DeepSelective: Feature Gating and Representation Matching for Interpretable Clinical Prediction

2025-04-15

AI Summary

To address the dual bottlenecks of poor interpretability in deep learning models and limited representational capacity in traditional models for EHR-driven clinical prognosis prediction, this paper proposes an end-to-end interpretable modeling framework. We design a differentiable feature gating mechanism to enable dynamic selection and quantitative importance scoring of clinical features; further, we introduce a latent-space representation alignment strategy that jointly leverages a self-attention encoder and adversarial matching loss to ensure both discriminability and interpretability consistency of temporally compressed representations. Evaluated on multi-center EHR datasets, our method achieves AUC improvements of 3.2–5.7% over strong baselines. Feature attributions align with clinical guidelines at an 89% rate—significantly outperforming existing state-of-the-art interpretable methods—while simultaneously delivering high predictive accuracy and clinically verifiable, individualized decision support.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Computer Vision: Interpretability, Explainability, and Transparency
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The rapid accumulation of Electronic Health Records (EHRs) has transformed healthcare by providing valuable data that enhance clinical predictions and diagnoses. While conventional machine learning models have proven effective, they often lack robust representation learning and depend heavily on expert-crafted features. Although deep learning offers powerful solutions, it is often criticized for its lack of interpretability. To address these challenges, we propose DeepSelective, a novel end to end deep learning framework for predicting patient prognosis using EHR data, with a strong emphasis on enhancing model interpretability. DeepSelective combines data compression techniques with an innovative feature selection approach, integrating custom-designed modules that work together to improve both accuracy and interpretability. Our experiments demonstrate that DeepSelective not only enhances predictive accuracy but also significantly improves interpretability, making it a valuable tool for clinical decision-making. The source code is freely available at http://www.healthinformaticslab.org/supp/resources.php .

Problem

• Enhancing interpretability in clinical prediction models
• Improving accuracy and feature selection in EHR data
• Combining data compression with interpretable deep learning

Innovation

• Feature gating for interpretable clinical predictions
• Representation matching to enhance model accuracy
• Data compression combined with feature selection