Gradient boosting models for gallstone disease classification: A comparative study using demographic and clinical data
- 1School of Data and Sciences, BRAC University, Dhaka, Bangladesh.
- 2Department of R&D, Chowa Giken Corporation, Sapporo, Japan.
- 3Department of Computer Science and Engineering, East Delta University, Chattogram, Bangladesh.
Abstract
Gallstone disease is a prevalent gastrointestinal condition with a substantial healthcare burden. While abdominal ultrasonography is the established first-line diagnostic modality, opportunistic risk stratification using routinely collected health parameters remains underexplored. This study evaluated the discriminatory capacity of four gradient boosting machine learning algorithms (XGBoost, LightGBM, CatBoost, and HistGBM) for classifying gallstone status using demographic, bioimpedance, and routine laboratory features. A retrospective clinical dataset of 319 patients (161 gallstone-positive individuals and 158 healthy controls) from Ankara VM Medical Park Hospital was analyzed. Model performance was assessed using repeated stratified 10-fold cross-validation, evaluated via AUC-ROC, accuracy, F1-score, sensitivity, specificity, Brier score, and decision curve analysis (DCA), with SHAP analyses employed for model interpretability. CatBoost achieved the highest discriminatory performance (AUC = 0.862±0.061, accuracy = 0.794±0.075) and the lowest Brier score (0.149±0.037), demonstrating statistically significant superiority over competing architectures (Friedman test, p < 0.001). Feature ablation revealed that bioimpedance parameters alone provided substantial independent discriminative signal (AUC = 0.797±0.079), approaching that of laboratory markers (AUC = 0.829±0.070), whereas demographic attributes alone were insufficient (AUC = 0.476±0.097). SHAP analyses identified C-reactive protein, Vitamin D, and bone mass as the most influential variables, alongside non-linear risk associations for visceral fat area and body mass index. Decision curve analysis demonstrated positive net clinical benefit across threshold probabilities of 0.10–0.80. These findings demonstrate that gradient boosting models, particularly CatBoost, can provide robust, interpretable retrospective classification of gallstone disease, offering proof-of-concept potential for opportunistic risk stratification in metabolic care settings and pre-imaging triage for ambiguous outpatient presentations rather than replacing first-line ultrasonography.
Related
- Comparative analysis of gradient boosting and random forest regressors for nutrient prediction in smart agriculture
- Leakage-Controlled Benchmarking of Variant Effect Predictors and Development of Gradient-Boosting Consensus Model
- AgroAdvisor: crop yield prediction, crop and fertilizer recommendation system using random forest with gradient boosting and DeepFM for precise agriculture
- Predicting driving performance from resting-state EEG using explainable gradient boosting
- Comparative Long-Term Immunogenicity and Boosting of 3-Session Versus 4-Session Intradermal Rabies Post-Exposure Prophylaxis Regimens in Cambodia and Madagascar: The RESIST-3 Study
BibTeX
@article{hasan2026gradient,
title = {{Gradient boosting models for gallstone disease classification: A comparative study using demographic and clinical data}},
author = {Kazi Sakib Hasan and Sumaiya Hossain Puspita},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0361572},
url = {https://doi.org/10.1371/journal.pone.0361572},
note = {CC BY},
}
RIS
TY - JOUR
TI - Gradient boosting models for gallstone disease classification: A comparative study using demographic and clinical data
AU - Kazi Sakib Hasan
AU - Sumaiya Hossain Puspita
PY - 2026
DA - 2026/10/30
JO - PLOS One
DO - 10.1371/journal.pone.0361572
UR - https://doi.org/10.1371/journal.pone.0361572
AB - Gallstone disease is a prevalent gastrointestinal condition with a substantial healthcare burden. While abdominal ultrasonography is the established first-line diagnostic modality, opportunistic risk stratification using routinely collected health parameters remains underexplored. This study evaluated the discriminatory capacity of four gradient boosting machine learning algorithms (XGBoost, LightGBM, CatBoost, and HistGBM) for classifying gallstone status using demographic, bioimpedance, and routine laboratory features. A retrospective clinical dataset of 319 patients (161 gallstone-positive individuals and 158 healthy controls) from Ankara VM Medical Park Hospital was analyzed. Model performance was assessed using repeated stratified 10-fold cross-validation, evaluated via AUC-ROC, accuracy, F1-score, sensitivity, specificity, Brier score, and decision curve analysis (DCA), with SHAP analyses employed for model interpretability. CatBoost achieved the highest discriminatory performance (AUC = 0.862±0.061, accuracy = 0.794±0.075) and the lowest Brier score (0.149±0.037), demonstrating statistically significant superiority over competing architectures (Friedman test, p < 0.001). Feature ablation revealed that bioimpedance parameters alone provided substantial independent discriminative signal (AUC = 0.797±0.079), approaching that of laboratory markers (AUC = 0.829±0.070), whereas demographic attributes alone were insufficient (AUC = 0.476±0.097). SHAP analyses identified C-reactive protein, Vitamin D, and bone mass as the most influential variables, alongside non-linear risk associations for visceral fat area and body mass index. Decision curve analysis demonstrated positive net clinical benefit across threshold probabilities of 0.10–0.80. These findings demonstrate that gradient boosting models, particularly CatBoost, can provide robust, interpretable retrospective classification of gallstone disease, offering proof-of-concept potential for opportunistic risk stratification in metabolic care settings and pre-imaging triage for ambiguous outpatient presentations rather than replacing first-line ultrasonography.
SN - 1932-6203
ER -