Description

Abstract: Atrial fibrillation (AF) is a common cardiac arrhythmias, which increases the risk and severity of ischemic stroke. For predicting ischemic stroke in AF patients, a risk prediction model that can achieve both good model discrimination (e.g., AUC) and statistical significance of predictors is required in real clinical practices. In this paper, we propose a new bootstrap-based wrapper (Boots-wrapper) method of feature selection, and apply this method on Chinese Atrial Fibrillation Registry data to develop 1-year stroke prediction models in AF. The proposed method can heuristically search a subset of features to maximize the discrimination of the prediction model and minimize the penalty for the non-significant features. To achieve robust feature selection, we perform bootstrap sampling to get a more reliable estimate of the variation and significance statistics. The experimental results show that Boots-wrapper can balance model discrimination and statistical significance of features for developing AF stroke prediction models.

Learning Objective 1: After participating in this session, the learner should be better able to:
Build a risk prediction model that can achieve both good model discrimination (e.g., AUC) and statistical significance of predictors

Authors:

Xiang Li (Presenter)
IBM Research

Zhaonan Sun, IBM Research
Xin Du, Anzhen hospital
Haifeng Liu, IBM Research
Gang Hu, IBM Research
Guotong Xie, IBM Research

Presentation Materials:

Tags