# Value of an automated machine learning model with post-hoc explanation for predicting healthcare-seeking delays among residents in Tibetan regions

## TL;DR

This study uses automated machine learning and SHAP explanations to predict healthcare-seeking delays among Tibetan residents and identify key factors influencing these delays.

## Contribution

The novel contribution is the integration of AutoML with post-hoc SHAP interpretation for predicting healthcare-seeking delays in a Tibetan population.

## Key findings

- The LightGBM model achieved an AUC > 0.86, outperforming conventional approaches.
- SHAP analysis identified age and hospital quality as top predictors of healthcare-seeking delays.
- A clinical decision support system was developed to optimize resource allocation in Tibetan healthcare.

## Abstract

This study aimed to investigate key determinants of healthcare-seeking delays among Tibetan residents and develop predictive models using automated machine learning (AutoML) with post-hoc SHAP interpretation alongside a clinical decision support system.

Face-to-face surveys using structured questionnaires were administered to 1,879 Tibetan residents. Data processing employed an AutoML framework: datasets were partitioned into training (n = 1,503) and testing (n = 376) subsets at an 8:2 ratio. Standardized preprocessing—including outlier rectification, one-hot encoding (OHE), and random forest-based multiple imputation (MI)—was applied. Model validation integrated 5-fold cross-validation and SHapley Additive exPlanations (SHAP) analysis.

Among 1,879 participants, the healthcare-seeking delay incidence was 41.99%. The LightGBM model significantly outperformed conventional approaches (AUC > 0.86). SHAP feature importance analysis revealed the predictor hierarchy: Age > County hospital quality score > Distance to county hospital > Township health center quality score > Able to communicate in Chinese.

A high-performance model with post-hoc SHAP interpretation accurately identifies geographical, cultural, and healthcare resource variables to accurately identify high-risk populations. The developed clinical decision support system enables risk computation through modular interfaces, providing an evidence-based tool for optimizing hierarchical diagnosis and resource allocation in Tibetan healthcare.