Authors:
S. Parthasarathy,B. Muthu Deepika,M. Elayarani,DOI NO:
https://doi.org/10.26782/jmcms.2026.09.00011Keywords:
Patient-flow network,Hospital admission prediction,Conformal prediction,calibration,Queueing models,Clinical decision support.,Abstract
An emergency department (ED) is a network: patient streams are sorted by acuity, queued, and routed through a finite pool of physicians and beds toward admission or discharge. We study admission-risk screening on 558,029 adult ED visits from the Yale-New Haven Health System, using the information present at the triage node: the Emergency Severity Index (ESI) and six triage vital signs, with age and sex retained for stratified validity checks. A gradient-boosted classifier ranks admission with AUC = 0.809, accuracy = 0.760, and Brier score = 0.157 on a held-out set of 111,607 visits. The methodological contribution is a Mondrian (per-acuity) split-conformal layer with a finite-sample, class-conditional coverage guarantee (Theorem 1) and a matching upper bound. Empirical coverage is 0.910 against a nominal 0.90, with mean prediction-set size 1.43. Residual audits show that ESI-level coverage can conceal within-class gaps, most clearly for abnormal vital signs inside ESI-4 (coverage 0.549 versus 0.943 when vitals are not abnormal). A joint Mondrian on ESI x age restores those cells to the nominal band whenever the calibration count meets n_c >= 99, the size that keeps the additive slack 1/(n_c+1) at most 0.01 (Proposition 1). We map each prediction set to an explicit routing action and a three-term decision loss (false preparation, delayed request, unresolved hedge). At a five-to-one delay-to-false-prep cost ratio, the conformal policy has mean cost 0.544, against 0.899 for a hard 0.50 threshold. Theorem 4 places the predictor in the queueing dynamics: committed false bed requests occur at a rate at most alpha, and MaxWeight stability is preserved when the oracle bed load plus that extra load stays below one. Scheduling and surge rules (Theorems 2 and 3) remain framework theory pending timestamped data. Every number is computed from real records.Refference:
I. Angelopoulos, A. N., Bates, S., Conformal prediction: A gentle introduction, Foundations and Trends in Machine Learning, 16(4) (2023) 494–591.
II. Armony, M., Israelit, S., Mandelbaum, A., Marmor, Y. N., Tseytlin, Y., Yom-Tov, G. B., On patient flow in hospitals: A data-based queueing-science perspective, Stochastic Systems, 5(1) (2015) 146–194.
III. Chocron, E., Cohen, I., Feigin, P., Delay prediction for managing multiclass service systems, IEEE Transactions on Engineering Management, 69(5) (2022) 2461–2471.
IV. Dai, J. G., Gluzman, M., Queueing network controls via deep reinforcement learning, Stochastic Systems, 12(1) (2022) 30–67.
V. Harchol-Balter, M., Performance Modeling and Design of Computer Systems: Queueing Theory in Action, Cambridge University Press, (2013).
VI. Hassoon, B. A., Xiong, S., Hasson, M. A., Abduljabbar, Z. A., A hybrid single-lead dataset for enhanced cardiovascular disease diagnosis, Network Modeling Analysis in Health Informatics and Bioinformatics, 14 (2025).
VII. Hong, W. S., Haimovich, A. D., Taylor, R. A., Predicting hospital admission at emergency department triage using machine learning, PLoS ONE, 13(7) (2018) e0201016.
VIII. Huang, J., Golubchik, L., Huang, L., Queue scheduling with adversarial bandit learning, IEEE/ACM Transactions on Networking (2024).
IX. Kadum, S. Y., et al., Machine learning-based telemedicine framework to prioritize remote patients with multi-chronic diseases for emergency healthcare services, Network Modeling Analysis in Health Informatics and Bioinformatics, 12 (2023).
X. Kaur, J., Kaur, H., Kaur, M., Sohal, R. S., Predicting autism spectrum disorder using intelligent framework, Network Modeling Analysis in Health Informatics and Bioinformatics, 14 (2025).
XI. Liu, B., Xie, Q., Modiano, E., RL-QN: A reinforcement learning framework for optimal control of queueing systems, ACM Transactions on Modeling and Performance Evaluation of Computing Systems, 7(1) (2022) 1–35.
XII. Mohajerin Esfahani, P., Kuhn, D., Data-driven distributionally robust optimization using the Wasserstein metric: Performance guarantees and tractable reformulations, Mathematical Programming, 171(1–2) (2018) 115–166.
XIII. Mythatha, E., Jenicka, S., A survey on mathematics behind AI models for disease prediction and diagnosis in healthcare, Network Modeling Analysis in Health Informatics and Bioinformatics, 14 (2025).
XIV. Pavse, B. S., Zurek, M., Chen, Y., Xie, Q., Hanna, J. P., Learning to stabilize online reinforcement learning in unbounded state spaces, Proceedings of the 41st International Conference on Machine Learning, 235 (2024) 40015–40033.
XV. Qureshi, A. M., Kaushik, A., Loughran, R., McDaid, K., McCaffery, F., Improving medical data quality via synthetic data generation: A review, Network Modeling Analysis in Health Informatics and Bioinformatics, 15 (2026) Article 46.
XVI. Rahman, M. A., Lim, D. Z., Davoren, M., Lok, I., Rahman, S., Hough, P., Mosa, T., Begum, S., Mapping the patient journey: Utilizing clinical informatics for a conceptual approach to identify aspects of emergency department access block, Network Modeling Analysis in Health Informatics and Bioinformatics, 13 (2024) Article 54.
XVII. Saghafian, S., Austin, G., Traub, S. J., Operations research/management contributions to emergency department patient flow optimization: Review and research prospects, IISE Transactions on Healthcare Systems Engineering, 5(2) (2015) 101–123.
XVIII. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O., Proximal policy optimization algorithms, arXiv preprint arXiv:1707.06347, (2017).
XIX. Sherzer, E., Baron, O., Krass, D., Resheff, Y., Approximating G(t)/GI/1 queues with deep learning, European Journal of Operational Research, 322(3) (2025) 889–907.
XX. Sundararajan, P., Dharmaraj, S., Gadiraju, P., An ensemble learning framework for brain tumour classification with explainable AI for medical diagnosis, Network Modeling Analysis in Health Informatics and Bioinformatics, 14 (2025).
XXI. Tassiulas, L., Ephremides, A., Stability properties of constrained queueing systems and scheduling policies for maximum throughput in multihop radio networks, IEEE Transactions on Automatic Control, 37(12) (1992) 1936–1948.
XXII. Vovk, V., Gammerman, A., Shafer, G., Algorithmic Learning in a Random World, 2nd ed., Springer, (2022).
XXIII. Walton, N., Xu, K., Learning and information in stochastic networks and queues, INFORMS TutORials in Operations Research, (2021) 161–198.
XXIV. Whitt, W., Stochastic-Process Limits, Springer, New York, (2002).
XXV. Whitt, W., Zhang, X., A data-driven model of an emergency department, Operations Research for Health Care, 12 (2017) 1–15.
XXVI. Zhou, G., Tian, W., Buyya, R., Xue, R., Song, J., Deep reinforcement learning-based methods for resource scheduling in cloud computing: A review and future directions, Artificial Intelligence Review, 57 (2024) Article 124.