A machine-learning algorithm can accurately screen for hypertension and diabetes using brief facial video recordings, offering a contactless diagnostic option.
Key Details
- 1Researchers from the University of Tokyo developed an AI algorithm to analyze facial and palm video recordings for undiagnosed hypertension and diabetes.
- 2In a prospective study of 215 participants, the algorithm detected hypertension with over 90% accuracy from a 5-second facial video and up to 95% with longer recordings.
- 3Diabetes was identified with 81.2% accuracy from 5-second videos and 88.2% accuracy from 30-second videos.
- 4The AI could estimate systolic blood pressure, achieving a mean error within the AAMI clinical criterion for bias but with higher-than-acceptable standard deviation.
- 5This contactless technology may allow mass public screening without traditional cuffs or blood sampling, pending further validation in larger, more diverse populations.
Why It Matters
This research demonstrates the expanding capabilities of imaging AI in non-traditional modalities (facial video) for scalable, contactless medical screening. If validated, it could significantly increase early detection and intervention for hypertension and diabetes, impacting public health and preventive care strategies.
Source
EurekAlert
Related News
•EurekAlert
AI Highlights Importance of Thymus Protection During Lung Cancer Radiotherapy
AI analysis reveals that radiation exposure to the thymus during lung cancer treatment may worsen patient outcomes.
•EurekAlert
Deep Learning Enables Single-Shot High-Resolution Lensless Dynamic Imaging
Researchers from NJU and PKU have developed a lensless imaging method using deep learning that reconstructs high-fidelity dynamic images from single shots.
•EurekAlert
Weill Cornell Launches AI and Data Science Biomedicine Department Led by Dr. Dan Landau
Weill Cornell Medicine establishes a new Department of Systems and Computational Biomedicine, appointing Dr. Dan Landau as its first chair to drive AI-powered biomedical innovation.