The Tribune

Researchers develop AI model that predicts disease risk from sleep data

Guardian

What we lose when we surrender care to algorithms

Youtube

- YouTube

Indiablooms

Stanford AI can predict 130 diseases from just one night of sleep

The Mighty 790 KFGO

Health Rounds: AI uses sleep study data to accurately predict dozens of health issues

Stanford Medicine

New AI model predicts disease risk while you sleep

Metaculus

Will There Be A Major Ai Related Healthcare Class Action Lawsuit Before 2028

The Hill

3965108 A Word Of Caution Before Ai Becomes Standard In Healthcare

Deloitte

AI in Health: Redefining patient care

Maeil Business Newpaper(MK)

Research has shown that sleep can go beyond simple rest and become a

University of Cambridge

Opinion: AI can transform health and medicine

Scripps News

Researchers say AI can accurately predict 130 diseases from one night of sleep

NDTV

Researchers Develop Ai Model That Predicts Disease Risk From Sleep Data 10460241

SciTech Daily

Stanfords Ai Predicts Disease Risk From A Single Night Of Sleep

Newsmax

1241115

Nature

A multimodal sleep foundation model for disease prediction

Elon Musk

Rishi Sunak

Kamala Harris

Bill Gates

Andrew Ng

Yoshua Bengio

Fei-Fei Li

Demis Hassabis

Melanie Mitchell

Sam Altman

Dario Amodei

Geoffrey Hinton

Yann LeCun

Gary Marcus

Max Tegmark

Connor Leahy

Eliezer Yudkowsky

Jaan Tallinn

Marc Andreessen

Eric Schmidt

Norbert Wiener

Arthur Clarke

Irving John Good

Claude Shannon

Hans Moravec

John Smart

There's a "wall of fear-mongering and doomerism" in the AI world right now.

"Worrying about AI today is like worrying about overpopulation on Mars."

Concerns that AI could pose a threat to humanity is "preposterously ridiculous."

Claiming AI poses an existential threat is "such an extreme" and risks "wip[ing] out some of its potential benefits."

"I'm more concerned about... the risks that are here and now [than the existential threat of AI]."

Current AI is "not anywhere close" to posing an existential threat but it could in the future.

AI is the "biggest existential threat" to humanity.

AGI's worst-case scenario would be "lights-out for all of us."

Powerful AI systems "taking control" pose an "existential threat."

AI has a "10 to 25 per cent" chance of destroying humanity.

"The most likely result of building a superhumanly smart AI... is that literally everyone on Earth will die."

Does AI Pose an Existential Threat to Humanity?

Researchers at Stanford University developed an artificial intelligence model called SleepFM that can predict the risk of developing over 100 health conditions using sleep data. The model was trained on approximately 585,000 hours of sleep recordings from about 65,000 participants.

Researchers at Stanford University developed an artificial intelligence model called SleepFM that can predict the risk of developing over 100 health conditions using sleep data. The model was trained on approximately 585,000 hours of sleep recordings from about 65,000 participants.

The AI system was tested on sleep analysis tasks such as tracking sleep stages and diagnosing sleep apnea severity before being used to predict future disease onset. Polysomnography, considered the gold standard in sleep studies, uses sensors to record brain activity, heart function, respiratory signals and eye movements.

The AI system was tested on sleep analysis tasks such as tracking sleep stages and diagnosing sleep apnea severity before being used to predict future disease onset. Polysomnography, considered the gold standard in sleep studies, uses sensors to record brain activity, heart function, respiratory signals and eye movements.

SleepFM analyzed more than 1,000 disease categories from health records and identified 130 conditions that could be predicted with reasonable accuracy using sleep data. The model incorporates multiple data streams including electroencephalography, electrocardiography, electromyography, pulse readings and breathing airflow.

SleepFM analyzed more than 1,000 disease categories from health records and identified 130 conditions that could be predicted with reasonable accuracy using sleep data. The model incorporates multiple data streams including electroencephalography, electrocardiography, electromyography, pulse readings and breathing airflow.

The research team developed a training technique called leave-one-out contrastive learning, which hides one data stream and challenges the model to reconstruct the missing information based on other signals. This approach helps the AI learn relationships between different physiological measurements during sleep.

The research team developed a training technique called leave-one-out contrastive learning, which hides one data stream and challenges the model to reconstruct the missing information based on other signals. This approach helps the AI learn relationships between different physiological measurements during sleep.

The AI system's predictions were particularly strong for cancer, pregnancy complications, circulatory conditions and mental disorders, achieving a C-index score higher than 0.8. The C-index measures the model's ability to predict which of two individuals will experience a health event first.

The AI system's predictions were particularly strong for cancer, pregnancy complications, circulatory conditions and mental disorders, achieving a C-index score higher than 0.8. The C-index measures the model's ability to predict which of two individuals will experience a health event first.

SleepFM demonstrated high accuracy in predicting specific conditions including Parkinson's disease with a C-index of 0.89, dementia at 0.85, heart attack at 0.81, prostate cancer at 0.89 and overall mortality risk at 0.84. The model showed strong performance across diverse health categories.

SleepFM demonstrated high accuracy in predicting specific conditions including Parkinson's disease with a C-index of 0.89, dementia at 0.85, heart attack at 0.81, prostate cancer at 0.89 and overall mortality risk at 0.84. The model showed strong performance across diverse health categories.

Stanford AI Predicts 100+ Diseases From Sleep Data

Stanford’s AI Predicts Disease100+ RiskDiseases From aSleep Single Night of SleepData

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

Go Deeper

Articles on this story

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters