ARCHITECTURAL PATTERNS FOR AI-ENABLED TRIAGE AND CRISIS PREDICTION SYSTEMS IN PUBLIC HEALTH PLATFORMS
DOI:
https://doi.org/10.15662/IJRAI.2025.0801003Keywords:
AI-Enabled Triage, Crisis Prediction, Public Health Architecture, Federated Learning, Real-Time Analytics, Micro Services in HealthcareAbstract
Utilizing hybrid architecture of microservices, event-driven messaging, and adaptive federated learning mechanisms, the system enables privacy-preserving AI training across distributed healthcare sites—including integration with the CVS Smart App for patient engagement, personalized health management, and access to unified CVS Pharmacy, Caremark, and Aetna services. The architecture was evaluated with simulated and real-world public health datasets (such as COVID-19 and influenza), deploying Random Forest, LSTM, and BERT-based NLP modules to predict symptom severity and crisis escalation. Test results demonstrated a triage accuracy rate of 92.6%, with crisis event prediction recall improving by approximately 24% compared to traditional rule-based methods. System scalability was validated, showing capacity to handle up to two-thirds greater loads and, through asynchronous containerized processing, a 38% reduction in latency relative to synchronous microservices. These findings highlight the effectiveness of such architectural patterns—particularly when paired with user-centric platforms like the CVS Smart App—in enabling proactive, AI driven public health interventions, even in resource-constrained environments.
References
1. L. Mondrejevski, I. Miliou, A. Montanino, D. Pitts, J. Hollmén, and P. Papapetrou, "FLICU: A Federated Learning Workflow for Intensive Care Unit Mortality Prediction," arXiv, May 2022.
2. K. Randl, N. Lladós Armengol, L. Mondrejevski, and I. Miliou, "Early prediction of the risk of ICU mortality with Deep Federated Learning," arXiv, Dec. 2022.
3. Mehrjou, A. Soleymani, A. Buchholz, J. Hetzel, P. Schwab, and S. Bauer, "Federated Learning in Multi-Center Critical Care Research: A Systematic Case Study using the eICU Database," arXiv, Apr. 2022.
4. Y. Park et al., "Federated learning model for predicting major postoperative complications," arXiv, Apr. 2024.
5. W. Pan, Z. Xu, S. Rajendran, and F. Wang, "An adaptive federated learning framework for clinical risk prediction with electronic health records from multiple hospitals," Patterns, vol. 5, no. 1, Jan. 2024
6. J. Wu et al., "Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records," Journal of Biomedical Informatics, 2019.
7. S. R. Abbas, Z. Abbas, A. Zahir, and S. W. Lee, "Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with Integration," 10.3390/healthcare12242587.
8. Y. Cheng, Y. Hu, W. Liu, and M. Bilal, “Federated Learning with Adaptive Local Aggregation for Privacy-Aware Recommender Systems in Internet of Vehicles,” Information Sciences, pp. https://doi.org/10.1016/j.ins.2025.122100.
9. H. Liang, Y. Tong, W. Ren et al., "Architectural Design of a Blockchain Enabled, Federated Learning Platform for Algorithmic Fairness in Predictive Health Care," Journal of Medical Internet Research, Oct. 2023.
10. W. Zhang et al., "Dynamic fusion based Federated Learning for COVID-19 Detection," arXiv, Sep. 2020.
11. S. Thwal et al., "Attention on Personalized CDSS: Federated Learning Approach," arXiv, Jan. 2024.
12. Dayan et al., "Federated learning for predicting clinical outcomes in patients with COVID 19," Nature Medicine, vol. 27, 2021.
13. Karargyris, R. Umeton, M. J. Sheller et al., "Federated benchmarking of medical artificial intelligence with MedPerf," Nature Machine Intelligence, vol. 5, pp. 799–810, 2023. doi: 10.1038/s42256-023-00652-2.
14. P. Sethi et al., "From challenges and pitfalls to recommendations in Federated Learning in healthcare," PubMed, 2025.
15. X. Xie et al., "Federated machine learning in healthcare: A systematic review on clinical applications and technical architecture," Cell Reports Medicine, vol. 5, no. 2, Feb. 2024.
