Comparison of methods for early-readmission prediction in a high-dimensional heterogeneous covariates and time-to-event outcome framework

TL;DR

This study compares various statistical and machine learning methods for early readmission prediction in high-dimensional, heterogeneous data, considering both binary and survival outcomes, and highlights the superior performance of the C-mix model.

Contribution

It introduces a comprehensive comparison methodology that evaluates methods across binary and survival settings, incorporating advanced machine learning strategies and variable selection techniques.

Findings

C-mix model outperforms other methods in prediction accuracy

Survival-based learning improves binary prediction performance

Consistent covariate selection within but not across settings

Abstract

Background: Choosing the most performing method in terms of outcome prediction or variables selection is a recurring problem in prognosis studies, leading to many publications on methods comparison. But some aspects have received little attention. First, most comparison studies treat prediction performance and variable selection aspects separately. Second, methods are either compared within a binary outcome setting (based on an arbitrarily chosen delay) or within a survival setting, but not both. In this paper, we propose a comparison methodology to weight up those different settings both in terms of prediction and variables selection, while incorporating advanced machine learning strategies. Methods: Using a high-dimensional case study on a sickle-cell disease (SCD) cohort, we compare 8 statistical methods. In the binary outcome setting, we consider logistic regression (LR), support vector machine (SVM), random forest (RF), gradient boosting (GB) and neural network (NN); while on the survival analysis setting, we consider the Cox Proportional Hazards (PH), the CURE and the C-mix models. We then compare performances of all methods both in terms of risk prediction and variable selection, with a focus on the use of Elastic-Net regularization technique. Results: Among all assessed statistical methods assessed, the C-mix model yields the better performances in both the two considered settings, as well as interesting interpretation aspects. There is some consistency in selected covariates across methods within a setting, but not much across the two settings. Conclusions: It appears that learning withing the survival setting first, and then going back to a binary prediction using the survival estimates significantly enhance binary predictions.