Development and temporal validation of an explainable machine learning model for predicting in-hospital diabetic foot ulcer in patients with type 2 diabetes using inflammatory–nutritional composite indices
- 1he Sixth Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China
Abstract
ObjectiveThis study aimed to develop and temporally validate explainable machine learning models for predicting in-hospital new-onset DFU in hospitalized patients with type 2 diabetes mellitus (T2DM) using routinely available admission variables and inflammatory–nutritional composite indices.MethodsThis retrospective prediction-model study enrolled 550 consecutive hospitalized patients with T2DM admitted between January 2022 and December 2024. Patients admitted during 2022–2023 (n = 400) constituted the development cohort, whereas those admitted in 2024 (n = 150) served as an independent temporal validation cohort. Candidate predictors included demographic characteristics, diabetes duration, routine laboratory biomarkers, ankle–brachial index (ABI), and inflammatory–nutritional composite indices, including neutrophil percentage-to-albumin ratio (NPAR), albumin-to-neutrophil-to-lymphocyte ratio (ANLR), hemoglobin–albumin–lymphocyte–platelet score (HALP), systemic immune-inflammation index (SII), and C-reactive protein-to-albumin ratio (CRP/ALB). Candidate variables were screened using univariable logistic regression followed by least absolute shrinkage and selection operator (LASSO) regression. Logistic regression, random forest, LightGBM, and XGBoost models were developed and evaluated using the area under the receiver operating characteristic curve (AUC), average precision (AP), sensitivity, specificity, F1-score, Brier score, calibration analysis, and decision curve analysis (DCA). Model interpretability was assessed using SHapley Additive exPlanations (SHAP).ResultsDuring hospitalization, 66 patients (12.0%) developed DFU. Eleven predictors were retained after feature selection, including age, diabetes duration, neutrophil percentage, C-reactive protein, high-density lipoprotein cholesterol, glycated hemoglobin, ABI, NPAR, ANLR, HALP, and SII. In the temporal validation cohort, logistic regression had the highest observed discrimination (AUC = 0.976; bootstrap 95% CI, 0.936–0.992), with a sensitivity of 0.944, specificity of 0.932, and F1-score of 0.773 at the prespecified threshold; however, its Hosmer–Lemeshow test indicated evidence of lack of fit (P = 0.001). LightGBM had the lowest Brier score (0.064), whereas XGBoost achieved an AUC of 0.945, a Brier score of 0.067, and a Hosmer–Lemeshow P value of 0.350. At the prespecified thresholds, LightGBM and XGBoost sensitivities were only 0.056 and 0.389, respectively. SHAP analysis identified ANLR, glycated hemoglobin, HALP, age, and SII as the five most influential XGBoost predictors. Because the temporal validation cohort contained only 18 DFU events, these performance estimates should be interpreted cautiously.ConclusionAdmission-based machine learning models showed high observed discrimination for in-hospital DFU risk stratification, but no model was uniformly superior across discrimination, calibration, and threshold-dependent sensitivity. The small number of validation events, possible redundancy among mathematically overlapping predictors, omitted established foot-risk variables, and the low sensitivity of LightGBM and XGBoost at their prespecified thresholds preclude direct use as screening tools. Prospective multicenter validation, formal assessment of predictor redundancy, threshold recalibration, and clinical-impact evaluation are required before implementation.
Related
- Development and internal temporal validation of an explainable XGBoost model for predicting clinical pregnancy after frozen embryo transfer
- Nutritional status, inflammatory burden, and CT-derived muscle phenotypes for predicting chronic postsurgical pain after total hip arthroplasty: an explainable machine learning study
- Development and validation of a novel metabolic-inflammatory health-related nomogram for predicting in-hospital mortality in older patients with type 2 diabetes mellitus combined with cardiovascular disease
- Construction and validation of a nomogram based on inflammatory, nutritional and metabolic indicators for predicting the risk of papillary thyroid carcinoma.
