{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T14:30:03Z","timestamp":1779114603593,"version":"3.51.4"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Diabetic foot (DF) is one of the most severe complications of type 2 diabetes mellitus (T2DM), contributing to over 85% of diabetes-related lower limb amputations and a 5-year mortality rate comparable to certain cancers. Current diagnostic approaches face challenges including over-reliance on single-indicator screening, limited multimodal data integration, and lack of model interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A dataset integrating five modalities-sociodemographic characteristics, physiological indicators, traditional Chinese medicine (TCM) tongue features, plantar hardness metrics, and laboratory biomarkers-was prospectively collected from 391 patients (124 T2DM, 267 DF) at a single tertiary hospital between May 2019 and October 2022. The final model was constructed using 18 clinical features from sociodemographic, physiological, and laboratory modalities. Seven machine learning algorithms were developed and compared, and SHapley Additive exPlanations (SHAP) were used for interpretability analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>LightGBM achieved optimal performance (accuracy: 88.61%, sensitivity: 87.76%, specificity: 90.00%, AUC: 0.9519). Key classification features included age, body mass index (BMI), creatinine (Cr), white blood cell count (WBC), and uric acid (UA).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These features reflect general systemic inflammation, metabolic burden, and renal function rather than DF-specific pathology. The study contributes (1) an open-source multimodal DF dataset bridging TCM and Western medicine, (2) a classification tool that distinguishes DF from uncomplicated T2DM with reasonable accuracy as a potential supplementary screening instrument pending external validation, and (3) novel mechanistic insights suggesting that systemic inflammatory markers may play an important role in DF pathophysiology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1806349","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T13:40:51Z","timestamp":1779111651000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development of a machine learning-based classification model for diabetic foot in patients with type 2 diabetes: an exploratory analysis with SHAP interpretation"],"prefix":"10.3389","volume":"13","author":[{"given":"Yuting","family":"Pei","sequence":"first","affiliation":[{"name":"School of Rehabilitation Medicine, Qilu Medical University","place":["Zibo, Shandong, China"]},{"name":"Faculty of Information Measurement and Biotechnical Systems, Saint Petersburg Electrotechnical University \u201cLETI\u201d","place":["Saint Petersburg, Russia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Mathematical Game Theory and Statistical Solutions, Saint Petersburg State University","place":["Saint Petersburg, Russia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianglan","family":"Hu","sequence":"additional","affiliation":[{"name":"Obstetrics and Gynecology Department, Zhoucun District People's Hospital","place":["Zibo, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianshi","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Rehabilitation Medicine, Qilu Medical University","place":["Zibo, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengjun","family":"Liu","sequence":"additional","affiliation":[{"name":"Measurement and Sensor Technology, Chemnitz University of Technology","place":["Chemnitz, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Asia-Pacific AI Research Center, Asian Business Research Institute","place":["Hong Kong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanqing","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Rehabilitation Medicine, Qilu Medical University","place":["Zibo, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Rehabilitation Medicine, Qilu Medical University","place":["Zibo, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhikui","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Rehabilitation Medicine, Qilu Medical University","place":["Zibo, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"S71","DOI":"10.1002\/1520-7560(200009\/10)16:1+<::AID-DMRR139>3.3.CO;2-#","article-title":"The burden of diabetic foot ulcers","volume":"16","author":"Apelqvist","year":"2000","journal-title":"Diab Metab Res Rev"},{"key":"B2","doi-asserted-by":"publisher","first-page":"107843","DOI":"10.1016\/j.diabres.2019.107843","article-title":"Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: results from the International Diabetes Federation Diabetes Atlas","volume":"157","author":"Saeedi","year":"2019","journal-title":"Diab Res Clin Pract"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.2337\/diacare.28.8.2064","article-title":"Diabetic foot ulcers and neuropathy: a comprehensive overview","volume":"28","author":"Boulton","year":"2005","journal-title":"Diabetes Care"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1056\/NEJMcp1103615","article-title":"Clinical practice: diabetic foot ulcers","volume":"363","author":"Armstrong","year":"2011","journal-title":"N Engl J Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1679","DOI":"10.2337\/dc08-9021","article-title":"Comprehensive foot examination and risk assessment: a report of the task force of the foot care interest group of the American Diabetes Association","volume":"31","author":"Boulton","year":"2008","journal-title":"Diab Care"},{"key":"B6","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1080\/07853890.2016.1231932","article-title":"Global epidemiology of diabetic foot ulceration: a systematic review and meta-analysis","volume":"49","author":"Zhang","year":"2017","journal-title":"Ann Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2367","DOI":"10.1056\/NEJMra1615439","article-title":"Diabetic foot ulcers and their recurrence","volume":"376","author":"Armstrong","year":"2017","journal-title":"N Engl J Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/j.idc.2012.05.002","article-title":"Diabetic foot infections: diagnosis and management","volume":"26","author":"Lipsky","year":"2012","journal-title":"Infect Dis Clin North Am"},{"key":"B9","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1177\/19322968221021109","article-title":"Machine learning approaches for predicting diabetic foot complications: a comparison of traditional and advanced models","volume":"17","author":"Patel","year":"2023","journal-title":"J Diabetes Sci Technol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"107824","DOI":"10.1016\/j.jdiacomp.2022.107824","article-title":"Application of machine learning models in predicting diabetic foot ulcers: a review","volume":"37","author":"Yin","year":"2023","journal-title":"J Diab Complic"},{"key":"B11","first-page":"3512178","article-title":"Risk factors for diabetic foot ulceration: a comprehensive review","volume":"2017","author":"Chavez","year":"2017","journal-title":"J Diab Res"},{"key":"B12","unstructured":"Explainable machine learning to predict the cost of capital\n          \n          \n            \n              Bussmann\n              N\n            \n            \n              Tanda\n              A\n            \n            \n              Yu\n              EP\n            \n          \n          40276493\n          SSRN Electron J.