
-
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
-
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
-
US tariffs take aim everywhere, including uninhabited islands
-
Trump sparks trade war with sweeping global tariffs
-
Israeli strikes hit Damascus, central Syria; monitor says 4 dead
-
Slot 'hates' offside rule that gave Liverpool win over Everton
-
US stocks end up, but volatility ahead after latest Trump tariffs
-
Barca oust Atletico to set up Clasico Copa del Rey final
-
Mourinho grabs Galatasaray coach's face after losing Istanbul derby
-
Grealish strikes early as Man City move up to fourth in Premier League
-
Reims edge out fourth-tier Cannes to set up PSG French Cup final
-
Liverpool beat Everton as title looms, Man City win without Haaland
-
Jota wins bad-tempered derby as Liverpool move 12 points clear
-
Inter and Milan level in derby Italian Cup semi
-
Stuttgart beat Leipzig to reach German Cup final
-
Trump unveils sweeping global tariffs
-
Italian director Nanni Moretti in hospital after heart attack: media
-
LIV Golf stars playing at Doral with Masters on their minds
-
Trump unveils sweeping 'Liberation Day' tariffs
-
Most deadly 2024 hurricane names retired from use: UN agency
-
Boeing chief reports progress to Senate panel after 'serious missteps'
-
Is Musk's political career descending to Earth?
-
On Mexico-US border, Trump's 'Liberation Day' brings fears for future
-
Starbucks faces new hot spill lawsuit weeks after $50mn ruling
-
Ally of Pope Francis elected France's top bishop
-
'Determined' Buttler leads Gujarat to IPL win over Bengaluru
-
US judge dismisses corruption case against New York mayor
-
Left-wing party pulls ahead in Greenland municipal elections
-
Blistering Buttler leads Gujarat to IPL win over Bengaluru
-
Tesla sales slump as pressure piles on Musk
-
Amazon makes last-minute bid for TikTok: report
-
Canada Conservative leader warns Trump could break future trade deal
-
British band Muse cancels planned Istanbul gig
-
'I'll be back' vows Haaland after injury blow
-
Trump to unveil 'Liberation Day' tariffs as world braces
-
New coach Edwards adamant England can win women's cricket World Cup
-
Military confrontation 'almost inevitable' if Iran nuclear talks fail: French FM
-
US stocks advance ahead of looming Trump tariffs

'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