Deep Reinforcement Learning for Efficient and Fair Allocation of Healthcare Resources

Li, Yikuan; Mao, Chengsheng; Huang, Kaixuan; Wang, Hanyin; Yu, Zheng; Wang, Mengdi; Luo, Yuan

doi:10.24963/ijcai.2025/1088

Deep Reinforcement Learning for Efficient and Fair Allocation of Healthcare Resources

Yikuan Li, Chengsheng Mao, Kaixuan Huang, Hanyin Wang, Zheng Yu, Mengdi Wang, Yuan Luo

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 9790-9798.

https://doi.org/10.24963/ijcai.2025/1088

Keywords

AI Ethics, Trust, Fairness: General
Multidisciplinary Topics and Applications: General
Planning and Scheduling: General

Abstract

The scarcity of health care resources, such as ventilators, often leads to the unavoidable consequence of rationing, particularly during public health emergencies or in resource-constrained settings like pandemics. The absence of a universally accepted standard for resource allocation protocols results in governments relying on varying criteria and heuristic-based approaches, often yielding suboptimal and inequitable outcomes. This study addresses the societal challenge of fair and effective critical care resource allocation by leveraging deep reinforcement learning to optimize policy decisions. We propose a transformer-based deep Q-network that integrates individual patient disease progression and interaction effects among patients to enhance allocation decisions. Our method aims to improve both fairness and overall patient outcomes. Experiments using metrics such as normalized survival rates and interracial allocation rate differences demonstrate that our approach significantly reduces excess deaths and achieves more equitable resource allocation compared to severity- and comorbidity-based protocols currently in use. Our findings highlight the potential of deep reinforcement learning to address critical health care challenges.

Yikuan Li, Chengsheng Mao, Kaixuan Huang, Hanyin Wang, Zheng Yu, Mengdi Wang, and Yuan Luo. 2025. Deep Reinforcement Learning for Efficient and Fair Allocation of Healthcare Resources. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 9790–9798. https://doi.org/10.24963/ijcai.2025/1088

@inproceedings{ijcai2025p1088,
  title     = {Deep Reinforcement Learning for Efficient and Fair Allocation of Healthcare Resources},
  author    = {Li, Yikuan and Mao, Chengsheng and Huang, Kaixuan and Wang, Hanyin and Yu, Zheng and Wang, Mengdi and Luo, Yuan},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {9790--9798},
  year      = {2025},
  month     = {8},
  note      = {AI and Social Good},
  doi       = {10.24963/ijcai.2025/1088},
  url       = {https://doi.org/10.24963/ijcai.2025/1088},
}

TY  - CPAPER
TI  - Deep Reinforcement Learning for Efficient and Fair Allocation of Healthcare Resources
AU  - Li, Yikuan
AU  - Mao, Chengsheng
AU  - Huang, Kaixuan
AU  - Wang, Hanyin
AU  - Yu, Zheng
AU  - Wang, Mengdi
AU  - Luo, Yuan
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 9790
EP  - 9798
DO  - 10.24963/ijcai.2025/1088
UR  - https://doi.org/10.24963/ijcai.2025/1088
ER  -