Explainable Generative AI for Real-Time HCC Risk Scoring from FHIR Streams
Keywords:
HCC Risk Prediction, Hepatocellular Carcinoma Analytics, Real-Time Clinical Scoring, Explainable AI in Healthcare, Generative Modeling Frameworks, Clinical Decision Support Systems, Medical Risk Stratification, Interpretable Deep Learning, Predictive Healthcare Models, ROC-Based Evaluation, Sensitivity and Specificity Analysis, Model Calibration Techniques, Trustworthy AI in Medicine, Patient Risk Assessment, Clinical Workflow Integration, AI-Driven Diagnostics, Healthcare Predictive Systems, Transparent AI Models, Data-Driven Clinical Decisions, Disease Risk Analytics.Abstract
Early detection and timely treatment of hepatocellular carcinoma (HCC) are critical to improving patient outcomes, yet existing risk-scoring models are poorly suited to clinical practice: their prediction horizons are too long, their input data are often unavailable at the point of care, and their outputs lack real-time interpretability. This study introduces a predictive model that computes HCC risk scores in real time, allowing seamless integration into routine clinical decision-making workflows. To address the interpretability limitations inherent to deep learning, we apply an Explainable Generative Modeling Framework — a novel combination of generative modeling and explainability techniques — to reveal the mechanisms underlying the model's predictions. Performance evaluation, based on area under the receiver operating characteristic curve, calibration, sensitivity, and specificity, confirms that the model is robust and suitable for clinical use. However, strong predictive performance alone is not sufficient: coupling the model with explainability analyses is essential for building clinician trust and ensuring adoption in practice. By aligning the model with natural clinical data flow and embedding transparency into its design and training, this work delivers an HCC risk-scoring tool that is both timely and trustworthy — supporting more effective, real-time patient management.
References
1. Albahri, A. S., Duhaim, A. M., Fadhel, M. A., Alnoor, A., Baqer, N. S., Alzubaidi, L., Albahri, O. S., Alamoodi, A. H., Bai, J., Salhi, A., Santamaría, J., Ouyang, C., Gupta, A., Gu, Y., & Deveci, M. (2023). A systematic review of trustworthy and explainable artificial intelligence in healthcare: Assessment of quality, bias risk, and data fusion. Information Fusion, 96, 156–191.
2. Ben Shoham, O., & Rappoport, N. (2024). CPLLM: Clinical prediction with large language models. PLOS Digital Health, 3(12), e0000680.
3. Bopche, R., Gustad, L. T., Afset, J. E., Ehrnström, B., Damås, J. K., & Nytrø, Ø. (2024). Leveraging explainable artificial intelligence for early prediction of bloodstream infections using historical electronic health records. PLOS Digital Health, 3(11), e0000506.
4. Mangalampalli, B. M. (2024). Transparent Intelligence Explainability Frameworks for AI-Driven Clinical Decision Support in Healthcare Business Intelligence. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 7(3), 10566-10579.
5. Chari, S., Acharya, P., Gruen, D. M., Zhang, O., Eyigoz, E. K., Ghalwash, M., Seneviratne, O., Suarez Saiz, F., Meyer, P., Chakraborty, P., & McGuinness, D. L. (2023). Informing clinical assessment by contextualizing post-hoc explanations of risk prediction models in type-2 diabetes. Artificial Intelligence in Medicine, 137, 102498.
6. Conte, J., & Avramovic, S. (2024). Clinical risk prediction using language models: Benefits and considerations. Journal of the American Medical Informatics Association, 31(9), 1856–1864.
7. Ding, S., Ye, J., Hu, X., & Zou, N. (2024). Distilling the knowledge from large-language model for health event prediction. Scientific Reports, 14, 30675.
8. Mattaparthi, R. (2024). Transformer-Based Fault Diagnosis for Large-Scale Standby Power Generators: Partial Discharge Pattern Recognition at Hyperscale Data Center Installations. Journal of Computational Analysis and Applications (JoCAAA), 33(08), 8781-8799.
