PREDICTIVE MODELING OF RESPIRATORY DISEASE RISK AND EVENTS

摘要

An application server predicts respiratory disease risk, rescue medication usage, exacerbation, and healthcare utilization using trained predictive models. The application server includes model modules and submodel modules, which communicate with a database server, data sources, and client devices. The submodel modules train submodels by determining submodel coefficients based on training data from the database server. The submodel modules further determine statistical analysis data and estimates for medication usage events, healthcare utilization, and other related events. The model modules combine submodels to predict respiratory disease risk, exacerbation, rescue medication usage, healthcare utilization, and other related information. Model outputs are provided to users, including patients, providers, healthcare companies, electronic health record systems, real estate companies and other interested parties.

主权项

1. A method comprising:
receiving a user location from a computing device associated with the user at a receipt time; determining a current air quality data set by inputting the user location into an air quality data set, the current air quality data set comprising air quality data for an area including the user location; accessing a current meteorological data set by inputting the user location into a meteorological data set including weather information for the day of the receipt time; accessing a local environment and land use data set by inputting the user location into an environment and land use data set including data classifying land use and land vegetation cover; accessing a respiratory disease risk model comprising an immediate environment trigger submodel correlating local air quality data and meteorological data close in proximity in time to expected incidence of medication usage events as a function of user location; inputting the user location, the current air quality data set, the current weather data set, and the local environment and land use data set into the respiratory disease risk model to generate an expected respiratory disease risk for the user location; determining a recommended action based on the expected respiratory disease risk; and sending a respiratory disease risk notification to the computing device including the recommended action and the expected respiratory disease risk.