Stabilizing Sparse Cox Model using Clinical Structures in Electronic Medical Records

Stability in clinical prediction models is crucial for transferability between studies, yet has received lit-tle attention. The problem is paramount in high-dimensional data which invites sparse models with fea-ture selection capability. We introduce an effective method to stabilize sparse Cox model of time-to-events using clinical structures inherent in Electronic Medical Records (EMR). Model estimation is stabilized using a feature graph derived from two types of EMR struc-tures: temporal structure of disease and intervention re-currences, and hierarchical structure of medical knowl-edge and practices. We demonstrate the efficacy of the method in predicting time-to-readmission of heart fail-ure patients. On two stability measures – the Jaccard index and the Consistency index – the use of clinical structures significantly increased feature stability with-out hurting discriminative power. Our model reported a competitive AUC of 0.64 (95 % CIs: [0.58,0.69]) for 6 months prediction.