Can AI screen for heart disease using photos of your tongue and face?
MedicinePublic HealthBiomedical Engineering
THE AI ANGLE
Classifying coronary heart disease from facial and tongue imagesResearchers trained a deep-learning model to identify coronary heart disease from photographs of the face and tongue. The tool reached 98 percent accuracy in a controlled test group of 104 people. The technique could provide a low-cost way to prioritize patients for diagnostic testing in areas with limited medical resources.
THE TEACHING ANGLE
A model evaluated only on healthy volunteers and confirmed patients risks high false-positive rates and confounding from age or lifestyle when applied to general populations.Read the original at theconversation.com Generate teaching or study materials
More in Medicine
- Artificial skin helps robots grasp pencil lead and pull away from needlesPhys.org — Technology · October 27, 2026
- A Market, Not a Mandate, Is the Fastest Way to Bring AI Into HospitalsMedCity News · October 27, 2026
- AI's preference for drugs with a strong online presence may cost millionsMedical Xpress · October 27, 2026
- AI-based computer model offers new weapon against hard-to-treat cancersMedical Xpress · October 26, 2026
- Study outlines comprehensive roadmap for AI in mental health careMedical Xpress · October 26, 2026