{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T18:53:08Z","timestamp":1793559188851,"version":"4.5.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T00:00:00Z","timestamp":1742860800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Diabetic foot ulcers (DFUs) constitute a significant complication among individuals with diabetes and serve as a primary cause of nontraumatic lower-extremity amputation (LEA) within this population. We aimed to develop machine learning (ML) models to predict the risk of LEA in DFU patients and used SHapley additive explanations (SHAPs) to interpret the model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this retrospective study, data from 1,035 patients with DFUs at Sun Yat-sen Memorial Hospital were utilized as the training cohort to develop the ML models. Data from 297 patients across multiple tertiary centers were used for external validation. We then used least absolute shrinkage and selection operator analysis to identify predictors of amputation. We developed five ML models [logistic regression (LR), support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN) and extreme gradient boosting (XGBoost)] to predict LEA in DFU patients. The performance of these models was evaluated using several metrics, including the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), precision, recall, accuracy, and F1 score. Finally, the SHAP method was used to ascertain the significance of the features and to interpret the model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In the final cohort comprising 1332 individuals, 600 patients underwent amputation. Following hyperparameter optimization, the XGBoost model achieved the best amputation prediction performance with an accuracy of 0.94, a precision of 0.96, an F1 score of 0.94 and an AUC of 0.93 for the internal validation set on the basis of the 17 features. For the external validation set, the model attained an accuracy of 0.78, a precision of 0.93, an F1 score of 0.78, and an AUC of 0.83. Through SHAP analysis, we identified white blood cell counts, lymphocyte counts, and blood urea nitrogen levels as the model\u2019s main predictors.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The XGBoost algorithm-based prediction model can be used to dynamically estimate the risk of LEA in DFU patients, making it a valuable tool for preventing the progression of DFUs to amputation.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fendo.2025.1526098","type":"journal-article","created":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T07:40:44Z","timestamp":1742888444000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["An interpreting machine learning models to predict amputation risk in patients with diabetic foot ulcers: a multi-center study"],"prefix":"10.3389","volume":"16","author":[{"given":"Haoran","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bichai","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,3,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"109119","DOI":"10.1016\/j.diabres.2021.109119","article-title":"Idf diabetes atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045","volume":"183","author":"Sun","year":"2022","journal-title":"Diabetes Res Clin Pract"},{"key":"B2","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1038\/nrendo.2017.151","article-title":"Global aetiology and epidemiology of type 2 diabetes mellitus and its complications","volume":"14","author":"Zheng","year":"2018","journal-title":"Nat Rev Endocrinol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e3266","DOI":"10.1002\/dmrr.v36.S1","article-title":"Practical guidelines on the prevention and management of diabetic foot disease (iwgdf 2019 update)","author":"Schaper","year":"2020","journal-title":"Diabetes Metab Res Rev"},{"key":"B4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1177\/1938640017694722","article-title":"Patients with diabetic foot disease fear major lower-extremity amputation more than death","volume":"11","author":"Wukich","year":"2018","journal-title":"Foot Ankle Spec"},{"key":"B5","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1186\/s13047-019-0345-y","article-title":"Predictors of lower extremity amputation in patients with diabetic foot ulcer: Findings from medfun, a multi-center observational study","volume":"12","author":"Ugwu","year":"2019","journal-title":"J Foot Ankle Res"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1053\/j.jfas.2016.01.012","article-title":"Mortality after nontraumatic major amputation among patients with diabetes and peripheral vascular disease: A systematic review","volume":"55","author":"Thorud","year":"2016","journal-title":"J Foot Ankle Surg"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/S1067-2516(96)80125-6","article-title":"Classification of diabetic foot wounds","volume":"35","author":"Lavery","year":"1996","journal-title":"J Foot Ankle Surg"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.2337\/dc05-2431","article-title":"A new wound-based severity score for diabetic foot ulcers: A prospective analysis of 1,000 patients","volume":"29","author":"Beckert","year":"2006","journal-title":"Diabetes Care"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.2337\/dc07-2367","article-title":"Use of the sinbad classification system and score