Computer network architecture with machine learning and artificial intelligence and risk adjusted performance ranking of healthcare providers

A computer network architecture with artificial intelligence and machine learning, comprising:

• a prediction module means for prediction with a prediction generator and an updated database,
• a learning module with artificial intelligence, machine learning, and a training submodule, in electronic communication with the prediction module means and the updated database,
• a patient risk scoring web application in electronic communication with the prediction module means and a user device, and
• a performance ranking web application (PRWA) with artificial intelligence and machine learning in electronic communication with the prediction module means, the patient risk scoring web application, and a user device, and
• wherein, the PRWA is configured to:
• a. log in a user, using a user device,
• b. receive a user request from the user device that a report on an a performance rankings be generated and transmitted,
• c. log out the user,
• d. automatically fit a two level regression model to the applicable data in the updated database, using a risk scoring web app,
• e. automatically predict the selected performance metrics for a level 1 for all patients with data in the architecture, and for a level 2 for all patients at the selected healthcare provider with data in the architecture,
• f. automatically calculate a standardized performance score for each provider based on the level 1 metrics and further based on the level 2 metrics for the respective provider,
• g. automatically rank all providers by performance score, and
• h. automatically produce and transmit to the user device, a report of performance ranking of each selected healthcare provider, and
• wherein, the learning module with artificial intelligence and machine learning is configured to:
• automatically receive a list of algorithm definitions and datasets for patient risk scoring,
• automatically calibrate one or more defined algorithms with the database,
• automatically test the calibrated algorithms with a plurality of evaluation metrics,
• automatically store the calibrated algorithms and evaluation metrics in a library,
• automatically select a currently selected best algorithm for patient risk scoring based on the best evaluation metrics,
• automatically update further the database with third party data, and with user episode data, and
• automatically re-execute the calibrate, test, store, and select steps after the update of the database step;
• wherein the prediction generator is configured to:
• receive a user prediction request for patient risk scoring, including episode data of an individual patient and a client model,
• run the currently selected best algorithm corresponding to the user of the episode data, and generate patient risk scoring prediction output,
• generate a patient risk scoring prediction report based on the algorithm output, wherein the patient risk scoring report identifies at least one possible medical treatment of an individual patient and an outcome probability associated with the at least one possible medical treatment, and
• transmit the patient risk scoring prediction report to the user.

A computer network architecture with a web application for artificial intelligence and machine learning and performance rankings:

• a performance ranking web application (PRWA) with artificial intelligence and machine learning in electronic communication with a prediction module means for prediction with a prediction generator, a learning module, a patient risk scoring web application, and a user device, and
• wherein, the PRWA is configured to:
• a. log in a user, using a user device,
• b. receive a user request from the user device that a report on performance rankings be generated and transmitted,
• c. log out the user,
• d. automatically fit a two level regression model to the applicable data in the updated database, using a risk scoring web app,
• e. automatically predict the selected performance metrics for a level 1 for all patients with data in the architecture, and for a level 2 for all patients at the selected healthcare provider with data in the architecture,
• f. automatically calculate a standardized performance score for each provider based on the level 1 metrics and further based on the level 2 metrics for the respective provider,
• g. automatically rank all providers by performance score, and
• h. automatically produce and transmit to the user device, a report of performance ranking of each selected healthcare provider,
• wherein, the learning module with artificial intelligence and machine learning is configured to:
• automatically receive a list of algorithm definitions and datasets for patient risk scoring,
• automatically calibrate one or more defined algorithms with the database,
• automatically test the calibrated algorithms with a plurality of evaluation metrics,
• automatically store the calibrated algorithms and evaluation metrics in a library,
• automatically select a currently selected best algorithm for patient risk scoring based on the best evaluation metrics,
• automatically update further the database with third party data, and with user episode data, and
• automatically re-execute the calibrate, test, store, and select steps after the update of the database step,
• wherein, the prediction generator is configured to:
• receive a user prediction request for patient risk scoring, including episode data of an individual patient and a client model,
• run the currently selected best algorithm corresponding to the user of the episode data, and generate patient risk scoring prediction output,
• generate a patient risk scoring prediction report based on the algorithm output, wherein the patient risk scoring report identifies at least one possible medical treatment of an individual patient and an outcome probability associated with the at least one possible medical treatment, and
• transmit the patient risk scoring prediction report to the user,
• wherein, the algorithm definitions are of types that are members of the group comprising one or more:
• multi-level models,
• random forest regression,
• logistical regression,
• gamma-distributed regression, or
• linear regression;
• the third party data is from a party that is a member of the group comprising one or more:
• hospitals,
• medical practices,
• insurance companies,
• credit reporting agencies, or
• credit rating agencies;
• the database includes one or more patient medical data, patient personal data, patient outcome data, or medical treatment data;
• the episode data includes one or more individual patient medical data or personal data;
• and
• the user is a member of the group comprising one or more:
• hospitals,
• medical practices, or
• insurance companies,
• wherein the user device is remote from the prediction module means, and the user device is a member of the group comprising one or more:
• a computer,
• a desktop PC,
• a laptop PC,
• a smart phone,
• a tablet computer, or
• 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 media and medical attributes of the patient, to the outcome of a specific patient clinical episode type.

A computer network architecture with a performance ranking web application with artificial intelligence and machine learning, comprising:

• a performance ranking web application (PRWA) with artificial intelligence and machine learning in electronic communication with a prediction module means for prediction with a prediction generator, a learning module, a patient risk scoring web application and a user device, and
• wherein, the PRWA web application is configured to:
• a. log in a user, using a user device,
• b. receive a user request from the user device that a report on a performance ranking be generated and transmitted,
• c. log out the user,
• d. automatically fit a two level regression model to the applicable data in the updated database, using a risk scoring web app,
• e. automatically predict the selected performance metrics for a level 1 for all patients with data in the architecture, and for a level 2 for all patients at the selected healthcare provider with data in the architecture,
• f. automatically calculate a standardized performance score for each provider based on the level 1 metrics and further based on the level 2 metrics for the respective provider,
• g. automatically rank all providers by performance score, and automatically produce and transmit to the user device, a report of performance ranking of each selected healthcare provider,
• wherein the prediction generator is configured to:
• receive a user prediction request for patient risk scoring, including episode data of an individual patient and a client model,
• run the currently selected best algorithm corresponding to the user of the episode data, and generate patient risk scoring prediction output,
• generate a patient risk scoring prediction report based on the algorithm output, wherein the patient risk scoring report identifies at least one possible medical treatment of an individual patient and an outcome probability associated with the at least one possible medical treatment, and
• transmit the patient risk scoring prediction report to the user.