Home / Current Issue / Paper 1717943
An Intelligent AI-Driven Primary Healthcare Triage Chatbot with Explainable Risk Classification
Subject area: Science,Engineering and Technology · Area of research: AI Healthcare
DOI: https://doi.org/10.64388/IREV9I11-1717943
Abstract
The increasing demand for accessible and efficient primary healthcare services highlights the need for intelligent systems capable of early-stage patient triage. Traditional healthcare systems often face challenges such as overcrowding, delayed diagnosis, and limited accessibility, particularly in resource-constrained environments. Existing studies have applied artificial intelligence and machine learning techniques, including Random Forest, Support Vector Machines, and deep learning models, for disease prediction and clinical decision support, along with basic chatbot systems for symptom collection. However, these approaches lack explainability, real-time interaction, and structured risk classification, reducing their reliability and user trust. To address these limitations, this research proposes an intelligent AI-driven primary healthcare triage chatbot that integrates explainable AI with risk-based classification. The system analyses patient symptoms to categorize cases into low, medium, and high-risk levels while providing transparent reasoning, thereby improving accessibility, enhancing trust, and supporting efficient decision-making in primary healthcare systems.
Keywords
Artificial Intelligence, Healthcare Triage, Explainable AI (XAI), Chatbot Systems, Risk Classification, Machine Learning, Clinical Decision Support
How to cite this paper
@article{1717943,
author = {Bharat M M, Dr Haripriya V},
title = {An Intelligent AI-Driven Primary Healthcare Triage Chatbot with Explainable Risk Classification},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {2600-2608},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717943.pdf},
abstract = {The increasing demand for accessible and efficient primary healthcare services highlights the need for intelligent systems capable of early-stage patient triage. Traditional healthcare systems often face challenges such as overcrowding, delayed diagnosis, and limited accessibility, particularly in resource-constrained environments. Existing studies have applied artificial intelligence and machine learning techniques, including Random Forest, Support Vector Machines, and deep learning models, for disease prediction and clinical decision support, along with basic chatbot systems for symptom collection. However, these approaches lack explainability, real-time interaction, and structured risk classification, reducing their reliability and user trust. To address these limitations, this research proposes an intelligent AI-driven primary healthcare triage chatbot that integrates explainable AI with risk-based classification. The system analyses patient symptoms to categorize cases into low, medium, and high-risk levels while providing transparent reasoning, thereby improving accessibility, enhancing trust, and supporting efficient decision-making in primary healthcare systems.},
keywords = {Artificial Intelligence, Healthcare Triage, Explainable AI (XAI), Chatbot Systems, Risk Classification, Machine Learning, Clinical Decision Support},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717943}
}