Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 9, 2026Healthcare Informatics ResearchOpen Access

Nonlinear Interaction Patterns in Health Literacy Identified through Explainable Artificial Intelligence: A Focus on Age and Education

View Full Paper
Ask AI
Bookmark
Share

Authors

NKN KimNLNam-Ju Lee

Discussion

Loading...

Member takes

Overview

Cross-sectional study identifies predictors of health literacy in Korean adults, highlighting complex interactions between age and education.

Key Points

  • The study aims to identify predictors of health literacy, focusing on nonlinear relationships and interaction effects in a representative population.
  • Cross-sectional analysis of data from 8,630 Korean adults participating in the Korea Health Panel Survey.
  • Health literacy assessed using the HLS-EU-Q16 questionnaire and categorized as sufficient or insufficient.
  • Extreme gradient boosting algorithm (XGBoost) was applied to analyze interaction effects among 69 features.
  • XGBoost model achieved good discrimination (AUC = 0.840) and calibration (Brier score = 0.161).
  • Age (24.4%) and education level (19.0%) were the most influential predictors of health literacy.
  • Interaction analysis revealed a significant interaction between age and education level, especially among adults aged 60–80 with lower education.

Cite This Study

Kim et al. (2026) studied this question.

synapsesocial.com/papers/69fed0e2b9154b0b82878045https://doi.org/10.4258/hir.2026.32.2.134
View Full Paper
Ask AI
Bookmark
Share