Multi-task deep learning of health care outcomes

A computer system for generating a communicable disease policy plan, the computer system comprising:

• a bus system;
• a storage device connected to the bus system, wherein the storage device stores program instructions;
• and
• a number of processors connected to the bus system, wherein the number of processors execute the program instructions:
• to identify a number of workplace policies for a plurality of business entities, wherein the workplace policies comprises a number of dimensions of data collected from a number of sources;
• to collect employment data for each of the business entities, the employment data including sick leave data about employees of the plurality of business entities;
• to determine metrics for the sick leave data during a given time interval;
• to simultaneously model the workplace policies and the metrics for sick leave data to identify correlations among the number of dimensions of data and generalize rules for predicting effective workplace policies, wherein the modeling outputs a vector comprising weighted averages for each policy of the number of workplace policies;
• to train a predictive model with the vectors of weighted averages;
• to predict, according to the predictive model, a number of effective workplace policies for a particular business entity based on the employment data of the particular business entity;
• and
• to generate the communicable disease policy plan for the particular business entity based on the number of effective workplace policies.

A computer program product for generating a communicable disease policy plan, the computer program product comprising:

• a computer-readable storage media;
• program code, stored on the computer-readable storage media, for identifying a number of workplace policies for a plurality of business entities, wherein the workplace policies comprises a number of dimensions of data collected from a number of sources;
• program code, stored on the computer-readable storage media, for collecting employment data for each of the business entities, the employment data including sick leave data about employees of the plurality of business entities;
• program code, stored on the computer-readable storage media, for determining metrics for the sick leave data during a given time interval;
• program code, stored on the computer-readable storage media, for simultaneously modeling the workplace policies and the metrics for sick leave data to identify correlations among the number of dimensions of data and generalize rules for predicting effective workplace policies, wherein the modeling outputs a vector comprising weighted averages for each policy of the number of workplace policies;
• program code, stored on the computer-readable storage media, for training a predictive model with the vectors of weighted averages;
• program code, stored on the computer-readable storage media, for predicting, according to the predictive model, a number of effective workplace policies for a particular business entity based on the employment data of the particular business entity;
• and
• program code, stored on the computer-readable storage media, for generating the communicable disease policy plan for the particular business entity based on the number of effective workplace policies.