Abstract: 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.

Abstract: An erase-on-demand memory cell 10(1) includes a memory layer 110 and a heating layer 130 that can heat memory layer 110 to at least an erase-effective temperature, to erase its data contents. Memory chips 270(1) and electronic systems 200 include cells 10(1). Electronic systems 200(1) include logic circuitry 210 to issue a signal to initiate heating. Electronic systems 200(2) include memory chips 270(2) with one or more erase-on-demand memory cells 10(2) that include a memory layer 110. One or more reservoirs 262 store chemicals. One or more valves 252 retain the chemicals, and respond to a signal to open, reacting the chemicals and/or exposing memory layers 110 to the chemicals. A method of erasing data contents of memory cells includes determining existence of an erase demand scenario, generating a signal in response to the erase demand scenario, and actuating erasure of the memory cells upon issue of the signal.