9. Fang, H. S. A., Tan, N. C., Tan, W. Y., Oei, R. W., Lee, M. L., & Hsu, W. (2021). Patient similarity analytics for explainable clinical risk prediction. BMC Medical Informatics and Decision Making, 21, 207.
10. Gao, X. R., Chiariglione, M., Qin, K., et al. (2023). Explainable machine learning aggregates polygenic risk scores and electronic health records for Alzheimer’s disease prediction. Scientific Reports, 13, 450.
11. Markus, A. F., Kors, J. A., & Rijnbeek, P. R. (2021). The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies. Journal of Biomedical Informatics, 113, 103655.
12. Loganathan, R., & Kolla, S. H. (2024). Harnessing generative AI for adaptive risk policy generation in multi-regulatory data center environments. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 15(3), 505-515.
13. Mesinovic, M., Watkinson, P., & Zhu, T. (2023). Explainable AI for clinical risk prediction: A survey of concepts, methods, and modalities.
14. Niu, S., Yin, Q., Ma, J., Song, Y., Xu, Y., Bai, L., Pan, W., & Yang, X. (2024). Enhancing healthcare decision support through explainable AI models for risk prediction. Decision Support Systems, 181, Article 114228.
15. Pang, C., Jiang, X., Kalluri, K. S., Spotnitz, M., Chen, R., Perotte, A., & Natarajan, K. (2021). CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks. Proceedings of Machine Learning for Health, 158, 239–260.
16. Kolla, S. H., & Peddi, R. K. (2024). Designing Governance-Aligned GenAI Pipelines Using Small Language Models for Enterprise Workflow Intelligence. International Journal of Science, Research and Technology, 7(6), 13256-13268.
17. Park, S., & Basu, A. (2021). Improving risk adjustment with machine learning: Accounting for service-level propensity scores to reduce service-level selection. Health Services and Outcomes Research Methodology, 21, 1–26.
18. Peng, J., Zou, K., Zhou, M., Teng, Y., Zhu, X., Zhang, F., & Xu, J. (2021). An explainable artificial intelligence framework for the deterioration risk prediction of hepatitis patients. Journal of Medical Systems, 45, 61.
19. Rasmy, L., Xiang, Y., Xie, Z., Tao, C., & Zhi, D. (2021). Med-BERT: Pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. npj Digital Medicine, 4, 86.
20. Twick, I., Zahavi, G., Benvenisti, H., Rubinstein, R., Woods, M. S., Berkenstadt, H., Nissan, A., Hosgor, E., & Assaf, D. (2022). Towards interpretable, medically grounded, EMR-based risk prediction models. Scientific Reports, 12, 9990.
21. Kolla, S. K., & Mangalampalli, B. M. (2024). Edge-Based Deep Learning Systems for Point-of-Care Diagnostic Intelligence. Journal of Neonatal Surgery, 13(1), 2387-2399.
22. Wang, S., Han, J., Jung, S. Y., Oh, T. J., Yao, S., Lim, S., Hwang, H., Lee, H.-Y., et al. (2022). Development and implementation of patient-level prediction models of end-stage renal disease for type 2 diabetes patients using fast healthcare interoperability resources. Scientific Reports, 12, 11232.
23. Wesołowski, S., Lemmon, G., Hernandez, E. J., Henrie, A., Miller, T. A., Weyhrauch, D., Puchalski, M. D., Bray, B. E., Shah, R. U., & Deshmukh, V. G. (2022). An explainable artificial intelligence approach for predicting cardiovascular outcomes using electronic health records. PLOS Digital Health, 1(1), e0000004.
24. Yang, C. C. (2022). Explainable artificial intelligence for predictive modeling in healthcare. Journal of Healthcare Informatics Research, 6, 228–239.
25. Reddy, V. A. R. (2024). Generative Intelligence for Healthcare Claims Processing and Personalized Benefits Management. International Journal of Advanced Engineering Science and Information Technology (IJAESIT), 7(3), 14099.
26. Yang, X., PourNejatian, N., Shin, H. C., Smith, K. E., Parisien, C., Compas, C., Martin, C., Flores, M. G., Zhang, Y., Magoc, T., Harle, C. A., Lipori, G., Mitchell, D. A., Hogan, W. R., Shenkman, E. A., Bian, J., & Wu, Y. (2022). GatorTron: A large clinical language model to unlock patient information from unstructured electronic health records. npj Digital Medicine, 5, 92.
