Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Applicant claims priority to application 63/335350, which was filed April 27th 2022. Examiner acknowledges Applicant’s claim for priority.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more.
Step 1
The claims fall within at least one of the four categories of patent eligible subject matter. The claims as written do not fall into “data per se” or “software per se”. Regardless, it will be shown in the following steps, that claims 1-20 are nonetheless unpatentable under 35 U.S.C. 101.
Step 2A Prong One
Claim 1 states:
An Artificial Intelligence (AI) based decision-support system, the system comprising:
a Data Pipeline (DP) configured to communicate with one or more health care provider systems and a plurality of wearable devices of a plurality of pediatric patients treated with a cardiotoxic pharmaceutical;
a Data Repository (DR);
and a processing device associated with the DR,
wherein the DP is configured to receive patient data and communicate the patient data to the DR, wherein the patient data is collected from a combination of the one or more health care provider systems and the plurality of wearable devices, and
wherein the DR is configured to receive the patient data from the DP and communicate the patient data to the processing device,
wherein the processing device is configured to execute at least one of an Artificial Intelligence Algorithm (AIA ) and a Machine Learning Algorithm (MLA) to divide the patient data into a training dataset and a validation dataset,
wherein at least one of the AIA and the MLA are configured to process the training dataset to generate an Al model to predict a probability of a patient experiencing a cardiac event as part of providing personalized cardio-oncology care to the patient through a mobile platform based on data collected from the patient and the plurality of pediatric patients,
wherein at least one of the AIA and the MLA are configured to process the Al model using the validation dataset to generate an Al Model Accuracy (AIMA) value,
and wherein the Al based decision-support system is configured to provide personalized care content to the mobile platform as part of providing personalized cardio-oncology care through risk stratification using assigned primary and secondary strategies based on risk level and provide patient reported data from the mobile platform to the DR as an update to the patient data.
The broadest reasonable interpretation of these steps includes mental processes and/ or organizing human activity because each bolded component can practically be performed by the human mind or with pen and paper. Other than reciting generic computer terms like a “processing device”, nothing in the claims precludes the bold portions from practically being performed in the human mind or with pen or paper. For example, but for the “processing device” language, “execute at least one of an Artificial Intelligence Algorithm (AIA ) and a Machine Learning Algorithm (MLA) to divide the patient data into a training dataset and a validation dataset, wherein at least one of the AIA and the MLA are configured to process the training dataset to generate an AI model to predict a probability of the patient experiencing a cardiac event” encompasses a mental process of the user following an algorithm to divide patient data into two various sets for predicting a cardiac event. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Independent claims 9 and 18 cover similar steps of communicating with one or more healthcare systems, executing an algorithm to process patient data for the purpose of generating an AI model, and providing personalized care content to the mobile platform for risk stratification. These claims fall under the same category of an abstract idea and follows the same rationale as claim 1.
Dependent claims recite additional subject matter which further narrows or defines the abstract idea embodied in the claims (such as claim 14, reciting particular aspects of how a “Data Pipeline (DP) configured to communicate with one or more health care provider systems and a plurality of wearable devices of a plurality of pediatric patients treated with a cardiotoxic pharmaceutical” which may be performed in the mind but for recitation of “wearable devices”).
Dependent claims 2, 3, 4, and 11 add additional elements to their parent claims which will be further inspected in the following steps for a practical application to their abstract idea.
Step 2A Prong Two
This judicial exception of “Mental Processes” or “Organizing Human Activity” is not integrated into a practical application. Independent claim 1's system recites additional elements such as wearable devices, processing devices, and an AI model. Independent claims 9 and 18 also recite the generic components and additional elements listed above. The as wearable devices, processing devices, and AI model will be treated as a generic computer components. In particular, these additional elements do not integrate the abstract idea into a practical application because the additional elements:
amount to mere instructions to apply an exception (such as recitation of “a processing device associated with the data repository”, and “to generate an Al model” amounts to invoking computers as a tool to perform the abstract idea, see MPEP 2106.05(f))
add insignificant extra-solution activity to the abstract idea (such as recitation of “wherein the patient data is collected from a combination of the one or more health care provider systems and the plurality of wearable devices” or “communicate the patient data to the processing device” amounts to mere data gathering, see MPEP 2106.05(g))
Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims. For instance, dependent claims add additional elements of “input device”, “server”, or “processing device” to their parent claims. These additional elements will be considered general computer components. Additionally, claims 2 and 11 “to receive the patient data from a Data Pipeline Input Device (DPIP)” additional limitations which add insignificant extra-solution activity to the abstract idea which amounts to mere data gathering, claims 5-6, 14-15, and 19 recite “modify the AI model” or “configured to process the training data” or “reprocess the AI model” as additional limitations which add insignificant extra-solution activity to the abstract idea by selecting a particular data source or type of data to be manipulated, claims 7, 16, and 20’s “collect new patient data; communicate the new patient data with the DR; and process the Al model using the new patient data to update the Al model; and communicate the Al model and the new patient data to the DR” recite additional limitations which amount to insignificant application). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application.
