Computer network architecture with machine learning and artificial intelligence and dynamic patient guidance
Embodiments in the present disclosure relate generally to computer network architectures for machine learning, artificial intelligence, and dynamic patient guidance. Embodiments automatically update patient guidance in the patient care plan, based on the effectiveness of the guidance to date, attributes of the patient, other updated information, ongoing experience of the network, and updated predictions of possible patient outcomes and metrics.
1. A method that utilizes artificial intelligence and machine learning, comprising:
logging a patient into a dynamic patient guidance web application (DPGWA) in electronic communication with both a prediction module and a user device,
receiving, by the DPGWA, data from the patient about the patient behavior and/or compliance with a patient care plan,
logging the patient out of the DPGWA,
automatically re-scoring, by the DPGWA, the patient's risk scores by accessing a patient risk scoring web application,
based on the new risk scores, updating, by the DPGWA, the patient care plan,
sending, by the DPGWA, an automated message for the patient to the user mobile device requesting that the patient complete a check-in with the DPGWA and receive the updated patient care plan,
creating, by the DPGWA, a reminder task for a patient clinical care coordinator to contact the patient, if the patient has not responded within a time period,
if the patient has a designated caregiver, sending, by the DPGWA, a notification to the designated caregiver either (1) to prompt the patient to respond or (2) to respond on behalf of the patient to provide patient check-in information, and receive the updated patient care plan, and
if the patient adheres to their patient care plan, reducing, by the DPGWA, the cadence of interventions by a care coordinator for that patient,
receiving, by a learning module with a training submodule and in electronic communication with a prediction module and an updated database, a list of algorithm definitions and datasets for patient risk scoring,
automatically calibrating, by the learning module, one or more defined algorithms with the database,
testing, by the learning module, the calibrated algorithms with a plurality of evaluation metrics,
storing, by the learning module, the calibrated algorithms and evaluation metrics in a library,
automatically selecting, by the learning module, an algorithm for patient risk scoring based on the evaluation metrics,
updating, by the learning module, further the database with third party data, and with user episode data, and
re-executing, by the learning module, the calibrate, test, store, and select steps after the update of the database step,
receiving, by the prediction module with a prediction generator, a user prediction request for patient risk scoring, including episode data and a client model,
running, by the prediction module, the currently selected algorithm corresponding to the user of the episode data, and generating patient risk scoring prediction output,
generating, by the prediction module, a patient risk scoring prediction report based on the algorithm output, and
transmitting, by the prediction module, the patient risk scoring prediction report to the user,
wherein, the algorithm definitions are of types that are members of the group comprising:
multi-level models,
random forest regression,
logistical regression,
gamma-distributed regression, and
linear regression;
the third party data is from a party that is a member of the group comprising:
hospitals,
medical practices,
insurance companies,
credit reporting agencies, and
credit rating agencies;
the database includes patient medical data, patient personal data, patient outcome data, and medical treatment data;
the episode data includes individual patient medical data and personal data; and
the user is a member of the group comprising:
hospitals,
medical practices, and
insurance companies,
wherein the user device is remote from the prediction module, and the user device is a member of the group comprising:
a computer,
a desktop PC,
a laptop PC,
a smart phone,
a tablet computer, and
a personal wearable computing device,
wherein the web application communicates with the user device by the Internet, or an extranet, or a VPN, or other network, and the web application is generic for any user, or customized for a specific user, or class of user, and
wherein, the user prediction request requests calibration of the correlation of demographic, social and medical attributes of the patient, to the outcome of a specific patient clinical episode type.
2. A method that utilizes artificial intelligence and machine learning, comprising:
logging a patient into a dynamic patient guidance web application (DPGWA) in electronic communication with a prediction module, a patient risk scoring web application, and a user device, wherein the prediction module has a prediction generator and an updated database, wherein the prediction module is in electronic communication with a learning module with a training submodule,
receiving, by the DPGWA, data from the patient about the patient behavior and/or compliance with a patient care plan,
logging the patient out of the DPGWA,
automatically re-scoring, by the DPGWA, the patient's risk scores by accessing the patient risk scoring web application,
based on the new risk scores, updating, by the DPGWA, the patient care plan,
sending, by the DPGWA, an automated message for the patient to the user mobile device requesting that the patient complete a check-in with the DPGWA and receive the updated patient care plan,
creating, by the DPGWA, a reminder task for a patient clinical care coordinator to contact the patient, if the patient has not responded within a time period,
if the patient has a designated caregiver, sending, by the DPGWA, a notification to the designated caregiver either (1) to prompt the patient to respond or (2) to respond on behalf of the patient to provide patient check-in information, and receive the updated patient care plan, and
if the patient adheres to their patient care plan, reducing, by the DPGWA, the cadence of interventions by a care coordinator for that patient.
