Feature importance analysis for patient management decisions
For healthcare AI researchers, this work provides insight into feature importance for clinical decision prediction, but it is incremental as it applies existing methods to a specific dataset.
The paper analyzes clinical data from 4486 post-surgical cardiac patients to identify which features most influence physician decisions on lab orders and medications, finding that many decisions can be well predicted from a small subset of features.
The objective of this paper is to understand what characteristics and features of clinical data influence physician's decision about ordering laboratory tests or prescribing medications the most. We conduct our analysis on data and decisions extracted from electronic health records of 4486 post-surgical cardiac patients. The summary statistics for 335 different lab order decisions and 407 medication decisions are reported. We show that in many cases, physician's lab-order and medication decisions can be well predicted from a small subset of all features.