- Explainable Machine Learning for Predicting Major Adverse Renal and Cardiovascular Events in Acute Myocardial Infarction With Chronic Kidney Disease: Algorithm Development and Validation
BibTeX
@article{wang2026development,
title = {{Development and temporal validation of an explainable machine learning model for predicting in-hospital diabetic foot ulcer in patients with type 2 diabetes using inflammatory–nutritional composite indices}},
author = {Xue Wang and Chao Li and Yanan Tuo and Bo Zhao and Ayiding Xiahati and Lu Fan and Paerhati Wahafu},
journal = {Frontiers in Medicine},
year = {2026},
month = oct,
doi = {10.3389/fmed.2026.1938429},
url = {https://doi.org/10.3389/fmed.2026.1938429},
note = {CC BY},
}
RIS
TY - JOUR
TI - Development and temporal validation of an explainable machine learning model for predicting in-hospital diabetic foot ulcer in patients with type 2 diabetes using inflammatory–nutritional composite indices
AU - Xue Wang
AU - Chao Li
AU - Yanan Tuo
AU - Bo Zhao
AU - Ayiding Xiahati
AU - Lu Fan
AU - Paerhati Wahafu
PY - 2026
DA - 2026/10/23
JO - Frontiers in Medicine
DO - 10.3389/fmed.2026.1938429
UR - https://doi.org/10.3389/fmed.2026.1938429
AB - ObjectiveThis study aimed to develop and temporally validate explainable machine learning models for predicting in-hospital new-onset DFU in hospitalized patients with type 2 diabetes mellitus (T2DM) using routinely available admission variables and inflammatory–nutritional composite indices.MethodsThis retrospective prediction-model study enrolled 550 consecutive hospitalized patients with T2DM admitted between January 2022 and December 2024. Patients admitted during 2022–2023 (n = 400) constituted the development cohort, whereas those admitted in 2024 (n = 150) served as an independent temporal validation cohort. Candidate predictors included demographic characteristics, diabetes duration, routine laboratory biomarkers, ankle–brachial index (ABI), and inflammatory–nutritional composite indices, including neutrophil percentage-to-albumin ratio (NPAR), albumin-to-neutrophil-to-lymphocyte ratio (ANLR), hemoglobin–albumin–lymphocyte–platelet score (HALP), systemic immune-inflammation index (SII), and C-reactive protein-to-albumin ratio (CRP/ALB). Candidate variables were screened using univariable logistic regression followed by least absolute shrinkage and selection operator (LASSO) regression. Logistic regression, random forest, LightGBM, and XGBoost models were developed and evaluated using the area under the receiver operating characteristic curve (AUC), average precision (AP), sensitivity, specificity, F1-score, Brier score, calibration analysis, and decision curve analysis (DCA). Model interpretability was assessed using SHapley Additive exPlanations (SHAP).ResultsDuring hospitalization, 66 patients (12.0%) developed DFU. Eleven predictors were retained after feature selection, including age, diabetes duration, neutrophil percentage, C-reactive protein, high-density lipoprotein cholesterol, glycated hemoglobin, ABI, NPAR, ANLR, HALP, and SII. In the temporal validation cohort, logistic regression had the highest observed discrimination (AUC = 0.976; bootstrap 95% CI, 0.936–0.992), with a sensitivity of 0.944, specificity of 0.932, and F1-score of 0.773 at the prespecified threshold; however, its Hosmer–Lemeshow test indicated evidence of lack of fit (P = 0.001). LightGBM had the lowest Brier score (0.064), whereas XGBoost achieved an AUC of 0.945, a Brier score of 0.067, and a Hosmer–Lemeshow P value of 0.350. At the prespecified thresholds, LightGBM and XGBoost sensitivities were only 0.056 and 0.389, respectively. SHAP analysis identified ANLR, glycated hemoglobin, HALP, age, and SII as the five most influential XGBoost predictors. Because the temporal validation cohort contained only 18 DFU events, these performance estimates should be interpreted cautiously.ConclusionAdmission-based machine learning models showed high observed discrimination for in-hospital DFU risk stratification, but no model was uniformly superior across discrimination, calibration, and threshold-dependent sensitivity. The small number of validation events, possible redundancy among mathematically overlapping predictors, omitted established foot-risk variables, and the low sensitivity of LightGBM and XGBoost at their prespecified thresholds preclude direct use as screening tools. Prospective multicenter validation, formal assessment of predictor redundancy, threshold recalibration, and clinical-impact evaluation are required before implementation.
SN - 2296-858X
ER -