The remaining dependent claims 3, 4, 8, 10, 12, 13, and 17 do not recite additional elements or activity but further narrow or define the abstract idea embodied in the claims and hence also do not integrate the aforementioned abstract idea into a practical application.
Step 2B
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 discussion of integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply an exception, and add insignificant extra-solution activity to the abstract idea.
To elaborate:
“wherein the patient data is collected from a combination of the one or more health care provider systems and the plurality of wearable devices”, is equivalently, receiving or transmitting data over a network, Symantec, MPEP
“communicate the patient data to the processing device”, is equivalently, storing and retrieving information in memory, Versata Dev. Group, MPEP 2106.05(d)(II)(iv);
“divide the patient data into a training dataset and a validation dataset” , is equivalently, selecting information, based on types of information and availability of information, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A;
“process the training dataset”, is equivalently, performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii);
Dependent claims recite additional subject matter which, as discussed above with respect to integration of the abstract idea into a practical application, amount to invoking computers as a tool to perform the abstract idea. Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims. These additional limitations amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields. To elaborate:
claims 2 and 11 “to receive the patient data from a Data Pipeline Input Device (DPIP)” , is equivalently, receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i);
claims 5 and 14’s “the processing device is configured to modify the Al model and reprocess the Al model using the validation dataset” , is equivalently, performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii);
claims 5 and 14’s “the processing device is configured to test the Al model with predetermined prospective data to generate an Al model performance value.” , is equivalently, performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii);
claims 6 and 15 “the processing device is configured to reprocess the Al model using the patient data using at least one of the Al algorithm and the ML algorithm”, is equivalently, performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii);
claims 7, 16, and 20’s “collect new patient data” , is equivalently, receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i);
claims 7, 16, and 20’s “communicate the new patient data with the DR”, is equivalently, receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i);
claims 7, 16, and 20’s “and process the Al model using the new patient data to update the Al model” , is equivalently, performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii);
claims 7, 16, and 20’s “communicate the Al model and the new patient data to the DR” , is equivalently, receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i);
claim 19’s “modify the AI model, and reprocessing the AI model using the validation dataset to redetermine the AIMA value” , is equivalently, performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii);
claim 19’s “testing the AI model with predetermined prospective data to generate an AI model performance value” , is equivalently, performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii);
claim 19’s “reprocessing the AI model using the patient data” , is equivalently, performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii);
Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Choudhuri in view of Oikonomou.
Regarding claim 1, Choudhuri teaches:
An Artificial Intelligence (AI) based decision-support system the system comprising: ([0005] A system for medical data management for a computing device providing indications for patientcare”)
a Data Pipeline (DP) configured to communicate with one or more health care provider systems and a plurality of wearable devices of a plurality of pediatric patients treated with a cardiotoxic pharmaceutical; ([0085] “DNS and content delivery network” depicts the DP; see also [0097] “FIG. 4 also gives an indication of how medical data can be collected and put into the system, in a single usable visual format. FIG. 4 shows wearables, where the “wearables” data may be from over 300+ wearable devices are available for use in the system platform for medical data collection.” and [0037] “When the chart is opened, the system auto will receive a set number of pieces of inform (vitals, notes, demographics, diagnostic test results, medical procedures, vitals, health statistics, observations, etc.) to populate the dashboard, and it does that immediately, so that the auto chart prep is an immediate time savings and shows the clinician in one view, everything they need to take care of the patient. [0070] “If a cardiac patient is on cancer medication, the prescribed post cancer medication may impact cardiac treatment. Thus, the system may include medical record databases, so this valuable medical information may be considered” where the system receives patient information via wearable devices across various demographics [i.e., pediatric patients] to be used alongside existing cancer treatment protocols [i.e., a cardiotoxic pharmaceutical]))
a Data Repository (DR) ([0099] “data lake eco system platform” is a DR); and a processing device associated with the DR ([0005] “processor can execute instructions for managing data resources associated with patient care” where the processor depicts the DR),
