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
Claims 1, 5-7, 11, 13, 18, 21, 22, 24, 26 and 29-33 have been amended.
Claims 34 and 35 are newly presented.
Claims 1, 5-7, 10, 11, 13, 17, 18, 21-26 and 29-35 as presented September 2, 2025 are currently pending and considered below.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on September 2, 2025 has been entered.
Claim Rejections - 35 USC § 112
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, 5-7, 10, 11, 13, 17, 18, 21-26 and 29-35 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.
As to claim 1, the claim recites “alter a dialysis treatment prescription for the patient based on the determined overlooked, unreported, and/or undocumented comorbidity”. A review of the specification reveals transmitting a new prescription (“the integrated care system may send the dialysis machine 1200, 1300, 1400, a prescription from a medical professional for a prescribed dialysis treatment” [0088]) and altering a dialysis treatment prescription (“Changes in treatment may be directly sent by the integrated care system 220, 220' to the selected dialysis machine” [0117]). It is unclear from the claims and the specification, as there is no mention of an unaltered treatment prescription, whether “alter a dialysis treatment prescription” covers the transmission of a new prescription or the modification of a treatment prescription.
Claim 13 is rejected for similar reasons as claim 1.
Claims 5-7, 10, 11, 29-31, 34 and 35 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph due to their dependence on claim 1.
Claims 17, 18, 21-26, 32 and 33 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph due to their dependence on claim 13.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1, 5-7, 10, 11, 13, 17, 18, 21-26 and 29-35 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e. an abstract idea) without significantly more.
Claims 1, 5-7, 10-11, 13 and 29-31 recite a system for determining an overlooked, unreported, and/or undocumented comorbidity in a patient, which is within the statutory category of a machine. Claims 13, 17-18, 21-26 and 32-33 recite a computer-implemented method determining an overlooked, unreported, and/or undocumented comorbidity in a patient, which is within the statutory category of a process.
Step 2A - Prong One:
Regarding Prong One of Step 2A, the claim limitations are to be analyzed to determine whether, under their broadest reasonable interpretation, they "recite" a judicial exception or in other words whether a judicial exception is "set forth" or "described" in the claims. An "abstract idea" judicial exception is subject matter that falls within at least one of the following groupings: a) mathematical concepts, b) certain methods of organizing human activity, and/or c) mental processes. Representative independent claim 1 includes limitations that recite at least one abstract idea.
Specifically, independent claim 1 recites: A system for treating a patient based on having determined an undocumented comorbidity condition in the patient, the system comprising:
a dialysis machine configured to provide a dialysis treatment for the patient; and
at least one computing device comprising:
at least one storage device storing instructions; and
at least one processor operatively coupled to the at least one storage device;
wherein the at least one processor, based on executing the instructions, is configured to cause the at least one computing device to:
extract population patient data from one or more databases corresponding to a pool of patients receiving dialysis treatment;
access a plurality of machine learning comorbidity models, each of the comorbidity models configured to generate a comorbidity risk score for a respective one of a plurality of comorbidities;
train each of the plurality of machine learning comorbidity models using the population patient data, excluding patient data of patients that have not been diagnosed with the respective one of a plurality of comorbidities specific comorbidity associated with a corresponding comorbidity model, to identify the respective one of the plurality of comorbidities;
extract patient data corresponding to the patient from patient records;
determine at least one reported comorbidity for the patient in the patient records;
generate a comorbidity risk score for each of the plurality of comorbidities using the plurality of machine learning comorbidity models with the extracted patient data;
aggregate the comorbidity risk scores generated by the plurality of machine learning models;
identify at least one comorbidity of the patient based on the aggregate of the comorbidity risk scores and a one of the comorbidity risk scores that is higher than a predetermined threshold value;
determine the identified at least one comorbidity of the patient is an overlooked, unreported, and/or undocumented comorbidity responsive to a determination that the identified at least one comorbidity not being included in the at least one reported comorbidity;
alter a dialysis treatment prescription for the patient based on the determined overlooked, unreported, and/or undocumented comorbidity; and
remotely program the altered dialysis treatment prescription into the dialysis machine;
wherein the dialysis machine is configured to provide the dialysis treatment for the patient based on the remotely programmed altered dialysis treatment prescription.
