Researchers say new AI program can predict majority of hospital readmissions

June 7 (UPI) -- Researchers at New York University have designed a new artificial intelligence program that can read notes by physicians, help diagnose patients and estimate their length of a hospital stay.

According to a new study published in the journal Nature, the new program, called NYUTron, was able to predict 80 percent of patients who were readmitted.

"Our findings highlight the potential for using large language models to guide physicians about patient care," said study lead author Lavender Jiang, a doctoral student at NYU's Center for Data Science. "Programs like NYUTron can alert healthcare providers in real time about factors that might lead to readmission and other concerns so they can be swiftly addressed or even averted."

Jiang also said NYUTron could help speed up workflow and allow physicians to spend more time speaking with their patients.

NYUTron also identified 85 percent of those who died in the hospital and was able to estimate 79 percent of patients' actual length of stay.

"These results demonstrate that large language models make the development of 'smart hospitals' not only a possibility, but a reality," said study senior author and neurosurgeon Eric Oermann. "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."