{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:28:40Z","timestamp":1793604520216,"version":"4.5.0"},"reference-count":50,"publisher":"BMJ","issue":"6","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"unspecified","delay-in-days":10,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Chronic Diseases-National Science and Technology Major Project of China","award":["2023ZD0509402"],"award-info":[{"award-number":["2023ZD0509402"]}]},{"DOI":"10.13039\/100000062","name":"National Institute of Diabetes and Digestive and Kidney Diseases","doi-asserted-by":"publisher","award":["1R01124789-01A1"],"award-info":[{"award-number":["1R01124789-01A1"]}],"id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CNS","award":["2052578"],"award-info":[{"award-number":["2052578"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82370903"],"award-info":[{"award-number":["82370903"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open Diab Res Care"],"accepted":{"date-parts":[[2025,10,21]]},"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Diabetic foot ulcer (DFU) is a severe complication of diabetes mellitus, often characterized by a chronic disease course and a high recurrence rate, posing significant challenges to patient management. Accurately predicting DFU recurrence is essential for enhancing patient care and outcomes through timely treatment and intervention. This study aimed to develop a machine learning (ML) model to predict the 3-year recurrence risk in patients with DFU.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 494 patients with DFU were included and assigned to a training set and a test set at a 4:1 ratio. Four feature selection methods\u2014least absolute shrinkage and selection operator, minimum redundancy maximum relevance, Fisher score and recursive feature elimination\u2014were applied to the training set, and intersecting features were selected to construct the final feature set. Seven ML algorithms, including logistic regression, support vector machine, random forest, gradient boosting decision tree, AdaBoost, extreme gradient boosting (XGBoost) and light gradient boosting machine, were employed to develop predictive models. The models\u2019 parameters were optimized using fivefold cross-validation. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC). The best-performing model was calibrated using Platt scaling, with calibration performance assessed by the Brier score. ML model interpretability was enhanced using SHapley Additive exPlanations (SHAP) analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The XGBoost model demonstrated superior predictive performance, achieving an AUROC of 0.924 (95% CI 0.867 to 0.967). Following calibration with Platt scaling, the model exhibited a Brier score of 0.096, indicating good calibration. SHAP analysis identified key risk factors that aligned with existing literature and clinical expertise, further validating the model\u2019s interpretability and clinical relevance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The XGBoost model demonstrated strong predictive accuracy and clinical relevance in assessing DFU recurrence risk. However, further multicenter validation with a larger sample size is needed to improve its generalizability and clinical applicability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjdrc-2025-005242","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T06:05:11Z","timestamp":1763013911000},"page":"e005242","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":7,"title":["Interpretable machine learning model for predicting recurrence in patients with diabetic foot ulcers"],"prefix":"10.1136","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7329-9449","authenticated-orcid":false,"given":"Weijiao","family":"Mou","sequence":"first","affiliation":[{"name":"Department of Endocrinology, School of Medicine, Chongqing University Central Hospital, Chongqing Emergency Medical Centre, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Waiping","family":"Shan","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, School of Medicine, Chongqing University Central Hospital, Chongqing Emergency Medical Centre, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9371-5827","authenticated-orcid":false,"given":"Shiyan","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, School of Medicine, Chongqing University Central Hospital, Chongqing Emergency Medical Centre, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunli","family":"Rui","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, School of Medicine, Chongqing University Central Hospital, Chongqing Emergency Medical Centre, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenzhen","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, School of Medicine, Chongqing University Central Hospital, Chongqing Emergency Medical Centre, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Huo","sequence":"additional","affiliation":[{"name":"Wolfson Institute of Population Health, Queen Mary University of London, London, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotian","family":"Gu","sequence":"additional","affiliation":[{"name":"British