wherein the DP is configured to receive patient data and communicate the patient data to the DR, ([0085] “The access may be through an http (request/response) 108” where the content delivery network accesses and retrieves data from the data lake ecosystem platform; also see “request (108)” [figure1]),
wherein the patient data is collected from a combination of the one or more health care provider systems and the plurality of wearable devices, ([0097] “FIG. 4 also gives an indication of how medical data can be collected and put into the system, in a single usable visual format. FIG. 4 shows wearables, where the “wearables” data may be from over 300+ wearable devices are available for use in the system platform for medical data collection.” is collection of pediatric patient data into the systems from wearable devices)
wherein the DR is configured to receive the patient data from the DP and communicate the patient data to the processing device ([0085] “Data may be requested and sent back to the API receivers in the platform for further determination and carrying out executed instruction” where the API receivers also depict the DP),
wherein the processing device is configured to execute at least one of an Artificial Intelligence Algorithm (AIA ) and a Machine Learning Algorithm (MLA) to divide the patient data into a training dataset and a validation dataset ([0009] “a rules engine of the clinical intelligence engine may be used for at least one of data verification elements such as the source of information” where the engine sources the information by separating the validation data from the training data),
wherein at least one of the AIA and the MLA are configured to process the training dataset to generate an AI model ([0090] “neural networks analysis (310) which runs subroutines to determine… an illness” where subroutines are processing data to create a predictive diagnostic model) to predict a probability of a patient experiencing a cardiac event, ([0127] For patient health and chart information, profile section deals with patient profile data generated using patient demographics, vitals and procedure reports like ECG, Echo, Cath, Stress and Lab… See, e.g., FIG. 2, “Heart Score” 202 and the cardio vascular conditions risk predictions 210) where patient demographics comprise age categories of a patient [i.e., the patient and plurality of pediatric patients])
Regarding claim 1, Choudhuri does not teach, as taught by Oikonomou et al.
as part of providing personalized cardio-oncology care to the patient through a mobile platform based on data collected from the patient and the plurality of pediatric patients ([Table 2] “Multivariable Cox regression model for prediction of cardiovascular mortality in long‐term survivors of childhood cancer” provides personalized cardio -oncology care for patients in a mobile manner)
Choudhuri-Oikonomou as a combination continue to teach:
wherein at least one of the AIA and the MLA are configured to process the AI model using the validation dataset to generate an AI Model Accuracy (AIMA) value. ([Choudhuri 0090] “NPL Engine (306)” and “network validation (312)” and “respective score of value” (316) where the NPL engine [i.e., AIA /MLA] uses network validation [i.e., process the AI Model] to make a score of values [i.e., AIMA values] to judge the accuracy of the model; see also [Figure 3])
and wherein the Al based decision-support system is configured to provide personalized care content to the mobile platform as part of providing personalized cardio-oncology care (see [Oikonomou Table 2] above for personalized cardio-oncology care) through risk stratification using assigned primary and secondary strategies based on risk level and provide patient reported data from the mobile platform to the DR as an update to the patient data. ([Choudhuri 0045] “Prioritization may use machine learning and AI techniques to allow the application to prioritize data and create the output for the user to view. The data may determine that certain pieces of data may apply a value to the data, based on clinician use, relevancy, guidelines, rules, etc. and may …. output based on the values of the data, presenting the information likely to be the most relevant useful to the user. The user can request that the graphical output show more or less data.” Where the prioritization using AI techniques [i.e., and AI based decision support system] applies a value to the data based on clinician guidelines [i.e., risk stratification] and allows the clinicians to show more or less data [i.e., using primary and secondary strategies based on risk level]; see also [Choudhuri 0056] “The RPM Alerts dashboard is additional warnings that are tied to a specific patient's threshold(s) for which the physician needs to be alerted for when the vitals parameters are reaching or went beyond the thresholds set. This allows the Physician to prioritize a group of patients that are showing more extreme signals compared to the normal feedback shown by their health statistics.” Where feedback shown by their health statistic [i.e., a personalized care content] is updated with the vital parameters by the patient; see also [Choudhuri 0100] “FIG. 7a is a mobile patient chart” i.e., a mobile platform)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Choudhuri with the teachings of Oikonomou, with a reasonable expectation of success, by explicitly using pediatrics cardio oncology data for providing personalized care content in their clinical scoring system. This would provide a healthcare professional with more information to diagnose a patient’s current health status. Oikonomou is adaptable to Choudhuri as both disclosures clinically score patient information for prognosing a patient’s disease state. Choudhuri would have found Oikonomou’s teaching while researching the paucity of risk‐stratification tools to identify those [childhood cancer survivors] at higher‐than‐normal risk.
