'AI doctor' better at predicting patient outcomes, including death

'AI doctor' better at predicting patient outcomes, including death

An army critical care nurse, tends to a Covid-19 patient on a ventilator; a predictive AI tool could soon help doctors better understand the likelihood of key patient outcomes
An army critical care nurse, tends to a Covid-19 patient on a ventilator; a predictive AI tool could soon help doctors better understand the likelihood of key patient outcomes. Photo: JEFF KOWALSKY / AFP/File
Source: AFP

PAY ATTENTION: Enjoy reading our stories? Join YEN.com.gh's Telegram channel for more!

Artificial intelligence has proven itself useful in reading medical imaging and even shown it can pass doctors' licensing exams.

Now, a new AI tool has demonstrated the ability to read physicians' notes and accurately anticipate patients' risk of death, readmission to hospital, and other outcomes important to their care.

Designed by a team at NYU Grossman School of Medicine, the software is currently in use at the university's affiliated hospitals throughout New York, with the hope that it will become a standard part of health care.

A study on its predictive value was published Wednesday in the journal Nature.

Lead author Eric Oermann, an NYU neurosurgeon and computer scientist, told AFP that while non-AI predictive models have been around in medicine for a long time, they were hardly used in practice because the data they needed requires cumbersome reorganization and formatting.

Read also

AI meets VR to keep Holocaust memory alive

But "one thing that's common in medicine everywhere, is physicians write notes about what they've seen in clinic, what they've discussed with patients," he said.

PAY ATTENTION: Сheck out news that is picked exactly for YOU ➡️ click on “Recommended for you” and enjoy!

"So our basic insight was, can we start with medical notes as our source of data, and then build predictive models on top of it?"

The large language model, called NYUTron, was trained on millions of clinical notes from the health records of 387,000 people who received care within NYU Langone hospitals between January 2011 and May 2020.

These included any records written by doctors, such as patient progress notes, radiology reports and discharge instructions, resulting in a 4.1-billion-word corpus.

One of the key challenges for the software was interpreting the natural language that physicians write in, which varies greatly among individuals, including in the abbreviations they choose.

Read also

EU approves first vaccine against common respiratory virus

By looking back at records of what happened, researchers were able to calculate how often the software's predictions turned out to be accurate.

They also tested the tool in live environments, training it on the records from, for example, a hospital in Manhattan then seeing how it fared in a Brooklyn hospital, with different patient demographics.

Not a substitute for humans

Overall, NYUTron identified an unnerving 95 percent of people who died in hospital before they were discharged, and 80 percent of patients who would be readmitted within 30 days.

It outperformed most doctors on its predictions, as well as the non-AI computer models used today.

But, to the team's surprise, "the most senior physician who's actually a very famous physician, he had superhuman performance, better than the model," said Oermann.

"The sweet spot for technology and medicine isn't that it's going to always deliver necessarily superhuman results, but it's going to really bring up that baseline."

Read also

EU wants to 'clearly label' AI-generated online content

NYUTron also correctly estimated 79 percent of patients' actual length of stay, 87 percent of cases where patients were denied coverage by insurance, and 89 percent of cases where a patient's primary disease was accompanied by additional conditions.

AI will never be a substitute for the physician-patient relationship, said Oermann. Rather, they will help "provide more information for physicians seamlessly at the point-of-care so they can make more informed decisions."

New feature: Сheck out news that is picked for YOU ➡️ click on “Recommended for you” and enjoy!

Source: AFP

Authors:
AFP avatar

AFP AFP text, photo, graphic, audio or video material shall not be published, broadcast, rewritten for broadcast or publication or redistributed directly or indirectly in any medium. AFP news material may not be stored in whole or in part in a computer or otherwise except for personal and non-commercial use. AFP will not be held liable for any delays, inaccuracies, errors or omissions in any AFP news material or in transmission or delivery of all or any part thereof or for any damages whatsoever. As a newswire service, AFP does not obtain releases from subjects, individuals, groups or entities contained in its photographs, videos, graphics or quoted in its texts. Further, no clearance is obtained from the owners of any trademarks or copyrighted materials whose marks and materials are included in AFP material. Therefore you will be solely responsible for obtaining any and all necessary releases from whatever individuals and/or entities necessary for any uses of AFP material.