Abstract: Risk adjustment models for intensive care outcomes have yet to realize the full potential of data unlocked by the increasing adoption of EHRs. In particular, they fail to fully leverage the information present in longitudinal, structured clinical data – including laboratory test results and vital signs – nor can they infer patient state from unstructured clinical narratives without lengthy manual abstraction. A fully electronic ICU risk model fusing these two types of data sources may yield improved accuracy and more personalized risk estimates, and in obviating manual abstraction, could also be used for real-time decision-making. As a first step towards fully “electronic” ICU models based on fused data, we present results of generalized additive modeling applied to a sample of over 36,000 ICU patients. Our approach outperforms those based on the SAPS and OASIS systems (AUC: 0.908 vs. 0.794 and 0.874), and appears to yield more granular and easily visualized risk estimates.
Learning Objective 1: To understand the limitations of existing ICU risk adjustment methodology and the need for more agile "fully electronic" ICU risk models.
Learning Objective 2 (Optional): To understand how features derived from unstructured data sources can add value to ICU risk models.
Learning Objective 3 (Optional): To understand the extent of possible interactions between these features derived from unstructured data and those from structured data.
Learning Objective 4 (Optional): To understand the possible challenges involved with incorporating features derived from unstructured data sources into ICU risk and other models.
Ben Marafino (Presenter)
R. Adams Dudley, University of California, San Francisco
Nigam Shah, Stanford University
Jonathan Chen, Stanford University