Regarding claim 2, Choudhuri teaches all of the limitations of claim 1. Choudhuri also teaches:
wherein the DP is configured to receive the patient data from a Data Pipeline Input Device (DPIP) ([0093] “user input (UI) module may receive user input through one or more of input device” where UI module depicts the data pipeline receiving patient data)
Regarding claim 3, Choudhuri teaches all of the limitations of claim 1. Choudhuri also teaches:
wherein the Data Pipeline (DP) includes at least one of a DP computer server and a DP processing device, wherein the DP computer server and DP processing device are configured to communicate the patient data to the DR via at least one of a hardwired communication and a wireless communication ([0095] “computing device may be connected to external devices through wired or wireless connection … to receive data or send data to a remote server” where the computing device is a DP processing device and the server is associated with the DP; see also “computer (100)” [figure 1])
Regarding claim 4, Choudhuri teaches all of the limitations of claim 2. Choudhuri also teaches:
wherein the DPIP includes at least one of an ECG/EKG machine, a blood pressure machine, a heart rate monitor, an MRI machine, a CT Scanner, an ultrasound machine, a computer, a laptop, a tablet, a smartphone, a PDA and a Patient Records Registry ([Figure 1] a computing device (100) is the DPIP).
Regarding claim 5, Choudhuri teaches all of the limitations of claim 1. Choudhuri also teaches:
wherein, if the AIMA value ([0090] see “respective score of value” reference above) is less than an AIMA threshold value ([0040] “Data that meets a minimum or maximum threshold value then is ranked or prioritize as information likely to be considered by the clinician” denotes AIMA threshold value), the processing device is configured to modify the AI model and reprocess the AI model using the validation dataset to redetermine the AIMA value ([0090] “the system will store the information and put it back into the system in a relearning process” where the information includes AIMA threshold values and validation datasets; see also Figure 3’s relearning process (314); and if the AIMA value is greater than the AIMA threshold value (see “threshold value” above), the processing device is configured to test the AI model with predetermined prospective data to generate an AI model performance value (see “relearning process” above where the information includes prospective data; see also [0059] “The collected data of similar patients may include information that the application may use when determining the likelihood of success when a parameter is changed” where the collected data includes a performance value)
Regarding claim 6, Choudhuri teaches all of the limitations of claim 5. Choudhuri also teaches:
wherein, if the AI model performance value is less than an AI threshold value ([0040] “Data that meets a minimum or maximum threshold value then is ranked or prioritize as information likely to be considered by the clinician” denotes threshold value), the processing device is configured to reprocess the AI model using the patient data using at least one of the AI algorithm and the ML algorithm ([0090] “the system will store the information and put it back into the system in a relearning process” where the information includes threshold values, performance values, and patient data; see also Figure 3’s “relearning process” (314) and “likelihood of success” above); and if the AI model performance value is greater than the AI threshold value, the processing device is configured to implement the AI model ([0090]“The information analyzed by the neural networks may then go to an execution of key entity extraction” where execution of key entity extraction is implementing the AI model)
Regarding claim 7, Choudhuri teaches all of the limitations of claim 6. Choudhuri also teaches:
wherein if the AI model is implemented, the processor is configured to, collect new patient data; communicate the new patient data with the DR ([0085] “The access may be through an http (request/response) 108” where the content delivery network accesses and retrieves data from the data lake ecosystem platform holding existing and newly created data; also see “request (108)” [figure1] where collection occurs via the http request/response); and process the AI model using the new patient data to update the AI model ([0090] “NPL Engine (306)” and “network validation (312)” and “data may be stored (316)” where the NPL engine [i.e. AI model] uses network validation [i.e. process the AI Model] using the newly stored patient data [i.e. data may be stored]; see also [Figure 3]); and communicate the AI model and the new patient data to the DR ([0090] “The data may then be stored” where data is the new AI model and patient data)
