at Col. 9, ln. 60 – Col. 11, ln. 31; Col. 16, ln. 1 – Col. 18, ln. 57; Figs. 1-11).
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 disclosure of Park, Wickert, Li and Chinnaiyan to incorporate the teachings of Thomas and provide certain prediction windows and certain times and determinations. Thomas relates to monitoring and alerting census periods for medical inpatient units. Incorporating the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Claims 11 is rejected under 35 U.S.C. 103 as being unpatentable over Park, in view of Wickert, in view of Thomas, in view of Li, in view of Chinnaiyan and further in view of U.S. 2019/0311807 A1 to Kannan et al., hereinafter “Kannan.”
Regarding claim 11, Park as modified by Wickert, Thomas, Li and Chinnaiyan teaches the limitations of claim 8. The references may not specifically describe but Kannan teaches the final dataset having data captured at multiple different points along the timeline has reduced sampling bias relative to the initial dataset (See Kannan at least at Paras. [0101]-[0104] (“Sources of bias in the samples that drive the models may be quantified, and the models may be corrected for known and estimated bias. The models may incorporate disease and symptom prevalence in the general population, and may include how those statistics vary in specific subpopulations by demographic, geography, calendar, social connections, etc.”); Figs. 1, 12).
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 disclosure of Park, Wickert, Thomas, Li and Chinnaiyan to incorporate the teachings of Kannan and provide reducing sampling bias. Kannan is directed to systems for responding to healthcare inquiries. Incorporating the responses and sampling bias of Kannan with the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Park, in view of Wickert, in view of Thomas, in view of Li, in view of Chinnaiyan, in view of Kannan and further in view of U.S. 2021/0064929 A1 to Trim et al., hereinafter “Trim.”
Regarding claim 12, Park as modified by Wickert, Thomas, Li, Chinnaiyan and Kannan teaches the limitations of claim 11. The references may not describe but Trim teaches the sampling bias results from one of seasonality, changes in data coverage, or changes in market conditions (See Trim at least at Paras. [0023]-[0025], [0043]-[0045]; Claim 1).
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 disclosure of Park, Wickert, Thomas, Li, Chinnaiyan and Kannan to incorporate the teachings of Trim and provide sampling bias from different sources. Trim is directed to preventing unwanted model training data. Incorporating the techniques for removing unwanted model training data as in Trim with the responses and sampling bias of Kannan, the monitoring and timelines of Thomas with the prediction model of Li, the treatment of Chinnaiyan, the healthcare prediction techniques of Wickert and the case management system using a medical event forecasting engine as in Park would thereby improve the functionality and applicability of medical event prediction.
Response to Arguments
Applicant’s amendments and remarks filed July 8, 2026 have been fully considered, but they are not persuasive. The following explains why:
Applicant’s arguments pertaining to subject matter eligibility are not persuasive. The claims have been addressed with regard to the updated 35 U.S.C. §101 rejection discussed above, and considered under relevant sections of the MPEP. The arguments at pages 12-17 of Applicant’s Remarks are not persuasive. At page 11-12 the Examiner disagrees that there is not an abstract idea. The Examiner disagrees at Pages 12-15 that the claim recites an improvement to the underlying computer technology “in computerized ETL processing and machine learning” and is not “a method of organizing human activity or a mental process.” That it may be tedious or laborious to perform analyses in the mind or manually is not of consequence in the eligibility analysis. The current claims are included as a mental process(es) for the judicial exception as well as organizing human activity as following rules or instructions. There is no clear technological improvement that is described in the claims for the underlying computer technology. The Examiner disagrees at Pages 14-16 that the abstract idea is integrated into a practical application. The “ordered combination of operations” like processing and using machine learning is noted as an additional element that is addressed in the rejection above and do not show an improvement to the technology. The timelines/snapshots of information and rolling windows and validation are part of the abstract idea and do not provide a practical application that is integrated in the claims or significantly more than the abstract idea. The claimed processing and machine learning of patient histories and data utilize computers as a tool to employ the abstract idea of making determinations about a patient’s health or indication of a disease or rare condition. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The Examiner disagrees at Pages 16-17 that the claims recite significantly more than the abstract idea. The “treatment course of action” for “a rare disease” is not sufficient for a showing of significantly more than the abstract idea. A nexus for the data that are processed and an explicit treatment that is being provided/recommended, e.g., an injection of medication, use of a medical implant, or an actual medical procedure being conducted as a result of the analyses of timelines, etc., or the like, would be more in line with a showing of significantly more than the abstract idea, and/or a practical application thereof. Merely providing “a treatment course of action for treating the rare disease,” is broad and not significantly more than the abstract idea or showing a practical application thereof. The combination of providing timelines for patients of interest having a rare disease and comparing those to other patients is part of the abstract idea, and not significantly more than it. For at least these reasons and those stated in the rejection above, the claims are not patent eligible.
Applicant’s arguments pertaining to prior art rejections are not persuasive. The rejection under 35 U.S.C. §103 has been considered under the amended claims. The arguments at Pages 19-21 are moot at least in light of new references Li and Chinnaiyan, discussed above.
Thus, the claims are rejected.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: U.S. 2020/0185102 A1 to Leventhal et al. (See Leventhal at least at Abstract; Paras. [0070]-[0074] (Symptom-Attribute-Values (SAV) and machine model training and for rare conditions), [0083] (training model for rare conditions from medical records), [0249]-[0252] (patient timeline), [0345]; Figs. 1-5, 6 (patient timeline), 13, 20, 27; Claims 1-5, 15 (“a[A] map that displays locations associated with the reference population having the one or more relevant symptoms and the one or more relevant profile features; a symptom timeline that presents an evolution of a value of a selected attribute of one of the relevant symptoms of the reference population; the symptom timeline that presents the evolution of the value for each selected medical treatment.”)); and U.S. 2020/0303071 A1 to Miller et al. (See Miller at least at Abstract (training data to predict commonality between undiagnosed patient and one or more patterns); Paras. [0002]-[0004] (rare diseases), [0006] (presence or absence of medical condition), [0013] (displaying probability of disease), [0030], [0039] (patient and anticipated timeline that is narrowed (snapshot)); Figs. 1, 3, 5-6); and U.S. 2012/0130740 A1 to Coutinho et al., for accessing rare disease databases. Para. [0042]; Fig. 2.
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 WILLIAM T. MONTICELLO whose telephone number is (313)446-4871. The examiner can normally be reached M-Th; 08:30-18:30 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, FONYA LONG can be reached at (571) 270-5096. 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.
/WILLIAM T. MONTICELLO/ Examiner, Art Unit 3682
/FONYA M LONG/ Supervisory Patent Examiner, Art Unit 3682
