Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199144,
        author = {Sahil Negi and Ritesh Tripathi and Harsh Goyal},
        title = {MediBot: An AI-Driven Smart Healthcare Portal Integrating NLP-Based Symptom Triage and Intelligent Physician Discovery},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {12646-12653},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199144},
        abstract = {Millions of patients across developing nations face persistent barriers in accessing qualified medical practitioners owing to infrastructure deficits and linguistic exclusion. This study introduces MediBot, a browser-native intelligent healthcare portal that unifies conversational Artificial Intelligence with structured clinical workflow management. The platform couples a generative Natural Language Processing engine—constructed on Google Gemini 2.5 Flash—with a locally-executable deter- ministic keyword-classification engine, yielding a dual-pathway triage architecture that delivers clinical guidance even when cloud connectivity is unavailable. Physician discovery relies on a weighted composite quality metric (Q = 1.0 · P% + 18 · Sstar +0.04 · min(Np, 3000) + 0.3 · Ey ) applied over a curated corpus of 5,000+ Indian healthcare providers, with a five-tier geospatially- aware fallback cascade. The system is realized as a nine-module single-page application in vanilla JavaScript ES6+, supporting bilingual voice interaction (English and Hindi) via the Web Speech API. Experimental evaluation confirms 100% test-suite passage, deterministic triage resolution under ten milliseconds, and a Pearson correlation of r = 0.91 between AI-generated urgency rankings and clinician panel assessments (p < 0.001), with a root mean square error of 4.1 points on a 100-point urgency scale.Millions of patients across developing nations face persistent barriers in accessing qualified medical practitioners owing to infrastructure deficits and linguistic exclusion. This study introduces MediBot, a browser-native intelligent healthcare portal that unifies conversational Artificial Intelligence with structured clinical workflow management. The platform couples a generative Natural Language Processing engine—constructed on Google Gemini 2.5 Flash—with a locally-executable deter- ministic keyword-classification engine, yielding a dual-pathway triage architecture that delivers clinical guidance even when cloud connectivity is unavailable. Physician discovery relies on a weighted composite quality metric (Q = 1.0 · P% + 18 · Sstar +0.04 · min(Np, 3000) + 0.3 · Ey ) applied over a curated corpus of 5,000+ Indian healthcare providers, with a five-tier geospatially- aware fallback cascade. The system is realized as a nine-module single-page application in vanilla JavaScript ES6+, supporting bilingual voice interaction (English and Hindi) via the Web Speech API. Experimental evaluation confirms 100% test-suite passage, deterministic triage resolution under ten milliseconds, and a Pearson correlation of r = 0.91 between AI-generated urgency rankings and clinician panel assessments (p < 0.001), with a root mean square error of 4.1 points on a 100-point urgency scale.},
        keywords = {healthcare portal, NLP symptom triage, large language model, dual-pathway architecture, physician recom- mendation, Flask, Gemini API},
        month = {April},
        }