Heart Foundation, King\u2019s College London, London, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David G","family":"Armstrong","sequence":"additional","affiliation":[{"name":"Department of Surgery, Keck School of Medicine of University of Southern California, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongfeng","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Life Course & Population Sciences, King\u2019s College London, London, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Life Course & Population Sciences, King\u2019s College London, London, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salma","family":"Ayis","sequence":"additional","affiliation":[{"name":"Faculty of Life Sciences & Medicine, King\u2019s College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Chen","sequence":"additional","affiliation":[{"name":"Health Studies Research, Methodologies, Florence Nightingale Faculty of Nursing, Midwifery & Palliative Care, King's College London, London, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, School of Medicine, Chongqing University Central Hospital, Chongqing Emergency Medical Centre, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4172-4571","authenticated-orcid":false,"given":"Wuquan","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, School of Medicine, Chongqing University Central Hospital, Chongqing Emergency Medical Centre, Chongqing University, Chongqing, China"},{"name":"School of Life Course & Population Sciences, King\u2019s College London, London, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"2025111222050771000_13.6.e005242.1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.10578"},{"key":"2025111222050771000_13.6.e005242.2","first-page":"0702","article-title":"Forecasting the Global Burden of Peripheral Artery Disease from 2021 to 2050: A Population-Based Study","volume":"8","author":"Deng","year":"2025","journal-title":"Research (Lambertville)"},{"key":"2025111222050771000_13.6.e005242.3","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1016\/j.reth.2025.02.005","article-title":"Platelet concentrates in diabetic foot ulcers: A comparative review of PRP, PRF, and CGF with case insights","volume":"28","author":"Yang","year":"2025","journal-title":"Regen Ther"},{"key":"2025111222050771000_13.6.e005242.4","doi-asserted-by":"publisher","DOI":"10.1080\/07853890.2016.1231932"},{"key":"2025111222050771000_13.6.e005242.5","doi-asserted-by":"crossref","DOI":"10.1136\/bmjdrc-2021-002593","article-title":"Custom-made footwear designed for indoor use increases short-term and long-term adherence in people with diabetes at high ulcer risk","volume":"10","author":"Keukenkamp","year":"2022","journal-title":"BMJ Open Diabetes Res Care"},{"key":"2025111222050771000_13.6.e005242.6","doi-asserted-by":"crossref","DOI":"10.1002\/dmrr.3657","article-title":"Practical guidelines on the prevention and management of diabetes-related foot disease (IWGDF 2023 update)","volume":"40","author":"Schaper","year":"2024","journal-title":"Diabetes Metab Res Rev"},{"key":"2025111222050771000_13.6.e005242.7","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1053\/j.semvascsurg.2012.05.002","article-title":"Prevention: Can We Stop Problems Before They Arise?","volume":"25","author":"Rhim","year":"2012","journal-title":"Semin Vasc Surg"},{"key":"2025111222050771000_13.6.e005242.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvs.2010.06.003"},{"key":"2025111222050771000_13.6.e005242.9","doi-asserted-by":"crossref","first-page":"1581403","DOI":"10.3389\/fendo.2025.1581403","article-title":"Novel glucose-lowering agents that benefit diabetic foot: icing on the cake","volume":"16","author":"Li","year":"2025","journal-title":"Front Endocrinol"},{"key":"2025111222050771000_13.6.e005242.10","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-008-1089-6"},{"key":"2025111222050771000_13.6.e005242.11","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1615439"},{"key":"2025111222050771000_13.6.e005242.12","doi-asserted-by":"publisher","DOI":"10.1111\/dme.13973"},{"key":"2025111222050771000_13.6.e005242.13","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1002\/dmrr.2245","article-title":"Cost of treating diabetic foot ulcers in five different countries","volume":"28 Suppl 1","author":"Cavanagh","year":"2012","journal-title":"Diabetes Metab Res Rev"},{"key":"2025111222050771000_13.6.e005242.14","doi-asserted-by":"crossref","DOI":"10.1002\/dmrr.3652","article-title":"Prevention of foot ulcers in persons with diabetes at risk of ulceration: A systematic review and meta-analysis","volume":"40","author":"van Netten","year":"2024","journal-title":"Diabetes Metab Res Rev"},{"key":"2025111222050771000_13.6.e005242.15","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1111\/iwj.13691","article-title":"An explainable machine learning model for predicting in\u2010hospital amputation rate of patients with diabetic foot ulcer","volume":"19","author":"Xie","year":"2022","journal-title":"Int Wound J"},{"key":"2025111222050771000_13.6.e005242.16","doi-asserted-by":"crossref","DOI":"10.1186\/s13098-023-01020-1","article-title":"Mortality