Other than the steps performed by the generic computer components, the underlined limitations are directed to methods of organizing human activity. The claim recites steps of extracting patient population data, accessing a plurality of machine learning models, training the models, extracting patient data, determining at least one reported comorbidity, generating comorbidity risk scores, aggregating the comorbidity risk scores, identifying at least one comorbidity, determining the identified comorbidity is an overlooked, unreported, and/or undocumented comorbidity, and programming the altered dialysis treatment prescription. These steps, under its broadest reasonable interpretation, are categorized as methods of organizing human activity, specifically associated with managing personal behavior or relationships or interactions between people (e.g. altering a dialysis treatment for a patient based on the determined overlooked, unreported, and/or undocumented comorbidity). The claim encompasses a person following rules or instructions to receive and process data in the manner described in the abstract idea. If the claim limitation, under its broadest reasonable interpretation, covers managing personal behavior or interactions between people but for the recitation of generic computer components, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. See MPEP §2106.04(a). The Examiner further notes that “Certain Methods of Organizing Human Activity” includes a person's interaction with a computer (see October 2019 Update: Subject Matter Eligibility at Pg. 5). Any limitation not identified above as part of methods of organizing human activity, are deemed “additional elements” and will be discussed further in detail below. Accordingly, claims 1 and 13 recite at least one abstract idea.
Similarly, dependent claims 5-7, 10-11, 17-18, 21-26 and 29-35 further narrow the abstract idea described in the independent claims. Claims 5-6, 17-18, 30 and 34 describe the machine learning models. Claims 7 and 22-26 describe the patient population data. Claims 10-11 describe the extracted patient data. Claim 21 describes the predetermined threshold value. Claims 29 and 31-33 describe the overlooked, unreported, and/or undocumented comorbidity. Claim 35 describes training each of the models. These limitations only serve to further limit the abstract idea and hence, are directed toward fundamentally the same abstract ideas as independent claims 1 and 13, even when considered individually and as an ordered combination.
Step 2A - Prong Two:
Regarding Prong Two of Step 2A, it must be determined whether the claim as a whole integrates the abstract idea into a practical application. It must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements merely using a computer to implement an abstract idea, adding insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a "practical application."
In the present case, claims 1, 5-7, 10, 11, 13, 17, 18, 21-26 and 29-35 as a whole do not integrate the abstract idea into a practical application because they do not impose meaningful limits on practicing the abstract idea. The additional elements or combination of additional elements, beyond the above-noted at least one abstract idea will be described as follows (where the bolded portions are the “additional limitations” while the underlined portions continue to represent the “abstract idea(s)”).
Specifically, independent claim 1 recites: A system for treating a patient based on having determined an undocumented comorbidity condition in the patient, the system comprising:
a dialysis machine configured to provide a dialysis treatment for the patient; and
at least one computing device comprising:
at least one storage device storing instructions; and
at least one processor operatively coupled to the at least one storage device;
wherein the at least one processor, based on executing the instructions, is configured to cause the at least one computing device to:
extract population patient data from one or more databases corresponding to a pool of patients receiving dialysis treatment;
access a plurality of machine learning comorbidity models, each of the comorbidity models configured to generate a comorbidity risk score for a respective one of a plurality of comorbidities;
train each of the plurality of machine learning comorbidity models using the population patient data, excluding patient data of patients that have not been diagnosed with the respective one of a plurality of comorbidities specific comorbidity associated with a corresponding comorbidity model, to identify the respective one of the plurality of comorbidities;
extract patient data corresponding to the patient from patient records;
determine at least one reported comorbidity for the patient in the patient records;
generate a comorbidity risk score for each of the plurality of comorbidities using the plurality of machine learning comorbidity models with the extracted patient data;
aggregate the comorbidity risk scores generated by the plurality of machine learning models;
identify at least one comorbidity of the patient based on the aggregate of the comorbidity risk scores and a one of the comorbidity risk scores that is higher than a predetermined threshold value;
determine the identified at least one comorbidity of the patient is an overlooked, unreported, and/or undocumented comorbidity responsive to a determination that the identified at least one comorbidity not being included in the at least one reported comorbidity;
alter a dialysis treatment prescription for the patient based on the determined overlooked, unreported, and/or undocumented comorbidity; and
remotely program the altered dialysis treatment prescription into the dialysis machine;
wherein the dialysis machine is configured to provide the dialysis treatment for the patient based on the remotely programmed altered dialysis treatment prescription.
