An 'AI Doctor' Is Helping Hospitals Predict Readmissions
Physicians' written notes can be notoriously hard to read, a bewildering combination of hard-to-interpret handwriting coupled with creative and individualized shorthand styles.
But “NYUTron,” a new artificial intelligence program now in use by New York University doctors and hospital executives, can not only read and accurately understand doctors’ notes, it can use them to predict whether a newly discharged patient will soon fall sick enough to be readmitted. NYUTron is what its developers call a “large language model,” an improvement over earlier health care computer algorithms that required data to be specially formatted and laid out in neat tables.
A study of its effectiveness showed that the program could predict about 80% of those patients who were readmitted for care. The tool also successfully assessed the likelihood that a patient might have additional conditions along with their primary disease, as well as the chances that insurance would deny coverage.
According to an NYU news release, “Programs like NYUTron can alert health care providers in real time about factors that might lead to readmission and other concerns so they can be swiftly addressed or even averted.”
By automating basic tasks, such technology could provide doctors more time to spend with their patients.
However, experts emphasize that NYUTron is considered a support tool for health care providers, not a replacement for a doctor’s judgment tailored to an individual patient.