# Optimal discharge of patients from intensive care via a data-driven policy learning framework

arXiv: https://arxiv.org/abs/2112.09315 · HTML: https://mlsanity.com/paper/2112.09315/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 72 references that are in the map.
- First posted on arXiv 17 Dec 2021.

## Builds on (most cited first, 4 of 4)

- [Reinforcement Learning in Healthcare: A Survey](https://mlsanity.com/paper/1908.08796/) (2019)
- [Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1705.08422/) (2017)
- [Enabling risk-aware Reinforcement Learning for medical interventions through uncertainty decomposition](https://mlsanity.com/paper/2109.07827/) (2021)
- [An Adversarial Domain Separation Framework for Septic Shock Early Prediction Across EHR Systems](https://mlsanity.com/paper/2010.13952/) (2020)

## Built on by (most cited first, 3 of 3)

- [Accuracy, Memory Efficiency and Generalization: A Comparative Study on Liquid Neural Networks and Recurrent Neural Networks](https://mlsanity.com/paper/2510.07578/) (2025)
- [Evaluation of Popular XAI Applied to Clinical Prediction Models: Can They be Trusted?](https://mlsanity.com/paper/2306.11985/) (2023)
- [A Causal Framework for Evaluating ICU Discharge Strategies](https://mlsanity.com/paper/2603.25397/) (2026)

## Abstract (arXiv)

Clinical decision support tools rooted in machine learning and optimization can provide significant value to healthcare providers, including through better management of intensive care units. In particular, it is important that the patient discharge task addresses the nuanced trade-off between decreasing a patient's length of stay (and associated hospitalization costs) and the risk of readmission or even death following the discharge decision. This work introduces an end-to-end general framework for capturing this trade-off to recommend optimal discharge timing decisions given a patient's electronic health records. A data-driven approach is used to derive a parsimonious, discrete state space representation that captures a patient's physiological condition. Based on this model and a given cost function, an infinite-horizon discounted Markov decision process is formulated and solved numerically to compute an optimal discharge policy, whose value is assessed using off-policy evaluation strategies. Extensive numerical experiments are performed to validate the proposed framework using real-life intensive care unit patient data.