Regarding claim 8, Choudhuri teaches all of the limitations of claim 1. Choudhuri also teaches:
wherein the cardiac event is at least one of heart failure, heart disease and myocardial infarction ([Table 1] “Aortic value disease” is a heart disease)
Regarding claim 9, Choudhuri teaches:
An Artificial Intelligence (AI) based decision-support system ([0070] “a cardiac patient is on cancer medication” where the patient’s care is provided by the AI system), the system comprising:
a Data Pipeline (DP) configured to communicate with one or more health care provider systems and a plurality of wearable devices of a plurality of pediatric patients treated with a cardiotoxic pharmaceutical; ([0085] “DNS and content delivery network” depicts the DP; see also [0097] “FIG. 4 also gives an indication of how medical data can be collected and put into the system, in a single usable visual format. FIG. 4 shows wearables, where the “wearables” data may be from over 300+ wearable devices are available for use in the system platform for medical data collection.” and [0037] “When the chart is opened, the system auto will receive a set number of pieces of inform (vitals, notes, demographics, diagnostic test results, medical procedures, vitals, health statistics, observations, etc.) to populate the dashboard, and it does that immediately, so that the auto chart prep is an immediate time savings and shows the clinician in one view, everything they need to take care of the patient. [0070] “If a cardiac patient is on cancer medication, the prescribed post cancer medication may impact cardiac treatment. Thus, the system may include medical record databases, so this valuable medical information may be considered” where the system receives patient information via wearable devices across various demographics [i.e., pediatric patients] to be used alongside existing cancer treatment protocols [i.e., a cardiotoxic pharmaceutical]))
a Data Repository (DR) ([0099] “data lake eco system platform” is a DR);
and a processing device associated with the DR, ([0005] “processor can execute instructions for managing data resources associated with patient care” where the processor depicts the DR),
wherein the patient data is collected from a combination of the one or more health care provider systems and the plurality of wearable devices, ([0097] “FIG. 4 also gives an indication of how medical data can be collected and put into the system, in a single usable visual format. FIG. 4 shows wearables, where the “wearables” data may be from over 300+ wearable devices are available for use in the system platform for medical data collection.” is collection of pediatric patient data into the systems from wearable devices)
wherein the DP is configured to receive patient data and communicate the patient data to the DR ([0085] “The access may be through an http (request/response) 108” where the content delivery network [i.e. the DP] accesses and retrieves data from the data lake ecosystem platform [i.e. DR]; also see “request (108)” [figure1]),
and wherein the DR is configured to receive the patient data from the DP and communicate the patient data to the processing device ([0085] “Data may be requested and sent back to the API receivers in the platform for further determination and carrying out executed instruction” where the API receivers [i.e. the DP] request data from the database [i.e. the DR’s processing device]),
wherein the processing device is configured to execute at least one of an Artificial Intelligence Algorithm (AIA ) and a Machine Learning Algorithm (MLA) to process at least a portion of the patient data to generate an AI model ([0090] “neural networks analysis (310) which runs subroutines to determine… an illness” where subroutines are processing data to create a predictive diagnostic model) to predict a probability of a patient experiencing a cardiac event, ([0127] For patient health and chart information, profile section deals with patient profile data generated using patient demographics, vitals and procedure reports like ECG, Echo, Cath, Stress and Lab… See, e.g., FIG. 2, “Heart Score” 202 and the cardio vascular conditions risk predictions 210) where patient demographics comprise age categories of a patient [i.e., the patient and plurality of pediatric patients])
Regarding claim 9, Choudhuri does not teach, as taught by Oikonomou et al.
