Incorporating Causal Effects into Deep Learning Predictions on EHR Data
This work addresses the problem of limited causal understanding in healthcare predictions for medical professionals, representing an incremental advancement in domain-specific methods.
The authors tackled the challenge of causal inference in Electronic Health Records (EHR) data by proposing a novel method to quantify causal effects and incorporate them into deep learning models, resulting in improved predictive performance and better result interpretation.
Electronic Health Records (EHR) data analysis plays a crucial role in healthcare system quality. Because of its highly complex underlying causality and limited observable nature, causal inference on EHR is quite challenging. Deep Learning (DL) achieved great success among the advanced machine learning methodologies. Nevertheless, it is still obstructed by the inappropriately assumed causal conditions. This work proposed a novel method to quantify clinically well-defined causal effects as a generalized estimation vector that is simply utilizable for causal models. We incorporated it into DL models to achieve better predictive performance and result interpretation. Furthermore, we also proved the existence of causal information blink spots that regular DL models cannot reach.