AIIMS, Google join hands to develop AI-powered dermatology app
What's the story
The All India Institute of Medical Sciences (AIIMS) is working with tech giant Google to create an artificial intelligence (AI)-based dermatology app. The project, dubbed Indus Derma, aims to make skincare more accessible and inclusive. It will use advanced image analysis technology to help patients and non-specialist healthcare providers identify and manage common skin conditions.
App features
Indus Derma: A tool for skin condition management
The Indus Derma app will let users upload a photo of their skin condition along with basic details like age, gender, duration of symptoms, and presence of itching or pain. Using advanced computer vision and large vision-language models, the AI analyzes the image against extensive databases of skin conditions to suggest a possible diagnosis. It will also recommend general skincare tips and whether a visit to a dermatologist is needed.
Addressing disparities
Indus Derma: A solution for underserved populations
Dr. Somesh Gupta, a professor of dermatology at AIIMS, highlighted that access to trained dermatologists is limited outside urban centers. He said most dermatologists in India are concentrated in cities and focus on cosmetic practice, leaving semi-urban and rural populations underserved. The app will empower general physicians or even non-physicians in these areas by helping them triage cases effectively with AI's assistance.
AI's role
Indus Derma: A decision support tool, not a replacement
The app will not generate legally valid prescriptions. Any medication suggestions provided by the AI will need to be verified and approved by a qualified medical professional. "This is a decision support tool, not a replacement for doctors," Dr. Gupta clarified. He also noted that dermatology is particularly well-suited for AI applications because it mainly relies on visual pattern recognition.
Data balance
Indus Derma: Addressing data imbalance in AI dermatology models
One of the major issues with existing global AI dermatology models is that they are trained mostly on images of white skin. This data imbalance affects diagnostic accuracy for Indian patients. To tackle this, AIIMS and Google are jointly developing Indian foundation models that will retrain global AI systems using Indian skin tones and dermatological conditions. "Skin color significantly influences visual diagnosis. That's why local data is essential," Dr. Gupta said.
Impact
Indus Derma: A significant shift in skin condition management
The AIIMS Google dermatology app could be a game changer in how skin conditions are diagnosed and treated in India. It would bring expert-level guidance closer to millions who currently lack access to specialist care. The team is aiming for an accuracy rate of 80-90%, which is much higher than the roughly 40% accuracy seen among non-specialists managing skin conditions. The app is expected to be launched sometime in 2026.