Key points are not available for this paper at this time.
Healthcare is a complex and intricate system where multiple factors interact to affect outcomes. Accordingly, simulation is a key tool to help healthcare researchers account for this complexity and explore “what if” scenarios. Similarly, machine learning is gaining popularity in healthcare as it can also account for this complexity and offers the potential to solve problems that are intractable for traditional methods. Given that both methods have conceptually similar objectives (both predict system responses), it begs a series of questions: Can they be used together to solve healthcare challenges and, if so, how can they be incorporated? What benefits and inspiration can such a combination bring to healthcare? This paper reviews the literature to help address these questions. First, the literature is broadly categorized into six types based on how they combined simulation and machine learning. Each type is then discussed and identified research gaps are presented.
Zhao et al. (Wed,) studied this question.