entertainment -WSS

entertainment

author：fashion 2025-08-23 08:54:27 - browse：713

Blue numbers and letter falling down a tunnel. -- health tech coverage from STAT — Adobe

A growing number of AI tools are being used to predict everything from sepsis to strokes, with the hope of accelerating the delivery of life-saving care. But over time, new research suggests, these predictive models can become a victim of their own success — sending their performance into a nosedive and generating inaccurate, potentially harmful results.

“There is no accounting for this when your models are being tested,” said Akhil Vaid, an instructor of data-driven and digital medicine at the Icahn School of Medicine at Mount Sinai and author of the new research, published Monday in the Annals of Internal Medicine. “You can’t run validation studies, do external validation, run clinical trials — because all they’ll tell you is that the model works. And when it starts to work, that is when the problems will arise.”

Vaid and his Mount Sinai colleagues simulated the deployment of two models that predicted a patient’s risk of dying and acute kidney injury within five days of entering the ICU. Their simulations assumed that the models did what they were supposed to — lower deaths and kidney injury by identifying patients for earlier intervention.

Get unlimited access to award-winning journalism and exclusive events.

Subscribe Log In

Previous article： Apple is now the first public company to be valued at $3 trillion
Next article： Was Amgen transparent enough on FDA's concern on cancer drug?

focus

WSS

Chan Zuckerberg Biohub Chicago to focus on inflammation

Chan Zuckerberg Biohub Chicago to focus on inflammation

Time to name cancers by genetics, not organ of origin, expert says

Readout Newsletter: Biotech news, including Moderna's Covid vaccine

FDA rejects Alnylam's heart disease treatment over insufficient data

A $475,000 price tag for a new cancer drug: crazy or meh?

focus

entertainment

leisure time

Alkermes shareholders re

The real point of Kenneth Smith’s execution by nitrogen gas

Affirmative action in medical school literally saved lives

Senate panel eyes new effort on drug shortages

Wildfire smoke exposes gaps in outdoor worker protections

Eli Lilly buys Point Biopharma in radiopharmaceuticals play

How one medical school became remarkably diverse

AI can decode, harness the power of the humane immune system

Malaria cases in Florida and Texas: Here’s what you need to know

A Q&A with the global head of Boehringer Ingelheim's innovation unit

hotspot

AI can decode, harness the power of the humane immune system

Was Amgen transparent enough on FDA's concern on cancer drug?

Covid misinformation case heads to Supreme Court

Apple Vision Pro: A first look at health apps on the new VR headset

VC firm General Catalyst wants to buy a health system

Readout LOUD podcast: Vertex data, Aduhelm, & Woodcock retires

knowledge

focus

entertainment

knowledge