A Multimodal, Explainable, and Bias-Aware AI System for Inclusive Skin Disease Risk Prediction

Author(s)	Snehal Patil, Meher Bhawnani
Country	India
Abstract	Skin manifestaions are common and frequently necessitate at least accurate diagnosis if not specifictreatment. Conventional methods of diagnosis may be subjective, time-consuming and inconsistent.In this paper, we present an AI-based system for skin disease classification that integrates dermoscopic image analysis, patient demographics, and medical history running on a Flask webserver. The model is a deep convolutional neural network (CNN) that has been trained on skindisease repositories to forecast states from the provided images. To increase interpretability, Grad- CAM heatmaps are provided to clin icians, indicating regions of interest, while brief and simpletextual summaries are given to patients as easily understandable e xplanations. This system gatherspatient information like name, age, gender, medical history and the predictions to formulate acomprehensive, multimodal diagnostic report. Results show that the solution enhances not onlydiagnostic accuracy but also trust, interpretability and inclusiveness in healthcare.
Keywords	Skin Disease Classification, Explainable AI, Grad-CAM, Patient History, Medical Imaging, Flask, Deep Learning, Interpretability, Healthcare AI.
Published In	Volume 7, Issue 3, May-June 2026
Published On	2026-05-28
DOI	https://doi.org/10.63363/aijfr.2026.v07i03.5769

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research