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{193089,
        author = {Kulkarni Shreyash and Gudhate Samarth and Inde Samarth and Jamma Atharva and Waghmare Pooja},
        title = {MedicareAI: A Neuro-Symbolic Framework for Secure Multi-Modal Remote Medical Triage},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {4060-4063},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193089},
        abstract = {The integration of Artificial Intelligence into healthcare faces significant barriers due to the "Black Box" problem and Large Language Model (LLM) hallucination tendencies. MedicareAI presents a diagnostic support ecosystem that addresses these challenges by combining Neuro-Symbolic AI with multi-modal deep learning. Unlike conventional chatbots, MedicareAI utilizes a LangGraph-based state machine that enforces clinical protocols through a deterministic pathway: Symptom Extraction, Differential Diagnosis, Risk Assessment, and Triage. The system integrates EfficientNet-B0 for X-ray analysis with Grad-CAM explainability mechanisms. An asynchronous "Write-Behind" architecture using Redis and Python worker queues manages longitudinal patient memory without latency. This paper details mathematical models for risk assessment, temporal memory decay, and computer vision pipelines, demonstrating a scalable approach to remote health management.},
        keywords = {Artificial Intelligence, Clinical Decision Support, Explainable AI, Large Language Models, Medical Triage, Neuro-Symbolic AI.},
        month = {February},
        }