The claim recites the additional elements of a dialysis machine, computing device, storage device, processor, database and machine learning that implement the identified abstract idea. The computing device, storage device, processor, database and machine learning are not described by the applicant and are recited at a high-level of generality such that they amounts to no more than mere instructions to apply the exception using a generic computer component (i.e., merely invoking the computer structure as a tool used to execute the limitations, MPEP 2106.05(f)). The dialysis machine generally links the use of a judicial exception to a particular technological environment or field of use, and thus, does not integrate a judicial exception into a practical application. In addition, the recitation of altering a dialysis prescription based on the determined overlooked, unreported, and/or undocumented comorbidity “recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished”, which is equivalent to the words "apply it" (MPEP 2106.05(f)).
Claim 1 further recites the additional element of providing the dialysis treatment. Under practical application, providing the dialysis treatment is a form of extra-solution activity. MPEP 2106.5(g) indicates the term "extra-solution activity" can be understood as activities incidental to the primary process or product that are merely a nominal or tangential addition to the claim. Therefore, even in combination, these additional elements do not integrate the abstract idea into a practical application.
The dependent claims 7, 23 and 31 recite additional element(s) beyond those recited in the independent claims that implement the identified abstract idea. Claim 7 and 31 recite a healthcare facility. Claim 23 recites Centers for Medicaid & Medicare Services. However, these additional elements do not integrate a practical application more than the abstract idea because:
the healthcare facility and Centers for Medicaid & Medicare Services generally link the use of a judicial exception to a particular technological environment or field of use.
Accordingly, the claims as a whole do not integrate the abstract idea into a practical application as they do not impose any meaningful limits on practicing the abstract idea.
Step 2B
Regarding Step 2B, representative independent claim 1 does not include additional elements (considered both individually and as an ordered combination) that are sufficient to amount to significantly more than the judicial exception for the same reasons to those discussed above with respect to determining that the claim does not integrate the abstract idea into a practical application.
When viewed as a whole, claims 1, 5-7, 10, 11, 13, 17, 18, 21-26 and 29-35 do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite processes that are routine and well-known in the art and simply implements the process on a computer(s) is not enough to qualify as "significantly more."
As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of using a computing device, storage device, processor, database and machine learning to perform the noted steps amount to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (“significantly more”). In addition, the additional element of the dialysis machine generally links the use of the judicial exception to a particular technological environment or field of use, and thus, does not amount to significantly more than the judicial exception
Also, as discussed above with respect to integration of the abstract idea into a practical application, the additional element of providing the dialysis treatment was considered extra-solution activity. This has been re-evaluated under the “significantly more” analysis and determined to be well-understood, routine, conventional activity in the field. Well-understood, routine, conventional activity cannot provide an inventive concept (“significantly more”). As such, the claims also do not recite significantly more than the abstract idea and are not patent eligible.
The dependent claims 7, 23 and 31 recite additional element(s) beyond those recited in the independent claims that implement the identified abstract idea. Claim 7 and 31 recite a healthcare facility. Claim 23 recites Centers for Medicaid & Medicare Services. However, these additional elements are not deemed significantly more than the abstract idea because:
the healthcare facility and Centers for Medicaid & Medicare Services generally link the use of a judicial exception to a particular technological environment or field of use.
Therefore, claims 1, 5-7, 10, 11, 13, 17, 18, 21-26 and 29-35 are rejected under 35 USC §101 as being directed to non-statutory subject matter.
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.
Claims 1, 5, 10-11, 13, 17, 22, 23, 25, 26, 29, 30, 32, 33 and 35 are rejected under 35 U.S.C. 103 as being unpatentable over Osorio (US 2014/0200414 A1) in further view of Chan (US Patent No. 10,733,566 B1) and Parisotto (US 2016/0199562 A1).