as part of providing personalized cardio-oncology care to the patient through a mobile platform based on data collected from the patient and the plurality of pediatric patients ([Table 2] “Multivariable Cox regression model for prediction of cardiovascular mortality in long‐term survivors of childhood cancer” provides personalized cardio -oncology care for patients in a mobile manner)
Choudhuri-Oikonomou as a combination continue to teach:
([0127]” the cardio vascular conditions risk predictions (210) and to generate and AI Model Accuracy (AIMA) value ([0090] “NPL Engine (306)” and “respective score of value” (316) and “network validation (312)” where the engine [i.e. AIA /MLA] uses network validation [i.e. process the AI Model] to make a score of values [i.e. AIMA values] to judge the accuracy of the model; see also [Figure 3])
and wherein the Al based decision-support system is configured to provide personalized care content to the mobile platform as part of providing personalized cardio-oncology care (see [Oikonomou Table 2] above for personalized cardio-oncology care) through risk stratification using assigned primary and secondary strategies based on risk level and provide patient reported data from the mobile platform to the DR as an update to the patient data. ([Choudhuri 0045] “Prioritization may use machine learning and AI techniques to allow the application to prioritize data and create the output for the user to view. The data may determine that certain pieces of data may apply a value to the data, based on clinician use, relevancy, guidelines, rules, etc. and may …. output based on the values of the data, presenting the information likely to be the most relevant useful to the user. The user can request that the graphical output show more or less data.” Where the prioritization using AI techniques [i.e., and AI based decision support system] applies a value to the data based on clinician guidelines [i.e., risk stratification] and allows the clinicians to show more or less data [i.e., using primary and secondary strategies based on risk level]; see also [Choudhuri 0056] “The RPM Alerts dashboard is additional warnings that are tied to a specific patient's threshold(s) for which the physician needs to be alerted for when the vitals parameters are reaching or went beyond the thresholds set. This allows the Physician to prioritize a group of patients that are showing more extreme signals compared to the normal feedback shown by their health statistics.” Where feedback shown by their health statistic [i.e., a personalized care content] is updated with the vital parameters by the patient; see also [Choudhuri 0100] “FIG. 7a is a mobile patient chart” i.e., a mobile platform)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Choudhuri with the teachings of Oikonomou, with a reasonable expectation of success, by explicitly using pediatrics cardio oncology data for providing personalized care content in their clinical scoring system. This would provide a healthcare professional with more information to diagnose a patient’s current health status. Oikonomou is adaptable to Choudhuri as both disclosures clinically score patient information for prognosing a patient’s disease state. Choudhuri would have found Oikonomou’s teaching while researching the paucity of risk‐stratification tools to identify those [childhood cancer survivors] at higher‐than‐normal risk.
Regarding claim 10, Choudhuri teaches all of the limitations of claim 9. Choudhuri also teaches:
wherein the processing device is configured to divide the patient data into a training dataset and a validation dataset ([0009] “a rules engine of the clinical intelligence engine may be used for at least one of data verification elements such as the source of information” where the engine sources the information by separating the validation data from the training data), wherein at least one of the AIA and the MLA are configured to process the training dataset to generate the AI model ([0090] “neural networks analysis (310) which runs subroutines to determine… an illness” where subroutines are processing data to create a predictive diagnostic model), and wherein at least one of the AIA and the MLA are configured to process the AI model using the validation dataset to generate the AI Model Accuracy (AIMA) value ([0090] “NPL Engine (306)” and “respective score of value… data” (316) and “network validation (312)” where the engine [i.e. AIA /MLA] uses network validation [i.e. process the AI Model] to make a score of values [i.e. AIMA values] to judge the accuracy of the model; see also [Figure 3])
Regarding claim 11, Choudhuri teaches all of the limitations of claim 9. Choudhuri also teaches:
wherein the DP is configured to receive the patient data from a Data Pipeline Input Device (DPIP) ([0093] “user input (UI) module may receive user input through one or more of input device” where UI module depicts the data pipeline receiving patient data)
Regarding claim 12, Choudhuri teaches all of the limitations of claim 9. Choudhuri also teaches:
wherein the Data Pipeline (DP) includes at least one of a DP computer server and a DP processing device, wherein the DP computer server and DP processing device are configured to communicate the patient data to the DR via at least one of a hardwired communication and a wireless communication ([0095] “computing device may be connected to external devices through wired or wireless connection … to receive data or send data to a remote server” where the computing device is a DP processing device and the server is associated with the DP; see also “computer (100)” [figure 1])
Regarding claim 13, Choudhuri teaches all of the limitations of claim 11. Choudhuri also teaches:
wherein the DPIP includes at least one of an ECG/EKG machine, a blood pressure machine, a heart rate monitor, an MRI machine, a CT Scanner, an ultrasound machine, a computer, a laptop, a tablet, a smartphone, a PDA and a Patient Records Registry ([Figure 1] a computing device (100) is the DPIP).
