Reinforcement Learning to Optimize Ventilator Settings for Patients on Invasive Mechanical Ventilation: Retrospective Study
Our study found that customizing ventilation settings for individual patients led to lower estimated hospital mortality rates compared to actual rates. This highlights the potential effectiveness of using reinforcement learning methodology to develop AI models that analyze complex clinical data for optimizing treatment parameters. Additionally, our findings suggest the integration of this model into a clinical decision support system for refining ventilation settings, supporting the need for prospective validation trials.
Authors
- Mengling Feng (ORCID: https://orcid.org/0000-0002-5338-6248)
- Guotong Xie
- Zhuoyang Xu (ORCID: https://orcid.org/0000-0003-0344-3424)
- Qianyi Xu (ORCID: https://orcid.org/0009-0009-5982-3953)
- Xingzhi Sun (ORCID: https://orcid.org/0000-0002-6519-0197)
- Kay Choong See (ORCID: https://orcid.org/0000-0003-2528-7282)
- Zhuo Liu (ORCID: https://orcid.org/0000-0001-9343-2969)
- Siqi Liu (ORCID: https://orcid.org/0000-0002-0605-2958)
Institutions
- National University of Singapore (SG)
- National University Hospital (SG)
- National University Health System (SG)
- Ping An (China)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2024-09-02
- DOI
- https://doi.org/10.2196/44494
- Citations
- 17
- Primary Topic
- Respiratory Support and Mechanisms
- Type
- article
- Field-Weighted Citation Impact
- 7.12