in comparing outcome of foot ulcer management on three continents","volume":"31","author":"Ince","year":"2008","journal-title":"Diabetes Care"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e3273","DOI":"10.1002\/dmrr.v36.S1","article-title":"Guidelines on the classification of diabetic foot ulcers (iwgdf 2019)","author":"Monteiro-Soares","year":"2020","journal-title":"Diabetes Metab Res Rev"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.22271\/ortho.2018.v4.i1n.133","article-title":"A review of wagner classification and current concepts in management of diabetic foot","volume":"4","author":"Mehraj","year":"2018","journal-title":"Int J Orthop Sci"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.18203\/2349-2902.isj20175401","article-title":"A study to test the validity of diabetic ulcer severity score (duss) at tertiary care hospital","volume":"4","author":"Kumar","year":"2017","journal-title":"Int Surg J"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3389\/ftox.2024.1461587","article-title":"Ai and ml-based risk assessment of chemicals: Predicting carcinogenic risk from chemical-induced genomic instability","volume":"6","author":"Singh","year":"2024","journal-title":"Front Toxicol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e006556","DOI":"10.1161\/CIRCOUTCOMES.120.006556","article-title":"Recommendations for reporting machine learning analyses in clinical research","volume":"13","author":"Stevens","year":"2020","journal-title":"Circ Cardiovasc Qual Outcomes"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1325434","article-title":"The role of machine learning in advancing diabetic foot: a review","volume":"15","author":"Guan","year":"2024","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.sjbs.2019.12.020","article-title":"The amputation and survival of patients with diabetic foot based on establishment of prediction model","volume":"27","author":"Lin","year":"2020","journal-title":"Saudi J Biol Sci"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e0278445","DOI":"10.1371\/journal.pone.0278445","article-title":"Machine learning for the prediction of minor amputation in university of texas grade 3 diabetic foot ulcers","volume":"17","author":"Wang","year":"2022","journal-title":"PloS One"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.13691","article-title":"An explainable machine learning model for predicting in-hospital amputation rate of patients with diabetic foot ulcer","volume":"19","author":"Xie","year":"2022","journal-title":"Int Wound J"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1177\/19322968221142899","article-title":"A machine learning model for prediction of amputation in diabetics","volume":"18","author":"Stefanopoulos","year":"2024","journal-title":"J Diabetes Sci Technol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.7797","article-title":"Unintended consequences of machine learning in medicine","volume":"318","author":"Cabitza","year":"2017","journal-title":"JAMA"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"Lundberg","year":"2018","journal-title":"Nat BioMed Eng"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e3276","DOI":"10.1002\/dmrr.v36.S1","article-title":"Guidelines on diagnosis, prognosis, and management of peripheral artery disease in patients with foot ulcers and diabetes (iwgdf 2019 update)","author":"Hinchliffe","year":"2020","journal-title":"Diabetes Metab Res Rev"},{"key":"B23","doi-asserted-by":"publisher","first-page":"8857453","DOI":"10.1155\/2024\/8857453","article-title":"Explainable machine learning-based prediction model for diabetic nephropathy","volume":"2024","author":"Yin","year":"2024","journal-title":"J Diabetes Res"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.1054358","article-title":"Development and validation of a machine learning model to predict the risk of lymph node metastasis in renal carcinoma","volume":"13","author":"Feng","year":"2022","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B25","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"B26","doi-asserted-by":"publisher","first-page":"15","DOI":"10.5121\/ijdkp.2013.3402","article-title":"Evaluation measures for models assessment over imbalanced data sets","volume":"3","author":"Bekkar","year":"2013","journal-title":"Intl J Data Mining Knowledge Manage Process"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic Anal Perform measures classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Information Processing & Management"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.2174\/0115734110316443240725051037","article-title":"Investigating tattoo pigments composition with uv-vis and ft-ir spectroscopy supported by chemometric modelling","volume":"20","author":"Singh","year":"2024","journal-title":"Curr Analytical Chem"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2022.1019638","article-title":"Nomogram established on account of lasso-cox regression for predicting recurrence in patients with early-stage hepatocellular carcinoma","volume":"13","author":"Wang","year":"2022","journal-title":"Front Immunol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3197156","article-title":"A synthetic minority oversampling technique based on gaussian mixture model filtering for imbalanced data