Computer network architecture for a pipeline of models for healthcare outcomes with machine learning and artificial intelligence

1. A method that utilizes automated model pipeline, artificial intelligence, and machine learning, comprising:

receiving, by a learning module, a list of algorithm definitions and a dataset, the learning module including a learning database and a training database, the learning database including a predictive model library storing calibrated algorithms and associated evaluation metrics, and the training database including a model type library storing algorithms for a plurality of model types,

calibrating, by the learning module, one or more algorithms for a plurality of the model types with the dataset,

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 the predictive model library,

selecting, by the learning module, an algorithm from the calibrated algorithms based on the evaluation metrics and storing the selected algorithms in a prediction database,

updating, by the learning module, the training database with third party data, and user episode data,

re-executing, by the learning module, the calibrating, testing, storing, selecting, and updating steps automatically and continually, either periodically, occasionally, or with each user prediction request,

receiving, by a prediction generator, a user prediction request for specified healthcare outcomes, including episode data and a client model, wherein a prediction module includes the prediction generator and the prediction database, wherein a web application is in electronic communication with both the prediction module and a user device,

updating, by the prediction generator, the training database with the episode data in the user prediction request,

running, by the prediction generator, the currently selected algorithm corresponding to the user using the episode data, and generating prediction output for the specified healthcare outcomes,

generating, by the prediction generator, a prediction report based on the algorithm output, and

transmitting, by the prediction generator, the prediction report to the user;

wherein the specified prediction output includes a plurality of the specified healthcare outcomes with at least one output for each of: patient healthcare outcomes, costs, quality of care, patient satisfaction, insurance claims, and clinical outcomes;

wherein, the model types include at least one of each of:

multi-level models,

random forest regression,

logistical regression,

gamma-distributed regression, and

linear regression;

wherein, the third-party data is from a plurality of parties, with at least one party of each type in the group of types comprising:

hospitals,

medical practices,

insurance companies,

credit reporting agencies, and

credit rating agencies;

wherein, the training database includes patient medical data, patient personal data, patient outcome data, and medical treatment data;

wherein, the episode data includes individual patient medical data and personal data; and

wherein, 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 users, or customized for a specific user, or class of user, and

wherein, the web application is specific to a specific class of user requests.

2. A method that utilizes automated model pipeline, artificial intelligence, and machine learning, comprising:

receiving, by a learning module, a list of algorithm definitions and a dataset, the learning module including a learning database and a training database, the learning database including a predictive model library storing calibrated algorithms and associated evaluation metrics, and the training database including a model type library storing algorithms for a plurality of model types,

calibrating, by the learning module, one or more algorithms for a plurality of the model types with the dataset,

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 the predictive model library,

selecting, by the learning module, an algorithm from the calibrated algorithms based on the evaluation metrics and storing the selected algorithm in a prediction database,

updating, by the learning module, the training database with third party data, and user episode data,

re-executing, by the learning module, the calibrating, testing, storing, selecting, and updating steps automatically and continually, either periodically, occasionally, or with each user prediction request;

receiving, by a prediction generator, a user prediction request, including episode data and a client model, the prediction module including a prediction generator and the prediction database, and

updating, by the prediction generator, the training database with the episode data in the user prediction request,

running, by the prediction generator, the currently selected algorithm corresponding to the user using the episode data, and generating prediction output for the specified healthcare outcomes,

generating, by the prediction generator, a prediction report for the specified healthcare outcomes based on the algorithm output, and

transmitting, by the prediction generator, the prediction report to the user.

3. The method of claim 2 , wherein the specified prediction output includes a plurality of the specified healthcare outcomes with at least one output for each of: patient healthcare outcomes, costs, quality of care, patient satisfaction, insurance claims, and clinical outcomes.

4. The method of claim 2 , wherein:

the model types include at least one of each of:

multi-level models,

random forest regression,

logistical regression,

gamma-distributed regression, and

linear regression;

the third-party data is from a plurality of parties, with at least one party of each type in the group of types comprising:

hospitals,

medical practices,

insurance companies,

credit reporting agencies, and

credit rating agencies;

the training 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.

5. The method of claim 2 , wherein a web application is in electronic communication with both the prediction module, and a user device.

6. The method of claim 5 , 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 5 , 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 users, or customized for a specific user, or class of user, and

wherein, the web application is specific to a specific class of user requests.