Regarding claim 1, Osorio teaches: A system for treating a patient based on having determined an undocumented comorbidity condition in the patient, the system comprising:
at least one computing device comprising at least one storage device storing instructions; and at least one processor operatively coupled to the at least one storage device; wherein the at least one processor, based on executing the instructions, is configured to cause the at least one computing device to: (a computer readable storage unit of the medical device encoded with instructions that, when executed by the computer, perform the method of the invention [0261], [0016], [0173]; the medical device comprises a controller comprising a processor capable of performing various executions of software components and memory [0111]-[0112])
access a plurality of […] comorbidity models, each of the comorbidity models configured to generate a comorbidity risk score for a respective one of a plurality of comorbidities; […] (assessing one or more comorbidities associated with a primary disease by assessing the body system at the site of the comorbidity, performed by: the autonomic index determination module/unit which determines the autonomic index, the neurologic index determination module/unit which determines the neurologic index, the stress marker index determination module/unit which determines the stress marker index, the psychiatric index determination module/unit which determines the psychiatric index, the endocrine index determination module/unit which determines the endocrine index, the quality of life index determination module/unit which determines the quality of life index [0015], [0121], [0044]-[0047], Fig. 4, Figs. 16-17)
[…] identify the respective one of the plurality of comorbidities; (assessing one or more comorbidities associated with a primary disease by assessing the body system at the site of the comorbidity; the assessment of the body system at the site of the comorbidity is performed by the autonomic index determination module/unit, the neurologic index determination module/unit, the stress marker index determination module/unit, the psychiatric index determination module/unit, the endocrine index determination module/unit, the quality of life index determination module/unit [0015], [0121], Fig. 4, Figs. 16-17)
extract patient data corresponding to the patient from patient records; (index measures may be derived from patient historical data [0042], [0173])
generate a comorbidity risk score for each of the plurality of comorbidities using the plurality of […] comorbidity models with the extracted patient data; (assessing a state of one or more comorbid diseases in a patient based on the comparison of one or more of an autonomic index, neurologic index, stress marker index, psychiatric index, endocrine index, adverse effect of therapy index, physical fitness index, and/or quality of life index (i.e. comorbidity risk score for each of the plurality of comorbidities) [0044]-[0047])
aggregate the comorbidity risk scores generated by the plurality of […] models; (index measures may be treated as a composite, and the weighted composite index (i.e. aggregate of the comorbidity risk scores) comprises a plurality of autonomic indices, neurologic indices, stress marker indices, adverse effect of therapy indices, physical fitness indices, quality of life indices or two or more, claim 28, claim 33, [0278]-[0279], [0042])
identify at least one comorbidity of the patient based on the aggregate of the comorbidity risk scores and a one of the comorbidity risk scores that is higher than a predetermined threshold value; determine the identified at least one comorbidity of the patient is an overlooked, unreported, and/or undocumented comorbidity responsive to a determination that the identified at least one comorbidity not being included in the at least one reported comorbidity. (a single index measure (i.e. one of the comorbidity risk scores) provides a univariate comparison on the effect of the patient’s disease state and a composite measure (i.e. aggregate of the comorbidity risk scores) provides a multivariate comparison on the effect of the disease state [0041]-[0042]; comparing the weighted composite index and/or the index value to a reference value, where reference values are predetermined from a set of normative data, to determine whether the comparison shows a change; if the determination is “yes” (construed to be higher than a predetermined threshold value), assessing the disease state [0278], [0263], [0097], [0054]-[0055]; assessing the state of the disease of the patient by identifying one or more comorbidities associated with the patient, which includes identifying new comorbidities not previously identified (i.e. determine an overlooked, unreported, and/or undocumented comorbidity) [0286], [0265], [0162], claim 113)
Osorio does not teach:
extract population patient data from one or more databases corresponding to a pool of patients […]
machine learning models
train each of the plurality of machine learning comorbidity models using the population patient data, excluding patient data of patients that have not been diagnosed with the specific comorbidity associated with a corresponding comorbidity model;
determine at least one reported comorbidity for the patient in the patient records;
However, Chan in the analogous art of analyzing patient data to identify medical conditions (col. 2 line 49 – col. 3 line 54) teaches:
extract population patient data from one or more databases corresponding to a pool of patients […] (“using a master set of coded hospital-provided data to train and test them. This master set may comprise hospital data…and may typically include data for hundreds of thousands of patient visits”, e.g. see col. 11 lines 48-52)
machine learning models (“an ensemble of condition models” where “models 210-240 may leverage gradient boosted models…neural network models…Other predictive machine learning models may also be utilized.”, e.g. see col. 10 lines 33-44)
train each of the plurality of machine learning comorbidity models using the population patient data, excluding patient data of patients that have not been diagnosed with the specific comorbidity associated with a corresponding comorbidity model; (“per-condition ML models 210-240 may be developed by using a master set of coded hospital-provided data to train and test them... For the purposes of developing and training the models, this master set is assumed to be correct in the aggregate, with patient medical conditions generally properly diagnosed…so that actually predictive factors can be identified”, e.g. see col. 11 lines 47-66)
determine at least one reported comorbidity for the patient in the patient records; (“predicting, based on electronic documentation received by the real-time medical communication system, which medical conditions have been documented”, e.g. see col. 3 lines 23-25)
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 teachings of Osorio to include extract population patient data from one or more databases corresponding to a pool of patients, train each of the plurality of machine learning comorbidity models using the population patient data, excluding patient data of patients that have not been diagnosed with the specific comorbidity associated with a corresponding comorbidity model and determine at least one reported comorbidity for the patient in the patient records as taught by Chan, for the purposes of “account[ing] for nuance and behavioral considerations” in medical data (Chan, col. 11 lines 28-30) and ensuring that there is accurate documentation of the patient’s health data on record (Chan, col. 2 lines 40-49).