Regarding claim 14, Choudhuri teaches all of the limitations of claim 9. Choudhuri also teaches:
wherein, if the AIMA value (see respective score of value reference above) is less than an AIMA threshold value ([0040] “Data that meets a minimum or maximum threshold value then is ranked or prioritize as information likely to be considered by the clinician” denotes AIMA threshold value), the processing device is configured to modify the AI model and reprocess the AI model using the validation dataset to redetermine the AIMA value ([0090] “the system will store the information and put it back into the system in a relearning process” where the information includes AIMA threshold values and validation datasets; see also Figure 3’s relearning process (314); and if the AIMA value is greater than the AIMA threshold value (see “threshold value” above), the processing device is configured to test the AI model with predetermined prospective data to generate an AI model performance value (see “relearning process” above where the information includes prospective data; see also [0059] “The collected data of similar patients may include information that the application may use when determining the likelihood of success when a parameter is changed” where the collected data is a performance value)
Regarding claim 15, Choudhuri teaches all of the limitations of claim 14. Choudhuri also teaches:
wherein, if the AI model performance value is less than an AI threshold value ([0040] “Data that meets a minimum or maximum threshold value then is ranked or prioritize as information likely to be considered by the clinician” denotes threshold value), the processing device is configured to reprocess the AI model using the patient data using at least one of the AI algorithm and the ML algorithm ([0090] “the system will store the information and put it back into the system in a relearning process” where the information includes threshold values, performance values, and patient data; see also Figure 3’s “relearning process” (314) and “likelihood of success” above); and if the AI model performance value is greater than the AI threshold value, the processing device is configured to implement the AI model ([0090]“The information analyzed by the neural networks may then go to an execution of key entity extraction” where execution of key entity extraction is implementing the AI model)
Regarding claim 16, Choudhuri teaches all of the limitations of claim 15. Choudhuri also teaches:
wherein if the AI model is implemented, the processor is configured to, collect new patient data; communicate the new patient data with the DR ([0085] “The access may be through an http (request/response) 108” where the content delivery network accesses and retrieves data from the data lake ecosystem platform [i.e. the DR] holding existing and newly created data; also see “request (108)” [figure1]); and process the AI model using the new patient data to update the AI model ([0090] “NPL Engine (306)” and “network validation (312)” and “data may be stored (316)” where the NPL engine [i.e. AI model] uses network validation [i.e. process the AI Model] using the newly stored patient data [i.e. data may be stored]; see also [Figure 3]); and communicate the AI model and the new patient data to the DR ([0090] “The data may then be stored” where data is the new AI model and patient data)
Regarding claim 17, Choudhuri teaches all of the limitations of claim 9. Choudhuri also teaches:
wherein the cardiac event is at least one of heart failure, heart disease and myocardial infarction ([Table 1] “Aortic value disease” is a heart disease)
Regarding claim 18, Choudhuri teaches:
A method for training an Artificial Intelligence (AI) based decision-support system ([0070] “a cardiac patient is on cancer medication” where the patient’s care is provided by this AI trained system),
wherein the system includes a Data Pipeline (DP) configured to communicate with one or more health care provider systems and a plurality of wearable devices of a plurality of pediatric patients treated with a cardiotoxic pharmaceutical ([0085] “DNS and content delivery network” depicts the DP; see also [0097] “FIG. 4 also gives an indication of how medical data can be collected and put into the system, in a single usable visual format. FIG. 4 shows wearables, where the “wearables” data may be from over 300+ wearable devices are available for use in the system platform for medical data collection.” and [0037] “When the chart is opened, the system auto will receive a set number of pieces of inform (vitals, notes, demographics, diagnostic test results, medical procedures, vitals, health statistics, observations, etc.) to populate the dashboard, and it does that immediately, so that the auto chart prep is an immediate time savings and shows the clinician in one view, everything they need to take care of the patient. [0070] “If a cardiac patient is on cancer medication, the prescribed post cancer medication may impact cardiac treatment. Thus, the system may include medical record databases, so this valuable medical information may be considered” where the system receives patient information via wearable devices across various demographics [i.e., pediatric patients] to be used alongside existing cancer treatment protocols [i.e., a cardiotoxic pharmaceutical]))
a Data Repository (DR) ([0099] “data lake eco system platform” is a DR)
and a processing device associated with the data repository ([0005] “processor can execute instructions for managing data resources associated with patient care” where the processor depicts the DR),
the method comprising: receiving patient data via the DP wherein the patient data is collected from a combination of the one or more health care provider systems and the plurality of wearable devices ([0085] “The [content delivery network] access may be through an http (request/response) 108” where the content delivery network [i.e. the DP] accesses and retrieves patient data from the data lake ecosystem platform; also see “request (108)” [figure1]; ([0097] “FIG. 4 also gives an indication of how medical data can be collected and put into the system, in a single usable visual format. FIG. 4 shows wearables, where the “wearables” data may be from over 300+ wearable devices are available for use in the system platform for medical data collection.” is collection of pediatric patient data into the systems from wearable devices);
communicating the patient data to the DR and the processing device ([0085] “Data may be requested and sent back to the API receivers in the platform for further determination and carrying out executed instruction” where the API receivers depicts the DP connecting to the database [i.e. the DR]; see also “data lake ecosystem platform” above);
and processing the patient data to execute at least one of an Artificial Intelligence Algorithm (AIA ) and a Machine Learning Algorithm (MLA) to divide the patient data into a training dataset and a validation dataset ([0009] “a rules engine of the clinical intelligence engine may be used for at least one of data verification elements such as the source of information” where the engine [i.e. the AIA ] sources the information by separating the validation data from the training data)
processing the training dataset to generate an AI model to predict a probability of a patient experiencing a cardiac event ([0090] “neural networks analysis (310) which runs subroutines to determine… an illness” where subroutines are processing data to create a predictive diagnostic model; see also [0127]” the cardio vascular conditions risk predictions (210)”),
Regarding claim 18, Choudhuri does not teach, as taught by Oikonomou et al.
