An Intelligent Clinical Decision Support Framework for Heart Disease Risk Prediction

Authors

  • Neha Gupta

    School of Computer Science and Engineering, Geeta University, Panipat 132103, India
  • Bhawna Singla

    School of Computer Science and Engineering, Geeta University, Panipat 132103, India

DOI:

https://doi.org/10.30564/jeis.v8i2.13217
Received: 27 February 2026 | Revised: 1 June 2026 | Accepted: 8 June 2026 | Published Online: 13 July 2026

Abstract

Cardiovascular diseases (CVDs) are among the leading causes of mortality worldwide. Early detection and risk stratification are critical for preventive care. Traditional machine learning (ML) models can predict heart disease risk but often lack interpretability and fail to integrate with real-time clinical data. Recent advances in fine-tuned large language models (Custom GPT) offer natural language explanations but are limited by insufficient interoperability with heterogeneous healthcare data sources. This study aims to design and evaluate a Model Context Protocol (MCP)–enabled Custom GPT framework that integrates ML-based predictive models with external healthcare systems—including EHRs, laboratory APIs, and wearable devices—to deliver context-aware, explainable, and clinically actionable heart disease risk predictions. The experimental evaluation was conducted on a validated cardiovascular dataset containing 303 patient records and 14 clinically relevant attributes derived from publicly available clinical repositories. Experimental evaluation demonstrated improved predictive accuracy (approximately 88% with the XGBoost ensemble) and robustness compared to standalone  models. MCP integration enabled dynamic contextual awareness, reduced latency in tool orchestration, and enriched interpretability through RAG-based explanations. Clinician and patient evaluations confirmed enhanced usability and transparency. This approach paves the way for broader adoption of agentic AI in clinical workflows.

Keywords:

Model Context Protocol; Custom GPT; Heart Disease Prediction; Explainable Artificial Intelligence; Clinical Decision Support; Ensemble Learning; Retrieval-Augmented Generation

References

[1] Wadhera, R.K., Dhruva, S.S., Bikdeli, B., et al., 2026. Cardiovascular Statistics in the United States, 2026. Journal of the American College of Cardiology. 87(9), 1094–1134. DOI: https://doi.org/10.1016/j.jacc.2025.12.027

[2] Napa, K.K., Govindarajan, R., Sathya, S., et al., 2025. Comparative analysis of explainable machine learning models for cardiovascular risk stratification using clinical data and shapley additive explanations. Intelligence-Based Medicine. 12, 100286. DOI: https://doi.org/10.1016/j.ibmed.2025.100286

[3] De Menezes-Júnior, L.A.A., De Moura, S.S., Carraro, J.C.C., et al., 2025. Framingham score adapted: a valid alternative for estimating cardiovascular risk in epidemiological studies. BMC Cardiovascular Disorders. 25(1), 187. DOI: https://doi.org/10.1186/s12872-025-04579-x

[4] Breiman, L., 2001. Random Forests. Machine Learning. 45(1), 5–32. DOI: https://doi.org/10.1023/A:1010933404324

[5] Yıldız, A.Y., Kalayci, A., 2025. Gradient Boosting Decision Trees on Medical Diagnosis Over Tabular Data. In Proceedings of the 2025 IEEE International Conference on AI and Data Analytics (ICAD), Medford, MA, USA, 24 June 2025; pp. 1–8. DOI: https://doi.org/10.1109/ICAD65464.2025.11114069

[6] Lundberg, S., Lee, S.-I., 2017.AUnifiedApproach to Interpreting Model Predictions. arXiv preprint. arXiv:1705.07874. DOI: https://doi.org/10.48550/ARXIV.1705.07874

[7] Mineeva, O., Li, C., Giulianini, F., et al., 2025. Development and Validation of Novel Residual Risk Scores for Patients With ASCVD. JACC: Advances. 4(11), 102162. DOI: https://doi.org/10.1016/j.jacadv.2025.102162

[8] Xie, Q., Chen, Q., Chen, A., et al., 2025. Medical foundation large language models for comprehensive text analysis and beyond. Npj Digital Medicine. 8(1), 141. DOI: https://doi.org/10.1038/s41746-025-01533-1

[9] Xu, G., Li, X., Chen, Y., et al., 2026. A comprehensive survey of AI agents in healthcare. Journal of Biomedical Informatics. 179, 105045. DOI: https://doi.org/10.1016/j.jbi.2026.105045

[10] Kalasampath, K., Spoorthi, K.N., Sajeev, S., et al., 2025. A Literature Review on Applications of Explainable Artificial Intelligence (XAI). IEEE Access. 13, 41111–41140. DOI: https://doi.org/10.1109/ACCESS.2025.3546681

[11] Mumuni, F., Mumuni, A., 2025. Explainable artificial intelligence (XAI): from inherent explainability to large language models. arXiv preprint. arXiv:2501.09967. DOI: https://doi.org/10.48550/ARXIV.2501.09967

[12] Noviandy, T.R., Idroes, G.M., Hardi, I., 2025. Integrating explainable artificial intelligence and light gradient boosting machine for glioma grading. Informatics and Health. 2(1), 1–8. DOI: https://doi.org/10.1016/j.infoh.2024.12.001

[13] Güçkiran, S., Büyükköse, Ş., 2026. A Survey of Local Interpretable Model-Agnostic Explanations (LIME) and its Variants: Mathematical Foundations, Extensions and Comparative Analysis. SSRN. Under review.