Osorio and Chan do not teach:
a dialysis machine configured to provide a dialysis treatment for the patient;
a pool of patients receiving dialysis treatment
alter a dialysis treatment prescription for the patient based on the determined overlooked, unreported, and/or undocumented comorbidity; and
remotely program the altered dialysis treatment prescription into the dialysis machine; wherein the dialysis machine is configured to provide the dialysis treatment for the patient based on the remotely programmed altered dialysis treatment prescription.
However, Parisotto in the analogous art of automated control of a dialysis machine based on patient assessment scores ([0020], [0016]) teaches:
a dialysis machine configured to provide a dialysis treatment for the patient; (“a hemodialysis system 100 includes a hemodialysis machine 102”; the “hemodialysis machine 102 includes a processor” and is “connected to a network”, e.g. see [0059]-[0062]; “The control unit is also configured to adjust the treatment parameter”, e.g. see [0025])
a pool of patients receiving dialysis treatment (“The clinical server 123 can evaluate and analyze the historical data of thousands of patients to detect [hemodialysis] treatment trends.”, e.g. see [0133])
alter a dialysis treatment prescription for the patient based on the determined overlooked, unreported, and/or undocumented comorbidity; and (“modifying operation of a medical fluid treatment machine based on the patient assessment score” including “adjusting a treatment parameter of the medical fluid treatment machine”, e.g. see [0003], [0005]; “If, for example, the pressure of the blood on the venous side is less than or equal to 200 mmHg, the patient's Combined Patient Assessment Score is over 3.5, and symptoms of vascular access are present…The processor 125 of the hemodialysis machine 102 sends an instruction to the blood pump 132 to adjust the blood flow rate accordingly”, e.g. see [0115])
remotely program the altered dialysis treatment prescription into the dialysis machine; wherein the dialysis machine is configured to provide the dialysis treatment for the patient based on the remotely programmed altered dialysis treatment prescription. (“The hemodialysis machine 102 is configured to communicate with a clinical server 123 via the network 122…The processor 125 is configured to receive data from the clinical server 123 and control the hemodialysis machine 102 based on the received data.”, e.g. see [0062]; “the central server is further configured to… propose implementing a treatment modification that, if accepted, automatically modifies operation of medical fluid treatment machines”, e.g. see claim 34)
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 teachings of Osorio and Chan to include a dialysis machine configured to provide a dialysis treatment for the patient, a pool of patients receiving dialysis treatment, alter a dialysis treatment prescription for the patient based on the determined overlooked, unreported, and/or undocumented comorbidity and remotely program the altered dialysis treatment prescription into the dialysis machine; wherein the dialysis machine is configured to provide the dialysis treatment for the patient based on the remotely programmed altered dialysis treatment prescription as taught by Parisotto, for the purposes of providing the complex assessment required of dialysis patients (Parisotto [0057]).
Regarding claim 5, Osorio, Chan and Parisotto teach the system of claim 1 as described above.
Chan teaches machine learning models as described above.
Osorio further teaches:
access an aggregate comorbid model configured to receive output of each of the plurality of […] comorbidity models as data input; and input each comorbidity risk score of the plurality of […] comorbidity models into the aggregate comorbid model for calculating an overall comorbidity risk score of the patient having any comorbidity condition associated with the plurality of […] comorbidity models to aggregate the comorbidity risk scores (the assessment unit receives the information of the comparison of the index information received from the index determination units, to perform an assessment of at least one comorbidity [0160]-[0161]; the weighted composite index comprises a plurality of autonomic indices, neurologic indices, stress marker indices, adverse effect of therapy indices, physical fitness indices, quality of life indices or two or more, claim 28, claim 33, [0278]-[0279], [0042])
Regarding claim 7, Osorio, Chan and Parisotto teach the system of claim 1 as described above.