classification","volume":"35","author":"Xu","year":"2024","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"B31","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1186\/s12967-020-02620-5","article-title":"Predicting 30-days mortality for mimic-iii patients with sepsis-3: A machine learning approach using xgboost","volume":"18","author":"Hou","year":"2020","journal-title":"J Transl Med"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-021-02476-x","article-title":"Hybrid gene selection approach using xgboost and multi-objective genetic algorithm for cancer classification","volume":"60","author":"Deng","year":"2022","journal-title":"Med Biol Eng Comput"},{"key":"B33","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1186\/s12967-023-04205-4","article-title":"Construction and validation of prognostic models in critically ill patients with sepsis-associated acute kidney injury: Interpretable machine learning approach","volume":"21","author":"Fan","year":"2023","journal-title":"J Transl Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2315298","DOI":"10.1080\/0886022X.2024.2315298","article-title":"Machine learning algorithm for predict the in-hospital mortality in critically ill patients with congestive heart failure combined with chronic kidney disease","volume":"46","author":"Li","year":"2024","journal-title":"Ren Fail"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2023.1144806","article-title":"Clinical characteristics and risk factors of lower extremity amputation in the diabetic inpatients with foot ulcers","volume":"14","author":"Gong","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-017-4488-8","article-title":"Risk of lower limb amputation in a national prevalent cohort of patients with diabetes","volume":"61","author":"Gurney","year":"2018","journal-title":"Diabetologia"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.2337\/dci22-0043","article-title":"Etiology, epidemiology, and disparities in the burden of diabetic foot ulcers","volume":"46","author":"McDermott","year":"2023","journal-title":"Diabetes Care"},{"key":"B38","doi-asserted-by":"publisher","first-page":"e0226226","DOI":"10.1371\/journal.pone.0226226","article-title":"Anemia in patients with diabetic foot ulcer and its impact on disease outcome among Nigerians: Results from the medfun study","volume":"14","author":"Gezawa","year":"2019","journal-title":"PloS One"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.14076","article-title":"Status and influencing factors of lower limb amputation in patients with diabetic foot ulcer","volume":"20","author":"Peng","year":"2023","journal-title":"Int Wound J"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.atherosclerosis.2015.02.006","article-title":"Hdl cholesterol as a predictor for the incidence of lower extremity amputation and wound-related death in patients with diabetic foot ulcers","volume":"239","author":"Ikura","year":"2015","journal-title":"Atherosclerosis"},{"key":"B41","doi-asserted-by":"publisher","first-page":"e13531","DOI":"10.1111\/1753-0407.13531","article-title":"Factors associated with diabetic foot ulcers and lower limb amputations in type 1 and type 2 diabetes supported by real-world data from the german\/Austrian dpv registry","volume":"16","author":"Eckert","year":"2024","journal-title":"J Diabetes"},{"key":"B42","doi-asserted-by":"publisher","first-page":"14120","DOI":"10.1038\/s41598-024-64009-4","article-title":"The risk factors in diabetic foot ulcers and predictive value of prognosis of wound tissue vascular endothelium growth factor","volume":"14","author":"Xu","year":"2024","journal-title":"Sci Rep"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1038\/s41581-023-00741-w","article-title":"Kidney lipid dysmetabolism and lipid droplet accumulation in chronic kidney disease","volume":"19","author":"Mitrofanova","year":"2023","journal-title":"Nat Rev Nephrol"},{"key":"B44","doi-asserted-by":"publisher","first-page":"e3701","DOI":"10.1002\/dmrr.v40.3","article-title":"Performance of non-invasive bedside vascular testing in the prediction of wound healing or amputation among people with foot ulcers in diabetes: A systematic review","volume":"40","author":"Chuter","year":"2024","journal-title":"Diabetes Metab Res Rev"},{"key":"B45","doi-asserted-by":"publisher","first-page":"e0239236","DOI":"10.1371\/journal.pone.0239236","article-title":"Risk factors for lower extremity amputation in patients with diabetic foot ulcers: A meta-analysis","volume":"15","author":"Lin","year":"2020","journal-title":"PloS One"},{"key":"B46","doi-asserted-by":"publisher","first-page":"e160","DOI":"10.3346\/jkms.2023.38.e160","article-title":"Medial arterial calcification and the risk of amputation of diabetic foot ulcer in patients with diabetic kidney disease","volume":"38","author":"So","year":"2023","journal-title":"J Korean Med Sci"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1526098\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T07:40:53Z","timestamp":1742888453000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1526098\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,25]]},"references-count":46,"alternative-id":["10.3389\/fendo.2025.1526098"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1526098","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,25]]},"article-number":"1526098"}}