Get Plus

Sign in to baba News

One account across the web, iPhone and Android — your subscription follows it.

or use an email code

Search stories

Type at least two characters. Results come from every newsroom baba reads.

↑↓ to move · ↵ to open · esc to close

Sign in to baba News

Sign in to keep asking. News Plus removes the daily limit.

or use an email code

CursorinfoTech

AI Detects Liver Health, Sleep Issues Through Body Movement Analysis

Translated & summarized from Cursorinfo by baba

CommunityNeutral tone

Russian · 1 newsroom

Scientists at the Weizmann Institute of Science have trained an AI to analyze body movements, revealing connections to liver health, sleep quality, and diabetes risk. The AI processed movement data from 3,228 adults, finding correlations that surpassed traditional metrics like walking speed. The system can predict liver stiffness and sleep apnea indicators, and improve diagnoses when combined with other health data. Researchers aim to use this method for early disease detection, though further validation is required.

The story in 5 lines · by baba

  • AI analyzes body movements to assess liver health, sleep quality, and diabetes risk in 3,228 adults.
  • Weizmann Institute researchers found AI predictions surpassed traditional health metrics like walking speed.
  • The AI can predict liver stiffness and sleep apnea indicators based on body motion.
  • Integrating movement analysis improved diagnostic accuracy for diabetes, depression, and insomnia.
  • Researchers aim to use movement analysis for early disease detection, pending further validation.

Researchers at the Weizmann Institute of Science have developed an artificial intelligence system capable of analyzing body movements to assess liver health, sleep quality, and the risk of diabetes. The AI was trained to monitor subtle body motions, identifying correlations with various health indicators that traditional measurements like walking speed might miss. The study, which involved 3,228 adults, analyzed recordings of participants performing tasks such as walking, standing, and rising from a chair, with a depth-sensing camera tracking 26 joints in three dimensions.

The AI model learned to predict body part coordination by reconstructing hidden parts of the movement data. These movement patterns were then converted into numerical data and compared with participants' health records, including blood tests, body composition, diagnoses, and lifestyle factors. The AI found statistically significant links between body movements and 1,887 out of 3,210 health characteristics studied, providing more insight than conventional metrics like walking speed and stride length.

Specifically, the AI could predict liver stiffness, a measure of liver scarring, with accuracy comparable to blood tests for liver fat. Movements of the torso were found to be particularly indicative of sleep quality, including predicting parameters related to sleep apnea, insomnia, and sleep duration. When integrated into a model that already accounted for age, BMI, visceral fat, and height, the AI's predictions for diabetes, depression, insomnia, and medication use became more accurate.

While the researchers hope this movement analysis could supplement routine medical check-ups by flagging potential issues for further investigation, they acknowledge limitations. The study design was cross-sectional, meaning it cannot establish causality or track changes over time. Furthermore, the findings may not be generalizable to other populations, as the participants were primarily healthy Ashkenazi Jews living in Israel. The researchers also noted the involvement of Newton Tech, a company that produces the specialized cameras used. Adam Gabet emphasized the need for independent clinical trials to validate the system's diagnostic capabilities before medical application.

The team plans to investigate whether subtle changes in movement patterns can precede the onset of disease, potentially enabling earlier health issue detection. This research builds on the understanding that while leg movements are commonly assessed, upper body and overall body motion offer significant, under-explored health insights.

CursorinfoOther · Tel Aviv

Sign in to baba News

Sign in to follow newsrooms, topics and people.

or use an email code

TechTopic

Sign in to baba News

Sign in to follow newsrooms, topics and people.

or use an email code

Mentioned

Open the Wire