Predicting risk for a new patient with missing risk factor: a submodel approach for binary outcome

2285 

Contributed Abstract 

Paper 

Tianyi Sun (1), Allison B. McCoy (2), Alan B. Storrow (2), Dandan Liu (2)

(1) Vanderbilt University, N/A, (2) Vanderbilt University Medical Center, N/A

Allison B. McCoy  
Vanderbilt University Medical Center

Alan B. Storrow  
Vanderbilt University Medical Center

Dandan Liu  
Vanderbilt University Medical Center

Tianyi Sun  
Vanderbilt University

Tianyi Sun  
Vanderbilt University

Massive clinical predictive models are published in medical literature in the past decades, however, very few of these models have been implemented into electronic health record (EHR) system to aid decision-making in clinical practice. One obstacle for real-time implementation is handling missing information upon risk score calculation. In this paper, we propose a new submodel approximation approach for binary outcome. Under certain assumption, this approach only relies on the original coefficients and the first two moments of a function involving all missing risk factor. The proposed approach has the advantage of borrowing information from the target population. The asymptotic properties of the proposed estimator was derived and assessed through comprehensive simulations. The model performance was also assessed in simulation studies and compared with existing approaches including one-step-sweep (OSS) submodel and the imputation by fixed chained equations approaches. The proposed method was applied to address missing risk factor issues in predicting the risk of 30-day adverse event of acute heart failure patients.

submodel approximation|binary outcome|missing risk factors|EHR|prediction model|

Biometrics Section

Risk Prediction