as part of providing personalized cardio-oncology care to the patient through a mobile platform based on data collected from the patient and the plurality of pediatric patients ([Table 2] “Multivariable Cox regression model for prediction of cardiovascular mortality in long‐term survivors of childhood cancer” provides personalized cardio -oncology care for patients in a mobile manner)
Choudhuri-Oikonomou as a combination continue to teach:
and processing the AI model using the validation dataset to generate an AI Model Accuracy (AIMA) value providing personalized care content to the mobile platform as part of providing personalized cardio-oncology care through risk stratification using assigned primary and secondary strategies based on risk level, ([0090] “NPL Engine (306)” and “network validation (312)” and “respective score of value” (316) where the engine [i.e. AIA /MLA] uses network validation [i.e. process the AI Model] to make a score of values [i.e. AIMA values] to judge the accuracy of the model; see also [Choudhuri 0045] “Prioritization may use machine learning and AI techniques to allow the application to prioritize data and create the output for the user to view. The data may determine that certain pieces of data may apply a value to the data, based on clinician use, relevancy, guidelines, rules, etc. and may …. output based on the values of the data, presenting the information likely to be the most relevant useful to the user. The user can request that the graphical output show more or less data.” Where the prioritization using AI techniques [i.e., and AI based decision support system] applies a value to the data based on clinician guidelines [i.e., risk stratification] and allows the clinicians to show more or less data [i.e., using primary and secondary strategies based on risk level]; see and [Oikonomou Table 2] Multivariable Cox regression model for prediction of cardiovascular mortality in long‐term survivors of childhood cancer”)
and providing patient reported data from the mobile platform to the DR as an update to the patient data. ([Choudhuri 0056] “The RPM Alerts dashboard is additional warnings that are tied to a specific patient's threshold(s) for which the physician needs to be alerted for when the vitals parameters are reaching or went beyond the thresholds set. This allows the Physician to prioritize a group of patients that are showing more extreme signals compared to the normal feedback shown by their health statistics.” Where feedback shown by their health statistic [i.e., a personalized care content] is updated with the vital parameters by the patient; see also [Choudhuri 0100] “FIG. 7a is a mobile patient chart” i.e., a mobile platform
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Choudhuri with the teachings of Oikonomou, with a reasonable expectation of success, by explicitly using pediatrics cardio oncology data for providing personalized care content in their clinical scoring system. This would provide a healthcare professional with more information to diagnose a patient’s current health status. Oikonomou is adaptable to Choudhuri as both disclosures clinically score patient information for prognosing a patient’s disease state. Choudhuri would have found Oikonomou’s teaching while researching the paucity of risk‐stratification tools to identify those [childhood cancer survivors] at higher‐than‐normal risk.
Regarding claim 19, Choudhuri teaches all of the limitations of claim 18. Choudhuri also teaches:
further comprising, if the AIMA value (see respective score of value reference above) is less than an AIMA threshold value ([0040] “Data that meets a minimum or maximum threshold value then is ranked or prioritize as information likely to be considered by the clinician” denotes AIMA threshold value), modify the AI model, and reprocessing the AI model using the validation dataset to redetermine the AIMA value ([0090] “the system will store the information and put it back into the system in a relearning process” where the information includes AIMA threshold values and validation datasets; see also Figure 3’s relearning process (314); and if the AIMA value is greater than the AIMA threshold value (see “threshold value” above), testing the AI model with predetermined prospective data to generate an AI model performance value (see “relearning process” above where the information includes prospective data; see also [0059] “The collected data of similar patients may include information that the application may use when determining the likelihood of success when a parameter is changed” where the collected data includes a performance value), wherein if the AI model performance value is less than an AI threshold value ([00