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{197191,
        author = {Dr. MK Jayanthi Kannan and Kasireddy Vara Lakshmi Priyanka},
        title = {TAPS-AD: A Transparent Multi-Agent Large Language Model Framework for Personalized Alzheimer's Disease Prognosis and Evidence-Based Intervention},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {5461-5472},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197191},
        abstract = {Alzheimer's Disease (AD) diagnosis models predominantly focus on binary risk classification, lacking the ability to predict the rate of cognitive decline and provide interpretable clinical decisions. We propose TAPS-AD (Transparent Multi-Agent Prognostic and Intervention System for AD), a novel multi-agent framework leveraging specialized Large Language Model (LLM) agents that analyze heterogeneous patient data: longitudinal electronic health record (EHR) clinical notes, structured biomarker data, and connected speech features. Coordinated by a central Orchestrator, TAPS-AD produces individualized quantitative predictions of the annual Mini-Mental State Examination (MMSE) decline rate, alongside personalized, evidence-based lifestyle and clinical trial interventions. Crucially, the system integrates a transparency pipeline where each agent presents its top influential features with confidence scores, enabling conflict resolution and generating an auditable, explanatory rationale that enhances trust and clinical utility. TAPS-AD advances AD care through dynamic prognosis and actionable insights, bridging the gap between state-of-the-art artificial intelligence and practical clinical decision-making.},
        keywords = {},
        month = {April},
        }