prediction in patients with hyperglycaemic crisis using explainable machine learning: a prospective, multicentre study based on tertiary hospitals","volume":"15","author":"Xie","year":"2023","journal-title":"Diabetol Metab Syndr"},{"key":"2025111222050771000_13.6.e005242.17","doi-asserted-by":"crossref","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":"2025111222050771000_13.6.e005242.18","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.jconrel.2024.06.050","article-title":"Exosomal miRNA-26b-5p from PRP suppresses NETs by targeting MMP-8 to promote diabetic wound healing","volume":"372","author":"Rui","year":"2024","journal-title":"J Control Release"},{"key":"2025111222050771000_13.6.e005242.19","doi-asserted-by":"crossref","first-page":"155990","DOI":"10.1016\/j.phymed.2024.155990","article-title":"Accelerating diabetic wound healing with Ramulus Mori (Sangzhi) alkaloids via NRF2\/HO-1\/eNOS pathway","volume":"134","author":"Xiao","year":"2024","journal-title":"Phytomedicine"},{"key":"2025111222050771000_13.6.e005242.20","doi-asserted-by":"publisher","DOI":"10.1097\/hco.0000000000000812"},{"key":"2025111222050771000_13.6.e005242.21","first-page":"657","article-title":"Predictive Factors and Nomogram for 30-Day Mortality in Heatstroke Patients: A Retrospective Cohort Study","volume":"26","author":"Li","year":"2025","journal-title":"West J Emerg Med"},{"key":"2025111222050771000_13.6.e005242.22","doi-asserted-by":"publisher","DOI":"10.4097\/kjae.2013.64.5.402"},{"key":"2025111222050771000_13.6.e005242.23","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-49539-6","article-title":"Efficient partition of integer optimization problems with one-hot encoding","volume":"9","author":"Okada","year":"2019","journal-title":"Sci Rep"},{"key":"2025111222050771000_13.6.e005242.24","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/17.6.520"},{"key":"2025111222050771000_13.6.e005242.25","first-page":"851","article-title":"Performance comparison between Logistic regression, decision trees, and multilayer perceptron in predicting peripheral neuropathy in type 2 diabetes mellitus","volume":"125","author":"Li","year":"2012","journal-title":"Chin Med J (Engl)"},{"key":"2025111222050771000_13.6.e005242.26","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1214\/aos\/1016218223","article-title":"Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)","volume":"28","author":"Friedman","year":"2000","journal-title":"Ann Statist"},{"key":"2025111222050771000_13.6.e005242.27","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1214\/ss\/1009213726","article-title":"Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)","volume":"16","author":"Breiman","year":"2001","journal-title":"Statist Sci"},{"key":"2025111222050771000_13.6.e005242.28","unstructured":"Ke G , Meng Q , Finley T , et al . LightGBM: a highly efficient gradient boosting decision tree. Presented at: 31st International Conference on Neural Information Processing Systems; Long Beach, United States, 2017 Available: https:\/\/hal.science\/hal-03953007"},{"key":"2025111222050771000_13.6.e005242.29","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0184129","article-title":"Prediction and analysis of essential genes using the enrichments of gene ontology and KEGG pathways","volume":"12","author":"Chen","year":"2017","journal-title":"PLoS One"},{"key":"2025111222050771000_13.6.e005242.30","doi-asserted-by":"crossref","DOI":"10.3389\/fgene.2020.605012","article-title":"Identification of Gene Signatures and Expression Patterns During Epithelial-to-Mesenchymal Transition From Single-Cell Expression Atlas","volume":"11","author":"Yu","year":"2020","journal-title":"Front Genet"},{"key":"2025111222050771000_13.6.e005242.31","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s41417-019-0105-y","article-title":"Identification of leukemia stem cell expression signatures through Monte Carlo feature selection strategy and support vector machine","volume":"27","author":"Li","year":"2020","journal-title":"Cancer Gene Ther"},{"key":"2025111222050771000_13.6.e005242.32","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1016\/j.procs.2022.12.044","article-title":"A Comparative Analysis of Machine Learning Algorithms for Classification Purpose","volume":"215","author":"Sheth","year":"2022","journal-title":"Procedia Comput Sci"},{"key":"2025111222050771000_13.6.e005242.