Deep Causal Behavioral Policy Learning: Applications to Healthcare
This addresses the challenge of leveraging tacit clinical knowledge in healthcare for applications like provider assignment and policy learning, though it appears incremental as it builds on existing deep learning and causal inference methods.
The paper tackles the problem of learning dynamic clinical behavioral regimes from non-randomized healthcare data by proposing deep causal behavioral policy learning (DC-BPL), which uses deep learning to model high-dimensional clinical action paths and identify causal links to patient outcomes, resulting in a method that identifies optimal providers and emulates their care decisions.
We present a deep learning-based approach to studying dynamic clinical behavioral regimes in diverse non-randomized healthcare settings. Our proposed methodology - deep causal behavioral policy learning (DC-BPL) - uses deep learning algorithms to learn the distribution of high-dimensional clinical action paths, and identifies the causal link between these action paths and patient outcomes. Specifically, our approach: (1) identifies the causal effects of provider assignment on clinical outcomes; (2) learns the distribution of clinical actions a given provider would take given evolving patient information; (3) and combines these steps to identify the optimal provider for a given patient type and emulate that provider's care decisions. Underlying this strategy, we train a large clinical behavioral model (LCBM) on electronic health records data using a transformer architecture, and demonstrate its ability to estimate clinical behavioral policies. We propose a novel interpretation of a behavioral policy learned using the LCBM: that it is an efficient encoding of complex, often implicit, knowledge used to treat a patient. This allows us to learn a space of policies that are critical to a wide range of healthcare applications, in which the vast majority of clinical knowledge is acquired tacitly through years of practice and only a tiny fraction of information relevant to patient care is written down (e.g. in textbooks, studies or standardized guidelines).