Osorio does not teach:
generate a report including at least a portion of the identified subset of the pool of patients and their respective patient risk scores; and
transmit the report to one or more health care facilities
However, Chan in the analogous art teaches:
generate a report including at least a portion of the pool of patients and their respective patient risk scores; and (generating a “list of patient cases prioritized by CDI scores”, e.g. see col. 2 line 62)
transmit the report to one or more health care facilities ( “generate an interface providing a list of patient cases ranked by the determined CDI score”, e.g. see col. 3 lines 4-5; CDI “refers to a process used in healthcare facilities”, e.g. see col. 1 lines 24-25)
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 teachings of Osorio to include generating a report of patients’ risk scores of the pool of patients and transmitting the report to a healthcare facility as taught by Chan, for the purposes of “efficiently and effectively initiate a query to resolve an identified documentation problem” (Chan, col. 2 lines 64-65).
Regarding claim 10, Osorio, Chan and Parisotto teach the system of claim 1 as described above.
Osorio further teaches:
wherein the extracted patient data comprises laboratory values, hospitalization history, hospitalization records, pharmacy prescription history, other documented comorbidity conditions, patient demographics, health care provider's notes, or keywords, or combinations thereof (the patient’s oxygen saturation, heart rate, cortisol level, EEG or EKG can be measured [0048], [0061], [0077]; a patient with congestive heart failure as a comorbidity [0045]-[0047])
Regarding claim 11, Osorio, Chan and Parisotto teach the system of claim 1 as described above.
Osorio further teaches:
wherein the extracted patient data comprises laboratory values, the laboratory values including hemoglobin levels, platelet count (PT), transferrin saturation (TSAT), or calcium levels, or combinations thereof (assessment using “blood hemogram” test (includes hemoglobin level and platelet count), e.g. see [0089])
Claim 13 recites substantially similar limitations as those already addressed in claim 1, and, as such is rejected for similar reasons as given above.
Regarding claim 17, Osorio, Chan and Parisotto teach the method of claim 13 as described above.
Chan teaches machine learning models as described above.
Osorio further teaches:
accessing an aggregate comorbid model configured to receive output of each of the plurality of […] comorbidity models as data input; and inputting each comorbidity risk score of the plurality of […] comorbidity models into the aggregate comorbid model for calculating an overall comorbidity risk score of the patient having any comorbidity condition associated with the plurality of […] comorbidity models to aggregate each of the comorbidity risk scores of the plurality of […] comorbidity models (the assessment unit receives the information of the comparison of the index information received from the index determination units, to perform an assessment of at least one comorbidity [0160]-[0161]; the weighted composite index comprises a plurality of autonomic indices, neurologic indices, stress marker indices, adverse effect of therapy indices, physical fitness indices, quality of life indices or two or more, claim 28, claim 33, [0278]-[0279], [0042])
Regarding claim 21, Osorio, Chan and Parisotto teach the method of claim 13 as described above.
Osorio does not teach:
wherein the predetermined threshold value is a predetermined threshold percentage, the predetermined threshold percentage being greater than or equal to 50%
However, Chan in the analogous art teaches:
wherein the predetermined threshold value is a predetermined threshold percentage, the predetermined threshold percentage being equal to or greater than 50% (the models return “numerical probabilities (which may each be expressed as a number between 0 and 1)”, e.g. see col. 18 lines 34-36; “This predictiveness factor can be compared with a configurable threshold for the given medical condition such that if the predictiveness factor is not smaller than the threshold, the system considers the medical condition to be valid.”, e.g. see col. 11 lines 38-42; in an example, a diagnostic probability of “0.60” (60%), e.g. see col. 18 lines 40-45)
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 teachings of Osorio to include the predetermined threshold value of 50% or greater as by Chan, for the purposes of representing a probability of the medical condition (Chan, col. 18 lines 40-45).
Regarding claim 22, Osorio, Chan and Parisotto teach the method of claim 13 as described above.
Osorio does not teach:
further comprising: analyzing the population patient data, prior to using one or more predictive models, for qualifying one or more patient records for inclusion into the one or more predictive models
However, Chan in the analogous art teaches:
further comprising: analyzing the population patient data, prior to using one or more predictive models, for qualifying one or more patient records for inclusion into the one or more predictive models (“Using a machine learning engine… an ML analysis of some portion (for example, 75%, 80%, 90%, or 95%) of the master set of data can be conducted so that actually predictive factors can be identified”; “For the purposes of developing and training the models, this master set is assumed to be correct”, e.g. see col. 11 lines 57-67)
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 teachings of Osorio to include analyzing the population patient date prior to inclusion into the one or more predictive models as taught by Chan, for the purposes of “account[ing] for nuance and behavioral considerations” in medical data (Chan, col. 11 lines 28-30).
Regarding claim 23, Osorio, Chan and Parisotto teach the method of claim 22 as described above.