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2025111222050771000_13.6.e005242.34","doi-asserted-by":"crossref","DOI":"10.1093\/burnst\/tkae052","article-title":"Angiogenesis during diabetic wound repair: from mechanism to therapy opportunity","volume":"13","author":"Huang","year":"2025","journal-title":"Burns Trauma"},{"key":"2025111222050771000_13.6.e005242.35","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1177\/19322968241253568","article-title":"Building Trustworthy Generative Artificial Intelligence for Diabetes Care and Limb Preservation: A Medical Knowledge Extraction Case","volume":"19","author":"Mashatian","year":"2025","journal-title":"J Diabetes Sci Technol"},{"key":"2025111222050771000_13.6.e005242.36","doi-asserted-by":"publisher","DOI":"10.1152\/ajpheart.00595.2018"},{"key":"2025111222050771000_13.6.e005242.37","doi-asserted-by":"publisher","DOI":"10.1089\/ars.2008.2220"},{"key":"2025111222050771000_13.6.e005242.38","doi-asserted-by":"publisher","DOI":"10.1111\/j.1742-481X.2012.01022.x"},{"key":"2025111222050771000_13.6.e005242.39","doi-asserted-by":"crossref","DOI":"10.1093\/burnst\/tkad003","article-title":"Sphingosine-1-phosphate derived from PRP-Exos promotes angiogenesis in diabetic wound healing via the S1PR1\/AKT\/FN1 signalling pathway","volume":"11","author":"Chen","year":"2023","journal-title":"Burns Trauma"},{"key":"2025111222050771000_13.6.e005242.40","doi-asserted-by":"crossref","first-page":"e232","DOI":"10.1161\/CIR.0000000000001192","article-title":"Current Status and Principles for the Treatment and Prevention of Diabetic Foot Ulcers in the Cardiovascular Patient Population: A Scientific Statement From the American Heart Association","volume":"149","author":"Gallagher","year":"2024","journal-title":"Circulation"},{"key":"2025111222050771000_13.6.e005242.41","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s12020-020-02431-0","article-title":"Predictors of healing, ulcer recurrence and persistence, amputation and mortality in type 2 diabetic patients with diabetic foot: a 10-year retrospective cohort study","volume":"71","author":"Gazzaruso","year":"2021","journal-title":"Endocrine"},{"key":"2025111222050771000_13.6.e005242.42","doi-asserted-by":"crossref","first-page":"2304023","DOI":"10.1080\/10641963.2024.2304023","article-title":"A smartwatch sphygmomanometer-based model for predicting short-term new-onset hypertension in individuals with high-normal blood pressure: a cohort study","volume":"46","author":"Liu","year":"2024","journal-title":"Clin Exp Hypertens"},{"key":"2025111222050771000_13.6.e005242.43","doi-asserted-by":"crossref","DOI":"10.1002\/dmrr.3651","article-title":"Guidelines on the prevention of foot ulcers in persons with diabetes (IWGDF 2023 update)","volume":"40","author":"Bus","year":"2024","journal-title":"Diabetes Metabolism Res"},{"key":"2025111222050771000_13.6.e005242.44","doi-asserted-by":"crossref","first-page":"103","DOI":"10.2147\/DMSO.S341364","article-title":"Custom-Molded Offloading Footwear Effectively Prevents Recurrence and Amputation, and Lowers Mortality Rates in High-Risk Diabetic Foot Patients: A Multicenter, Prospective Observational Study","volume":"15","author":"Zhang","year":"2022","journal-title":"Diabetes Metab Syndr Obes"},{"key":"2025111222050771000_13.6.e005242.45","doi-asserted-by":"crossref","DOI":"10.1136\/bmjdrc-2021-002257","article-title":"Development of a prediction model for foot ulcer recurrence in people with diabetes using easy-to-obtain clinical variables","volume":"9","author":"Aan de Stegge","year":"2021","journal-title":"BMJ Open Diabetes Res Care"},{"key":"2025111222050771000_13.6.e005242.46","unstructured":"Wang Y , Qiu X , Pan L . Development of A Prediction model for recurrence of healing diabetic foot ulcer. Military Nursing 2023. doi:10.3969\/j.issn.2097-1826.2023.05.015"},{"key":"2025111222050771000_13.6.e005242.47","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1177\/17085381211040984","article-title":"Machine learning prediction of diabetic foot ulcers in the inpatient population","volume":"30","author":"Stefanopoulos","year":"2022","journal-title":"Vascular"},{"key":"2025111222050771000_13.6.e005242.48","doi-asserted-by":"crossref","first-page":"3347","DOI":"10.2147\/DMSO.S383960","article-title":"Machine Learning Models for Predicting the Risk of Hard-to-Heal Diabetic Foot Ulcers in a Chinese Population","volume":"15","author":"Wang","year":"2022","journal-title":"Diabetes Metab Syndr Obes"},{"key":"2025111222050771000_13.6.e005242.49","first-page":"4013","article-title":"Construction of Recurrence Risk Prediction Model for Diabetic Foot Ulcer on the Basis of Logistic Regression, Support Vector Machine and BP Neural Network Model","volume":"26","author":"Juan","year":"2023","journal-title":"Chinese General Practice"},{"key":"2025111222050771000_13.6.e005242.50","doi-asserted-by":"crossref","unstructured":"Rui S , Xiao F , Li Q , et al . PPARs Mediated Diabetic Wound Healing Regulates Endothelial Cells Mitochondrial Function via Sonic Hedgehog Signaling. Burns Trauma 2025;, tkaf063,. doi:10.1093\/burnst\/tkaf063","DOI":"10.1093\/burnst\/tkaf063"}],"container-title":["BMJ Open Diabetes Research &amp; Care"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjdrc-2025-005242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T06:05:18Z","timestamp":1763013918000},"score":1,"resource":{"primary":{"URL":"https:\/\/drc.bmj.com\/lookup\/doi\/10.1136\/bmjdrc-2025-005242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":50,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,11,12]]},"published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1136\/bmjdrc-2025-005242"],"URL":"https:\/\/doi.org\/10.1136\/bmjdrc-2025-005242","relation":{},"ISSN":["2052-4897"],"issn-type":[{"value":"2052-4897","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}