Automated Supervised Feature Selection for Differentiated Patterns of Care

TL;DR

This paper presents an automated feature selection pipeline combining multiple techniques to improve the detection of anomalous care patterns, emphasizing the importance of data distribution in selecting features.

Contribution

The study introduces a comprehensive feature selection pipeline for Differentiated Patterns of Care, integrating filters, wrappers, and embedded methods, and evaluates their effectiveness in anomaly detection.

Findings

Feature selection improves anomaly detection performance.

Data distribution influences the choice of feature selection technique.

Selected features enhance the identification of anomalous care subpopulations.

Abstract

An automated feature selection pipeline was developed using several state-of-the-art feature selection techniques to select optimal features for Differentiating Patterns of Care (DPOC). The pipeline included three types of feature selection techniques; Filters, Wrappers and Embedded methods to select the top K features. Five different datasets with binary dependent variables were used and their different top K optimal features selected. The selected features were tested in the existing multi-dimensional subset scanning (MDSS) where the most anomalous subpopulations, most anomalous subsets, propensity scores, and effect of measures were recorded to test their performance. This performance was compared with four similar metrics gained after using all covariates in the dataset in the MDSS pipeline. We found out that despite the different feature selection techniques used, the data distribution is key to note when determining the technique to use.