27. Wornow, M., Xu, Y., Thapa, R., Patel, B., Steinberg, E., Fleming, S., Pfeffer, M. A., Fries, J., & Shah, N. H. (2023). The shaky foundations of large language models and foundation models for electronic health records. npj Digital Medicine, 6, 135.
28. Oermann, E. K., et al. (2023). Health system-scale language models are all-purpose prediction engines. Nature, 619, 357–362.
29. Mahadevan, S. (2024). Clouding the Future: Innovating Towards Net-Zero Emissions. International Journal of Computing and Engineering, 6(2), 17-23.
30. Nori, H., King, N., McKinney, S. M., Carignan, D., & Horvitz, E. (2023). Capabilities of GPT-4 on medical challenge problems. arXiv.
31. Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A. K., Cole-Lewis, H., Pfohl, S. R., Payne, P., Seneviratne, M., Gamble, P., Kelly, C., Babiker, A., Schärli, N., Chowdhery, A., Mansfield, P., Demner-Fushman, D., … Natarajan, V. (2023). Large language models encode clinical knowledge. Nature, 620, 172–180.
32. Singhal, K., Tu, T., Gottweis, J., Sayres, R., Wulczyn, E., Hou, L., Clark, J., Azizi, S., Mahdavi, S. S., Agrawal, R., & others. (2023). Towards expert-level medical question answering with large language models. Nature Medicine, 29, 1870–1880.
33. Mangala, N. (2022). Real-Time Data Quality Monitoring and Gating Frameworks in Cloud-Based Data Pipelines. International Journal of Research and Applied Innovations, 5(6), 8197-8219.
34. Lee, P., Bubeck, S., & Petro, J. (2023). Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine. New England Journal of Medicine, 388, 1233–1239.
35. Thirunavukarasu, A. J., Ting, D. S. J., Elangovan, K., Gutierrez, L., Tan, T. F., & Ting, D. S. W. (2023). Large language models in medicine. Nature Medicine, 29, 1930–1940.
36. Moor, M., Banerjee, O., Abad, Z. S. H., Krumholz, H. M., Leskovec, J., Topol, E. J., & Rajpurkar, P. (2023). Foundation models for generalist medical artificial intelligence. Nature, 616, 259–265.
37. Wornow, M., Thapa, R., Steinberg, E., Fries, J., & Shah, N. H. (2023). EHRSHOT: An EHR benchmark for few-shot evaluation of foundation models. Proceedings of Machine Learning Research.
38. Bertsimas, D., Pauphilet, J., & others. (2022). From predictions to prescriptions: A data-driven approach to healthcare decision-making. Management Science.
39. Khera, R., et al. (2023). Artificial intelligence and machine learning in cardiovascular risk prediction and management. Circulation Research.
40. Rajkomar, A., Dean, J., & Kohane, I. (2022). Machine learning in medicine. New England Journal of Medicine, 386, 134–145.
41. Yandamuri, U. S. (2024). AI-Driven Decision Support Systems for Operational Optimization in Hospitality Technology. Metallurgical and Materials Engineering.
42. Sutton, R. T., Pincock, D., Baumgart, D. C., Sadowski, D. C., Fedorak, R. N., & Kroeker, K. I. (2021). An overview of clinical decision support systems: Benefits, risks, and strategies for success. npj Digital Medicine, 4, 1–9.
43. Nymberg, V. M., Bolmsjö, B. B., Wolters, E., et al. (2021). Having a good understanding of the clinical decision support system: A qualitative study of primary care clinicians’ experiences. BMC Medical Informatics and Decision Making, 21, 1–10.
44. Alami, H., Gagnon, M.-P., Fortin, J.-P., & others. (2024). Artificial intelligence and machine learning in healthcare: A systematic review of implementation challenges and opportunities. Journal of Medical Internet Research.
Additional Files
Published
Issue
Section
License
Copyright (c) 2025 Daniel Thompson (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