3. The method of claim 2 , further comprising:
receiving, by the learning module, a list of algorithm definitions and datasets for patient risk scoring,
automatically calibrating, by the learning module, one or more defined algorithms with the database,
testing, by the learning module, the calibrated algorithms with a plurality of evaluation metrics,
storing, by the learning module, the calibrated algorithms and evaluation metrics in a library,
automatically selecting, by the learning module, an algorithm for patient risk scoring based on the evaluation metrics,
updating, by the learning module, further the database with third party data, and with user episode data, and
re-executing, by the learning module, the calibrate, test, store, and select steps after the update of the database step.
4. The method of claim 2 , further comprising:
receiving, by the prediction module with a prediction generator, a user prediction request for patient risk scoring, including episode data and a client model,
running, by the prediction module, the currently selected algorithm corresponding to the user of the episode data, and generating patient risk scoring prediction output,
generating, by the prediction module, a patient risk scoring prediction report based on the algorithm output, and
transmitting, by the prediction module, the patient risk scoring prediction report to the user.
5. The method of claim 2 , wherein:
the algorithm definitions are of types that are members of the group comprising:
multi-level models,
random forest regression,
logistical regression,
gamma-distributed regression, and
linear regression;
the third party data is from a party that is a member of the group comprising:
hospitals,
medical practices,
insurance companies,
credit reporting agencies, and
credit rating agencies;
the database includes patient medical data, patient personal data, patient outcome data, and medical treatment data;
the episode data includes individual patient medical data and personal data; and
the user is a member of the group comprising:
hospitals,
medical practices, and
insurance companies.
6. The method of claim 2 , wherein the user device is remote from the prediction module, and the user device is a member of the group comprising:
a computer,
a desktop PC,
a laptop PC,
a smart phone,
a tablet computer, and
a personal wearable computing device.
7. The method of claim 2 , wherein the web application communicates with the user device by the Internet, or an extranet, or a VPN, or other network, and the web application is generic for any user, or customized for a specific user, or class of user, and
wherein, the user prediction request requests calibration of the correlation of demographic, social and medical attributes of the patient, to the outcome of a specific patient clinical episode type.
8. A method that utilizes a web application for artificial intelligence and machine learning, comprising:
logging a patient into a dynamic patient guidance web application (DPGWA) in electronic communication with a prediction module, a patient risk scoring web application, and a user device,
receiving, by the DPGWA, data from the patient about the patient behavior and/or compliance with a patient care plan,
logging the patient out of the DPGWA,
automatically re-scoring, by the DPGWA, the patient's risk scores by accessing the patient risk scoring web application,
based on the new risk scores, updating, by the DPGWA, the patient care plan,
sending, by the DPGWA, an automated message for the patient to the user mobile device requesting that the patient complete a check-in with the DPGWA and receive the updated patient care plan,
creating, by the DPGWA, a reminder task for a patient clinical care coordinator to contact the patient, if the patient has not responded within a time period,
if the patient has a designated caregiver, sending, by the DPGWA, a notification to the designated caregiver either (1) to prompt the patient to respond or (2) to respond on behalf of the patient to provide patient check-in information, and receive the updated patient care plan, and
if the patient adheres to their patient care plan, reducing, by the DPGWA, the cadence of interventions by a care coordinator for that patient,
receiving, by a learning module with a training submodule and in electronic communication with a prediction module and an updated database, a list of algorithm definitions and datasets for patient risk scoring, automatically calibrating, by the learning module, one or more defined algorithms with the database,
testing, by the learning module, the calibrated algorithms with a plurality of evaluation metrics,
storing, by the learning module, the calibrated algorithms and evaluation metrics in a library,
automatically selecting, by the learning module, an algorithm for patient risk scoring based on the evaluation metrics,
updating, by the learning module, further the database with third party data, and with user episode data, and
re-executing, by the learning module, the calibrate, test, store, and select steps after the update of the database step,
receiving, by a prediction generator of the prediction module, a user prediction request for patient risk scoring, including episode data and a client model,
running, by the prediction generator, the currently selected algorithm corresponding to the user of the episode data, and generating patient risk scoring prediction output,
generating, by the prediction generator, a patient risk scoring prediction report based on the algorithm output, and
transmitting, by the prediction generator, the patient risk scoring prediction report to the user,
wherein, the algorithm definitions are of types that are members of the group comprising:
multi-level models,
random forest regression,
logistical regression,
gamma-distributed regression, and
linear regression;
the third party data is from a party that is a member of the group comprising:
hospitals,
medical practices,
insurance companies,
credit reporting agencies, and
credit rating agencies;
the database includes patient medical data, patient personal data, patient outcome data, and medical treatment data;
the episode data includes individual patient medical data and personal data; and
the user is a member of the group comprising:
hospitals,
medical practices, and
insurance companies,
wherein, the user device is remote from the prediction module, and
the user device is a member of the group comprising:
a computer,
a desktop PC,
a laptop PC,
a smart phone,
a tablet computer, and
a personal wearable computing device,
wherein the web application communicates with the user device by the Internet, or an extranet, or a VPN, or other network, and the web application is generic for any user, or customized for a specific user, or class of user, and
wherein, the user prediction request requests calibration of the correlation of demographic, social and medical attributes of the patient, to the outcome of a specific patient clinical episode type.
