Publications by authors named "Floris den Hengst"
Reinforcement Learning (RL) has recently found many applications in the healthcare domain thanks to its natural fit to clinical decision-making and ability to learn optimal decisions from observational data. A key challenge in adopting RL-based solution in clinical practice, however, is the inclusion of existing knowledge in learning a suitable solution. Existing knowledge from e.
View Article and Find Full Text PDFArticle Synopsis
- Reinforcement learning (RL) has potential applications in ICU settings for improving decision-making, and a systematic review was conducted to evaluate its impact on critically ill patients.
- A total of 1,033 articles were screened, resulting in 18 journal articles and 18 conference papers focused on RL techniques; however, all studies only showed RL outperforming clinicians based on retrospective data.
- The review concluded that while RL techniques reported better decision-making than clinicians, there were no studies proving actual improvements in patient outcomes, and there was a high risk of bias in the evaluation procedures.