• Devi Prabha S
• Akshaya Bala A
• Sathana C
• Ram Ganesh G H

Varicose veins affect nearly 20–30% of adults worldwide due to venous valve insufficiency, leading to blood pooling and circulation issues in the lower limbs. Conventional diagnostic methods such as Doppler ultrasound are costly and inaccessible in rural areas. This project, “Personalized Clinical Guidance for Varicose Vein Management,” presents a deep learning–based mobile application for automated CEAP stage (C0–C6) classification using smartphone-captured leg images. The system employs an ensemble of MobileNetV2 and EfficientNetB0 models with K-Means clustering for pseudo-label generation to overcome limited labelled data. The Node.js backend and React Native frontend enable real-time stage prediction, personalized remedial guidance, and specialist referrals, offering an affordable and accessible solution for early varicose vein detection and management.

Varicose veins, Deep learning, CEAP classification, MobileNetV2, EfficientNetB0, Ensemble learning, Clinical guidance, Telemedicine, Image classification

"Personalized Clinical Guidance For Varicose Vein Management", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 10, page no.e511-e518, October-2025, Available :http://www.jetir.org/papers/JETIR2510463.pdf

"Personalized Clinical Guidance For Varicose Vein Management", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 10, page no. ppe511-e518, October-2025, Available at : http://www.jetir.org/papers/JETIR2510463.pdf