Bayesian Latent Class Regression and Variable Selection with Applications to Sleep Patterns Data

2025-12-16

AI Summary

Children’s sleep problems exhibit high phenotypic heterogeneity, yet conventional scales (e.g., CSHQ) rely on a single total score, obscuring clinically distinct subtypes requiring tailored interventions. To address key limitations of latent class regression (LCR) models under Bayesian inference—including non-identifiability, high computational cost, and absence of bidirectional variable selection—we propose a novel, identifiable, and interpretable Bayesian LCR framework. It uniquely integrates Pólya–Gamma data augmentation with partial marginalization to jointly perform automated selection of both predictive covariates and scale items. Applied to CSHQ data from 148 children, the model robustly identifies three clinically meaningful subtypes: anxiety-related night wakings, short/shallow sleep, and pervasive sleep disturbances. Crucially, ASD diagnosis emerges as a highly discriminative predictor—significantly outperforming total-score-based assessment in subtype differentiation.

Technology Category

• Machine Learning: Bayesian Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Sleep difficulties in children are heterogeneous in presentation, yet conventional assessment tools like the Children's Sleep Habits Questionnaire (CSHQ) reduce this complexity to a single cumulative score, obscuring distinct patterns of sleep disturbance that require different interventions. Latent Class Regression (LCR) models offer a principled approach to identify subgroups with shared sleep behaviour profiles whilst incorporating predictors of group membership, but Bayesian inference for these models has been hindered by computational challenges and the absence of variable selection methods. We propose a fully Bayesian framework for LCR that uses Pólya-Gamma data augmentation, enabling efficient sampling of regression coefficients. We extend this framework to include variable selection for both predictors and item responses: predictor variable selection via latent inclusion indicators and item selection through a partially collapsed approach. Through simulation studies, we show that the proposed methods yield accurate parameter estimates, resolve identifiability issues arising in full models and successfully identify informative predictors and items while excluding noise variables. Applying this methodology to CSHQ data from 148 children reveals distinct latent subgroups with different sleep behaviour profiles, anxious nighttime sleepers, short/light sleepers and those with more pervasive sleep problems, with each carrying distinct implications for intervention. Results also highlight the predictive role of Autism Spectrum Disorder diagnosis in subgroup membership. These findings demonstrate the limitations of conventional CSHQ scoring and illustrate the benefits of a probabilistic subgroup-based approach as an alternative for understanding paediatric sleep difficulties.

Problem

• Identifies distinct sleep disturbance subgroups in children using Bayesian Latent Class Regression.
• Incorporates variable selection for predictors and items to exclude noise variables.
• Demonstrates limitations of conventional scoring and benefits of probabilistic subgroup analysis.

Innovation

• Bayesian LCR with Pólya-Gamma augmentation for efficient sampling
• Variable selection via latent indicators and partially collapsed approach
• Identifies subgroups and predictors in sleep data for targeted interventions