A Real‐Time Mobile AI‐Assisted System for Skin Disease Prescreening: A Technical Feasibility Study
Utshob Sutradhar, Priyankar Biswas, Tapos Chandra Saha, Sumon Hossain, Mahmud Iftekhar Asef · 2026
Read A Real‐Time Mobile AI‐Assisted System for Skin Disease Prescreening: A Technical Feasibility Study by Utshob Sutradhar, Priyankar Biswas, Tapos Chandra Saha, Sumon Hossain, Mahmud Iftekhar Asef (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13243179.txt.
Description
Utshob Sutradhar and co-authors built a phone app that prescreens skin disease from photos in real time. Their feasibility study appeared in Health Science Reports in 2026. Skin disease is common where dermatologists are scarce, so a light on-device model could flag who needs care first. Their Android app, SkinLearn, runs a trimmed YOLO11 network directly on the phone with no internet needed, trained on a public seven-class set of skin images.
On its home dataset the model named the right disease almost every time. On a second, different skin cancer dataset its accuracy fell sharply, though it still beat the older model used for comparison. That drop exposes how much image sets differ in lighting, skin tones, and class mix. The authors claim technical feasibility for real-time, offline prescreening on cheap hardware. They insist on more validation before any clinical use.
Catalog record
| CREATOR | Utshob Sutradhar, Priyankar Biswas, Tapos Chandra Saha, Sumon Hossain, Mahmud Iftekhar Asef |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 26 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |