Heterogeneity-Aware Regression with Nonparametric Estimation and Structured Selection for Hospital Readmission Prediction

2025-07-08

AI Summary

Addressing the challenges of high clinical heterogeneity, complex risk mechanisms, and the need for interpretability in hospital readmission prediction, this paper proposes an interpretable hierarchical nonparametric regression model. Methodologically, it introduces a hierarchical grouped kernel structure with sparsity-inducing kernel addition, enabling adaptive alignment or separation of kernel functions across diagnostic groups. By integrating functional ANOVA expansion with group-specific kernels, the model achieves structured variable selection among high-dimensional covariates and captures high-order interaction effects. Experiments on simulated data and a real-world cohort of 18,096 hematologic patients demonstrate that the model significantly outperforms Lasso and XGBoost, yielding consistent improvements in AUROC and PRAUC across clinical subgroups. Moreover, it provides both global variable importance rankings and subgroup-specific heterogeneity analysis, thereby balancing predictive accuracy with clinical interpretability.

Technology Category

• Machine Learning: Kernel Methods
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Readmission prediction is a critical but challenging clinical task, as the inherent relationship between high-dimensional covariates and readmission is complex and heterogeneous. Despite this complexity, models should be interpretable to aid clinicians in understanding an individual's risk prediction. Readmissions are often heterogeneous, as individuals hospitalized for different reasons, particularly across distinct clinical diagnosis groups, exhibit materially different subsequent risks of readmission. To enable flexible yet interpretable modeling that accounts for patient heterogeneity, we propose a novel hierarchical-group structure kernel that uses sparsity-inducing kernel summation for variable selection. Specifically, we design group-specific kernels that vary across clinical groups, with the degree of variation governed by the underlying heterogeneity in readmission risk; when heterogeneity is minimal, the group-specific kernels naturally align, approaching a shared structure across groups. Additionally, by allowing variable importance to adapt across interactions, our approach enables more precise characterization of higher-order effects, improving upon existing methods that capture nonlinear and higher-order interactions via functional ANOVA. Extensive simulations and a hematologic readmission dataset (n=18,096) demonstrate superior performance across subgroups of patients (AUROC, PRAUC) over the lasso and XGBoost. Additionally, our model provides interpretable insights into variable importance and group heterogeneity.

Problem

• Predict hospital readmission with complex heterogeneous relationships
• Ensure interpretable models for clinical risk understanding
• Address patient heterogeneity via structured variable selection

Innovation

• Hierarchical-group structure kernel for heterogeneity
• Sparsity-inducing kernel summation for variable selection
• Adaptive variable importance for higher-order effects