Osorio does not teach:
wherein qualifying one or more patient records includes removing any outlier patients, patients with predetermined clinical indicators, or patients associated with Centers for Medicaid & Medicare Services, or combinations thereof
However, Chan in the analogous art teaches:
wherein qualifying one or more patient records includes removing any outlier patients, patients with predetermined clinical indicators, or patients associated with Centers for Medicaid & Medicare Services, or combinations thereof (qualifying records for the model by only using a “portion (for example, 75%, 80%, 90%, or 95%) of the master set” for training (the remaining portion is removed, i.e. outlier patients), e.g. see col. 11 lines 57-67)
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 teachings of Osorio to include qualifying one or more patient records includes removing any outlier patients, patients with predetermined clinical indicators, or patients associated with Centers for Medicaid & Medicare Services, or combinations thereof as taught by Chan, for the purposes of “account[ing] for nuance and behavioral considerations” in medical data (Chan, col. 11 lines 28-30).
Regarding claim 25, Osorio, Chan and Parisotto teach the method of claim 13 as described above.
Osorio further teaches:
wherein the population patient data comprises laboratory values, hospitalization history, hospitalization records, pharmacy prescription history, other documented comorbidity conditions, patient demographics, health care provider's notes, or keywords, or combinations thereof
However, Chan in the analogous art teaches:
wherein the population patient data comprises laboratory values, hospitalization history, hospitalization records, pharmacy prescription history, other documented comorbidity conditions, patient demographics, health care provider's notes, or keywords, or combinations thereof (the system may receive “Lab Orders, Microbiology Results, Pathology Results, Pharmacy Orders, Radiology Orders, Radiology Results, Cardiology Results, Vital Signs, Physician Documentation”, e.g. see col. 8 lines 33-37)
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 teachings of Osorio to include the population patient data as taught by Chan, for the purposes of “account[ing] for nuance and behavioral considerations” in medical data (Chan, col. 11 lines 28-30).
Regarding claim 26, Osorio, Chan and Parisotto teach the method of claim 25 as described above.
Osorio does not teach:
wherein the population patient data comprises laboratory values […]
However, Chan in the analogous art teaches:
wherein the population patient data includes laboratory values, the laboratory values including hemoglobin levels, platelet count (PT), transferrin saturation (TSAT), or calcium levels, or combinations thereof (a “complete blood count (CBC) lab procedure” includes hemoglobin and platelet count, e.g. see col. 14 line 52 – col. 15 line 14)
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 teachings of Osorio to include the population patient data laboratory values as taught by Chan, for the purposes of “account[ing] for nuance and behavioral considerations” in medical data (Chan, col. 11 lines 28-30).
Regarding claim 29, Osorio, Chan and Parisotto teach the system of claim 1 as described above.
Osorio does not teach:
wherein the at least one processor, based on executing the instructions, is further configured to cause the at least one computing device to correct the patient records to include the overlooked, unreported, and/or undocumented comorbidity
However, Chan in the analogous art teaches:
wherein the at least one processor, based on executing the instructions, is further configured to cause the at least one computing device to correct the patient records to include the overlooked, unreported, and/or undocumented comorbidity (correct under-documentation so that the documentation correctly and accurately presents the medical condition(s) of the patient, col. 24 lines 6-17, col. 33 lines 63-67; data for documenting a comorbidity is missing, then it is assumed to be undocumented, col. 22 lines 47-51)
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 teachings of Osorio to include correcting the patient records as taught by Chan. This assists in ensuring that there is accurate documentation of the patient’s health data on record (Chan, col. 2 lines 40-49).
Regarding claim 30, Osorio, Chan and Parisotto teach the system of claim 1 as described above.
Osorio does not teach:
wherein the plurality of machine learning comorbidity models are trained based on keywords indicating a patient has an associated comorbidity and miss keywords indicating a patient does not have the associated comorbidity
However, Chan in the analogous art teaches:
wherein the plurality of machine learning comorbidity models are trained based on keywords indicating a patient has an associated comorbidity and miss keywords indicating a patient does not have the associated comorbidity (extracting keywords of medical conditions such as “acute renal failure” and processing the documented medical concepts by machine learning models, col. 12 lines 56-66; if data for documenting a comorbidity is missing, then it is assumed to be undocumented, col. 22 lines 47-51)
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 teachings of Osorio to include the plurality of machine learning comorbidity models are trained based on keywords indicating a patient has an associated comorbidity and miss keywords indicating a patient does not have the associated comorbidity as taught by Chan. This assists in ensuring that there is accurate documentation of the patient’s health data on record (Chan, col. 2 lines 40-49).
