Events

NYU Langone Machine Learning Seminar Series: Evaluating a COVID-19 AI Model to Facilitate Discharge With a Randomized Controlled Trial

Speaker: Vincent J. Major

Location: On-Line : Passcode: 447268
Videoconference link: https://nyulangone.zoom.us/j/95994962949?pwd=MW9kN3BHSFJUUS9OUGphOTJqWG1jUT09

Date: Friday, October 7, 2022

In 2020, we developed and validated a predictive model to help clinicians identify hospitalized adults with COVID-19 who may be ready for discharge given their low risk of adverse events. Whether this algorithm could prompt more timely discharge for stable patients in practice was unknown. To evaluate the system, we integrated model output into the electronic health record (EHR) at the four hospitals of NYU Langone Health. The aim of the study was to estimate the effect of displaying risk scores on length of stay (LOS). Display of the score was pseudo-randomized 1:1 into intervention and control arms. Adverse safety outcomes of death, hospice, and re-presentation were monitored. We also tracked adoption and sustained use through daily counts of score displays.