9. A method that utilizes a dynamic patient guidance web application with artificial intelligence and machine learning, comprising:
logging a patient into a dynamic patient guidance web application (DPGWA) in electronic communication with a prediction module, a patient risk scoring web application, and a user device,
receiving, by the DPGWA, data from the patient about the patient behavior and/or compliance with a patient care plan,
logging the patient out of the DPGWA,
automatically re-scoring, by the DPGWA, the patient's risk scores by accessing the patient risk scoring web application,
based on the new risk scores, updating, by the DPGWA, the patient care plan,
sending, by the DPGWA, an automated message for the patient to the user mobile device requesting that the patient complete a check-in with the DPGWA and receive the updated patient care plan,
creating, by the DPGWA, a reminder task for a patient clinical care coordinator to contact the patient, if the patient has not responded within a time period,
if the patient has a designated caregiver, sending, by the DPGWA, a notification to the designated caregiver either (1) to prompt the patient to respond or (2) to respond on behalf of the patient to provide patient check-in information, and receive the updated patient care plan, and
if the patient adheres to their patient care plan, reducing, by the DPGWA, the cadence of interventions by a care coordinator for that patient.
10. The method of claim 9 , further comprising:
receiving, by a learning module with a training submodule and in electronic communication with the prediction module and an updated database, a list of algorithm definitions and datasets for patient risk scoring,
automatically calibrating, by the learning module, one or more defined algorithms with the database,
testing, by the learning module, the calibrated algorithms with a plurality of evaluation metrics,
storing, by the learning module, the calibrated algorithms and evaluation metrics in a library,
automatically selecting, by the learning module, an algorithm for patient risk scoring based on the evaluation metrics,
updating, by the learning module, further the database with third party data, and with user episode data, and
re-executing, by the learning module, the calibrate, test, store, and select steps after the update of the database step.
11. The method of claim 9 , further comprising:
receiving, by a prediction generator of the prediction module, a user prediction request for patient risk scoring, including episode data and a client model,
running, by the prediction generator, the currently selected algorithm corresponding to the user of the episode data, and generating patient risk scoring prediction output,
generating, by the prediction generator, a patient risk scoring prediction report based on the algorithm output, and
transmitting, by the prediction generator, the patient risk scoring prediction report to the user.
12. The method of claim 9 , wherein:
the algorithm definitions are of types that are members of the group comprising:
multi-level models,
random forest regression,
logistical regression,
gamma-distributed regression, and
linear regression;
the third party data is from a party that is a member of the group comprising:
hospitals,
medical practices,
insurance companies,
credit reporting agencies, and
credit rating agencies;
the database includes patient medical data, patient personal data, patient outcome data, and medical treatment data;
the episode data includes individual patient medical data and personal data; and
the user is a member of the group comprising:
hospitals,
medical practices, and
insurance companies.
13. The method of claim 9 ,
wherein the user device is remote from the prediction module, and the user device is a member of the group comprising:
a computer,
a desktop PC,
a laptop PC,
a smart phone,
a tablet computer, and
a personal wearable computing device.
14. The method of claim 9 , wherein the web application communicates with the user device by the Internet, or an extranet, or a VPN, or other network, and the web application is generic for any user, or customized for a specific user, or class of user, and
wherein, the user prediction request requests calibration of the correlation of demographic, social and medical attributes of the patient, to the outcome of a specific patient clinical episode type.