Clinicians at New York City-based NYU Langone Health are using an artificial intelligence algorithm that can predict the chance of a discharged patient being readmitted within a month.
The tool, called NYUTron, was developed by researchers at the NYU Grossman School of Medicine. After testing on EHR data, NYUTron could predict 80 percent of patients who would be readmitted, according to a June 7 NYU Langone news release.
NYUTron shows about a 5 percent improvement in predicting readmission risk compared to standard computer models.
The program can also read clinician notes and predict the risk of death. Researchers trained the tool on the EHR data of 336,000 NYU Langone patients.
"These results demonstrate that large language models make the development of 'smart hospitals' not only a possibility, but a reality," study senior author and neurosurgeon Eric Oermann, MD, said in the release. "Since NYUTron reads information taken directly from the electronic health record, its predictive models can be easily built and quickly implemented through the healthcare system."