
-
Tsunoda vows to bring 'something different' after Red Bull promotion
-
Verstappen not happy with Tsunoda-Lawson Red Bull swap
-
Experts accuse 54 top Nicaragua officials of grave abuses
-
Remains of 30th victim of Los Angeles fires found
-
EU to target US online services after Trump tariffs: France
-
How Trump's 'liberation day' tariffs will impact China
-
Malaysia suspends search for long-missing flight MH370
-
Search for long-missing flight MH370 suspended: Malaysia minister
-
Europe hits out at Trump tariffs, keeps door open for talks
-
Myanmar's junta chief to head to Bangkok summit as quake toll surpasses 3,000
-
Lawson vows to prove he belongs in F1 after shock of Red Bull axing
-
Australia sweats through hottest 12 months on record: official data
-
Livestock theft is central to jihadist economy in west Africa
-
South African artist champions hyenas in 'eco-queer' quest
-
Danish PM in 'unity' Greenland visit amid US takeover threats
-
Taiwan says US tariffs 'highly unreasonable'
-
Lawson says ruthless Red Bull axing was 'tough to hear'
-
Heat humble Celtics for sixth straight win, Thunder roll on
-
Trump escalates trade war with sweeping global tariffs
-
Japan says US tariffs 'extremely regrettable', may break WTO rules
-
South Koreans anxious, angry as court to rule on impeached president
-
Juve at in-form Roma with Champions League in the balance
-
Injuries put undermanned Bayern's title bid to the test
-
Ovechkin scores 892nd goal -- three away from Gretzky's NHL record
-
Australian former rugby star Petaia signs for NFL's Chargers
-
China says opposes new US tariffs, vows 'countermeasures'
-
Athletics world watching as 'Grand Slam Track' prepares for launch
-
Heat humble Celtics for sixth straight win, Cavs top Knicks
-
Quake-hit Myanmar's junta chief to head to Bangkok summit
-
New Spielberg, Nolan films teased at CinemaCon
-
Shaken NATO allies to meet Trump's top diplomat
-
Israel's Netanyahu arrives in Hungary, defying ICC warrant
-
Shiny and deadly, unexploded munitions a threat to Gaza children
-
Stocks tank, havens rally as Trump tariffs fan trade war
-
Altomare hangs on to tie defending champ Korda at LPGA Match Play
-
Paraguay gold rush leaves tea producers bitter
-
Health concerns swirl as Bolivian city drowns in rubbish
-
Syria says deadly Israeli strikes a 'blatant violation'
-
Financial markets tumble after Trump tariff announcement
-
Starbucks faces new hot spill lawsuits weeks after $50mn ruling
-
Europe riled, but plans cool-headed response to Trump's tariffs
-
'Shenmue' voted most influential video game ever in UK poll
-
New coal capacity hit 20-year low in 2024: report
-
Revealed: Why monkeys are better at yodelling than humans
-
Hemogenyx Pharmaceuticals PLC Announces FDA Annual Report
-
Pantheon Resources PLC Announces Participation in Upcoming Investor Conferences
-
Key details on Trump's market-shaking tariffs
-
'A little tough love': Top quotes from Trump tariff talk
-
US business groups voice dismay at Trump's new tariffs
-
Grealish dedicates Man City goal to late brother

'AI doctor' better at predicting patient outcomes, including death
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.
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.
"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.
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."
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."
C.Garcia--AMWN