Regarding claim 31, Osorio, Chan and Parisotto teach the system of claim 1 as described above.
Osorio does not teach:
wherein the at least one processor, based on executing the instructions, is further configured to cause the at least one computing device to determine a key performance indicator for tracking and improvement of a healthcare facility based on identifying the overlooked, unreported, and/or undocumented comorbidity
However, Chan in the analogous art teaches:
wherein the at least one processor, based on executing the instructions, is further configured to cause the at least one computing device to determine a key performance indicator for tracking and improvement of a healthcare facility based on identifying the overlooked, unreported, and/or undocumented comorbidity (the accurate representation of clinical status can be “translated into hospital quality report cards… [and] reimbursement”, e.g. see col. 2 lines 42-45; the system tracks "success rate" of each query to “learn and/or gain knowledge”, e.g. see col. 10 lines 7-8)
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 teachings of Osorio to include determining a key performance indicator for tracking and improvement of a healthcare facility as taught by Chan, for the purposes of “generating additional reimbursement” (Chan, col. 23 lines 61-62).
Claim 32 recites substantially similar limitations as those already addressed in claim 29, and, as such is rejected for similar reasons as given above.
Regarding claim 33, Osorio, Chan and Parisotto teach the method of claim 13 as described above.
Osorio further teaches:
further comprising determining clinical decision-making for treatment of the patient based on identifying the overlooked, unreported, and/or undocumented comorbidity (changes in index values relative to normative data may be used to issue warnings so that treatment or preventative measures may be instituted [0043], [0187])
Regarding claim 35, Osorio, Chan and Parisotto teach the system of claim 1 as described above.
Osorio does not teach:
wherein training each of the plurality of machine learning comorbidity models using the population patient data includes training each of the plurality of machine learning comorbidity models using: laboratory values, hospitalization history, hospitalization records, pharmacy prescription history, documented comorbidity conditions, patient demographics, health care provider's notes, keywords, and miss keywords
However, Chan in the analogous art teaches:
wherein training each of the plurality of machine learning comorbidity models using the population patient data includes training each of the plurality of machine learning comorbidity models using: laboratory values, hospitalization history, hospitalization records, pharmacy prescription history, documented comorbidity conditions, patient demographics, health care provider's notes, keywords, and miss keywords (the system may receive “Lab Orders, Microbiology Results, Pathology Results, Pharmacy Orders, Radiology Orders, Radiology Results, Cardiology Results, Vital Signs, Physician Documentation”, e.g. see col. 8 lines 33-37; extracting keywords of medical conditions such as “acute renal failure” and processing the documented medical concepts by machine learning models, col. 12 lines 56-66; if data for documenting a comorbidity is missing, then it is assumed to be undocumented, col. 22 lines 47-51)
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 teachings of Osorio to include training each of the plurality of machine learning comorbidity models using the population patient data includes training each of the plurality of machine learning comorbidity models using the data above as taught by Chan, for the purposes of “account[ing] for nuance and behavioral considerations” in medical data (Chan, col. 11 lines 28-30).
Claims 6, 18 , 24 and 34 are rejected under 35 U.S.C. 103 as being unpatentable over Osorio, Chan and Parisotto in further view of Holmes (US 2016/0180050 A1).
Regarding claim 6, Osorio, Chan and Parisotto teach the system of claim 5 as described above.
Osorio, Chan and Parisotto do not teach:
wherein the plurality of machine learning comorbidity models is selected from two or more of: a gastrointestinal (GI) bleed model, a pericarditis model, a myelodysplasia model, a hemolytic anemia model, or a sickle cell anemia model
However, Holmes in the analogous art of identifying a health risk of a patient ([0003]) teaches:
wherein the plurality of machine learning comorbidity models is selected from two or more of: a gastrointestinal (GI) bleed model, a pericarditis model, a myelodysplasia model, a hemolytic anemia model, or a sickle cell anemia model (the “system of the invention can be applied to any health condition” including “sickle cell disease” and “myelodysplastic syndromes”, e.g. see [0074]-[0076]; generating a “disease-specific logistic regression risk model”, e.g. see [0149])
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 teachings of Osorio, Chan and Parisotto to include the one or more predictive models mentioned above as taught by Holmes, for the purposes of “creat[ing]…highly-accurate disease-specific or health-condition specific models” (Holmes [0021]).
Claim 18 recites substantially similar limitations as those already addressed in claim 6, and, as such is rejected for similar reasons as giv