A Deep Reinforcement Learning-Based Feature Selection Method for Invasive Disease Event Prediction Using Imbalanced Follow-Up Data

• Published in: IEEE journal of biomedical and health informatics Vol. 29; no. 2; pp. 1472 - 1483
• Main Authors: Du, Yangyi, Zhou, Xiaojun, Gao, Qian, Yang, Chunhua, Huang, Tingwen
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2025
• Subjects: Breast cancer; Breast Neoplasms - pathology; Datasets as Topic; Deep reinforcement learning; Diseases; Feature extraction; feature selection; Female; Hospitals; Humans; imbalanced data; invasive disease events; Iterative methods; Neoplasm Invasiveness; Prediction algorithms; Predictive models; Prognosis; Prognostics and health management; Reinforcement learning; Reinforcement Machine Learning; Training
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2024.3497325

The machine learning-based model is a promising paradigm for predicting invasive disease events (iDEs) in breast cancer. Feature selection (FS) is an essential preprocessing technique employed to identify the pertinent features for the prediction model. However, conventional FS methods often fail with imbalanced clinical data due to the bias towards the majority class. In this paper, a novel FS framework based on reinforcement learning (RLFS) is developed to identify the optimal feature subset for the imbalanced data. The RLFS employs an iterative methodology, wherein data resampling technique generates a balanced dataset before each iteration. A decision network is trained using a deep RL algorithm to identify the relevant features for the dataset in the current iteration. With such an iterative training strategy, numerous constructed datasets gradually boost the FS capacity of the decision network, resulting in a robust performance for imbalanced data. Finally, a weighted model is proposed to determine the most suitable FS solution. The RLFS is employed to predict breast cancer iDEs using real follow-up data. The comparison results demonstrated that RLFS effectively reduces the number of features while outperforming several state-of-the-art FS algorithms.