[14] M, Y., Vamja, R., Vala, V., et al., 2025. Community-based evaluation of cardiovascular risk using QRISK®3 in type 2 diabetes mellitus population in Gujarat, India. BMC Public Health. 25(1), 3384. DOI: https://doi.org/10.1186/s12889-025-24783-w

[15] Li, Y., Zhang, W., Yang, Y., et al., 2025. Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs. arXiv preprint. arXiv:2507.09477. DOI: https://doi.org/10.48550/ARXIV.2507.09477

[16] Matarazzo, A., Torlone, R., 2025. A Survey on Large Language Models with some Insights on their Capabilities and Limitations. arXiv print. arXiv:2501.04040. DOI: https://doi.org/10.48550/ARXIV.2501.04040

[17] Narayanan, P., Ganesh, S., Periasamy, K., et al., 2026. Multi-modal medical image diagnosis through LIME with explainable AI. AIP Conference Proceedings. 3345, 020272. DOI: https://doi.org/10.1063/5.0298329

[18] Touvron, H., Lavril, T., Izacard, G., et al., 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv preprint. arXiv:2302.13971. DOI: https://doi.org/10.48550/ARXIV.2302.13971

[19] Said, A., 2025. On explaining recommendations with Large Language Models: a review. Frontiers in Big Data. 7, 1505284. DOI: https://doi.org/10.3389/fdata.2024.1505284

[20] Singh, A., Ehtesham, A., Kumar, S., et al., 2025. A Survey of the Model Context Protocol (MCP): Standardizing Context to Enhance Large Language Models (LLMs). Preprints. DOI: https://doi.org/10.20944/preprints202504.0245.v1

[21] Guo, H., Hao, Y., Zhang, Y., et al., 2025. A Measurement Study of Model Context Protocol Ecosystem. arXiv preprint. arXiv:2509.25292. DOI: https://doi.org/10.48550/ARXIV.2509.25292

[22] Mandulapalli, S., Hernandez, E., Hall, W.J., et al., 2026. Development of Agentic Workflows with LangGraph for Software Development Life Cycle Automation. In: Florez, H., Rabelo, L., Diaz, C. (eds.). Industrial Engineering and Operations Management. Springer Nature: Cham, Switzerland. pp. 45–54. DOI: https://doi.org/10.1007/978-3-031-98235-4_4

[23] Saraswat, D., Bhattacharya, P., Verma, A., et al., 2022. Explainable AI for Healthcare 5.0: Opportunities and Challenges. IEEE Access. 10, 84486–84517. DOI: https://doi.org/10.1109/ACCESS.2022.3197671

[24] Pelluru, K., 2025. LangChain & LangGraph in Production: Architectures for Multi-Agent LLM Systems. Journal of Data and Digital Innovation (JDDI). 2(3), 1–9.

[25] Roman, A., Roman, J., 2026. Orchestral AI: A Framework for Agent Orchestration. arXiv preprint. arXiv:2601.02577. DOI: https://doi.org/10.48550/ARXIV.2601.02577

[26] Malakouti, S.M., 2025. Leveraging SHapley Additive exPlanations (SHAP) and fuzzy logic for efficient rainfall forecasts. Scientific Reports. 15(1), 36499. DOI: https://doi.org/10.1038/s41598-025-22081-4

[27] Sapkota, R., Shrestha, R., Rijal, M., et al., 2025. LangChain vs. LangGraph vs. LangSmith: Taxonomies of Agentic AI Toolchains for End-to-End Orchestration. TechRxiv preprint. DOI: https://doi.org/10.36227/techrxiv.175695645.52670060/v1

[28] Alam, S.M.K., Li, P., Rahman, M., et al., 2025. Key factors affecting groundwater nitrate levels in the Yinchuan Region, Northwest China: Research using the eXtreme Gradient Boosting (XGBoost) model with the SHapley Additive exPlanations (SHAP) method. Environmental Pollution. 364, 125336. DOI: https://doi.org/10.1016/j.envpol.2024.125336

[29] Pavithra, K., Ramkumar, M., 2026. Feature importance analysis approach using SHAP and LIME for enhancing interpretability and accuracy in income prediction models. AIP Conference Proceedings. 3345, 020363. DOI: https://doi.org/10.1063/5.0298409

[30] Singh, A., Ehtesham, A., Kumar, S., et al., 2025. Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG. arXiv preprint. arXiv:2501.09136. DOI: https://doi.org/10.48550/ARXIV.2501.09136

[31] Ray, P.P., 2025. A Survey on Model Context Protocol: Architecture, State-of-the-art, Challenges and Future Directions. TechRxiv preprint. DOI: https://doi.org/10.36227/techrxiv.174495492.22752319/v1

[32] Hou, X., Zhao, Y., Wang, S., et al., 2025. Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions. arXiv preprint. arXiv:2503.23278. DOI: https://doi.org/10.48550/ARXIV.2503.23278

Downloads

How to Cite

Gupta, N., & Singla, B. (2026). An Intelligent Clinical Decision Support Framework for Heart Disease Risk Prediction. Journal of Electronic & Information Systems, 8(2), 14–42. https://doi.org/10.30564/jeis.v8i2.13217

Issue

Vol. 8 , Iss. 2 (October 2026)

Article Type

ARTICLE

License

Copyright © 2026 Neha Gupta, Bhawna Singla

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.

Crossref
Scopus
Google Scholar
Europe PMC