\n          \n          2022"},{"key":"B13","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1177\/1932296819898553","article-title":"Data-driven models for predicting diabetic foot ulcers: current challenges and opportunities","volume":"14","author":"Zhou","year":"2020","journal-title":"J Diab Sci Technol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1473659","DOI":"10.3389\/fphys.2024.1473659","article-title":"Predicting the diabetic foot in the population of type 2 diabetes mellitus from tongue images and clinical information using multi-modal deep learning","volume":"15","author":"Tian","year":"2024","journal-title":"Front Physiol"},{"key":"B15","first-page":"135","article-title":"Tongue color classification by using machine learning algorithms in traditional Chinese medicine","volume":"100","author":"Duan","year":"2018","journal-title":"Comput Biol Med"},{"key":"B16","first-page":"626","article-title":"method for the standardized acquisition and analysis of tongue images for diagnostic use in traditional Chinese medicine","volume":"44","author":"Su","year":"2011","journal-title":"J Biomed Inform"},{"key":"B17","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"B18","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"B19","doi-asserted-by":"publisher","first-page":"150","DOI":"10.54254\/2755-2721\/104\/20241154","article-title":"Comparative analysis of water applicability predictions explained by the LightGBM model using SHAP and LIME","volume":"104","author":"Zhang","year":"2024","journal-title":"Appl Comput Eng"},{"key":"B20","first-page":"3149","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS 2017)","author":"Ke","year":"2017"},{"key":"B21","article-title":"Interpretable machine learning","author":"Molnar","year":"2020","journal-title":"Lulu com"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"B23","doi-asserted-by":"publisher","first-page":"S17","DOI":"10.2337\/dc22-S002","volume":"45","year":"2022","journal-title":"Diab Care"},{"key":"B24","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.jimed.2021.07.003","article-title":"Guidelines for the diagnosis and treatment of diabetic foot in China","volume":"48","author":"Gu","year":"2020","journal-title":"Chin J Clin"},{"key":"B25","doi-asserted-by":"publisher","first-page":"89","DOI":"10.2337\/diaspect.26.2.89","article-title":"Diabetic neuropathy: the clinical spectrum and management","volume":"26","author":"Callaghan","year":"2013","journal-title":"Diabetes Spectrum"},{"key":"B26","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1016\/S0965-206X(05)51016-7","article-title":"The diabetic foot: a global view","volume":"22","author":"Boulton","year":"2005","journal-title":"Diab Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s00125-010-2000-4","article-title":"Diabetic neuropathy: challenges in diagnosis and management","volume":"54","author":"Ziegler","year":"2011","journal-title":"Diabetologia"},{"key":"B28","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.diabres.2004.03.016","article-title":"Diabetic neuropathy: a clinical perspective","volume":"66","author":"Vinik","year":"2004","journal-title":"Diab Res Clin Pract"},{"key":"B29","doi-asserted-by":"publisher","first-page":"S214","DOI":"10.2337\/diacare.28.2.S214","article-title":"Diabetic foot ulcers and neuropathy: a comprehensive overview","volume":"28","author":"Boulton","year":"2005","journal-title":"Diab Care"},{"key":"B30","doi-asserted-by":"publisher","first-page":"14","DOI":"10.2337\/dc06-1600","article-title":"Preventing diabetic foot ulcer recurrence in high-risk patients: use of temperature monitoring as a self-assessment tool","volume":"30","author":"Lavery","year":"2007","journal-title":"Diab Care"},{"key":"B31","doi-asserted-by":"publisher","first-page":"67579","DOI":"10.1109\/ACCESS.2020.2983074","article-title":"A survey of data preprocessing techniques for data mining","volume":"8","author":"Xia","year":"2020","journal-title":"IEEE Access"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1016\/S0895-4356(96)00236-3","article-title":"A simulation study of the number of events per variable in logistic regression analysis","volume":"49","author":"Peduzzi","year":"1996","journal-title":"J Clin Epidemiol"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1002\/sim.7992","article-title":"Minimum sample size for developing a multivariable prediction model: PART II - binary and time-to-event outcomes","volume":"38","author":"Riley","year":"2019","journal-title":"Stat Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"m441","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"B35","first-page":"338","article-title":"Estimating continuous distributions in Bayesian classifiers","volume-title":"Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence","author":"John","year":"1995"},{"key":"B36","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans Inform Theory"},{"key":"B37","first-page":"3","article-title":"Weighted k-nearest neighbor classification","volume-title":"Proceedings of the International Conference on Data Mining (ICDM)","author":"Basu","year":"2005"},{"key":"B38","volume-title":"Classification and Regression Trees","author":"Breiman","year":"1986"},{"key":"B39","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1002\/widm.1093","article-title":"Classification and regression trees","volume":"4","author":"Loh","year":"2014","journal-title":"Wiley Interdiscipl Rev: Data Min Knowl Discov"},{"key":"B40","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"B41","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s11749-016-0481-7","article-title":"random forest guided tour","volume":"25","author":"Biau","year":"2016","journal-title":"TEST"},{"key":"B42","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc: Ser B (Methodol)"},{"key":"B43","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"Hastie","year":"2009"},{"key":"B44","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat Soc: Ser B (Stat Methodol)"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"Friedman","year":"2010","journal-title":"J Stat Softw"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2019\/3761203","article-title":"LightGBM: an efficient gradient boosting algorithm for large-scale data mining tasks","volume":"2019","author":"Qian","year":"2019","journal-title":"Comput Intell Neurosci"},{"key":"B47","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"B48","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS 2017)","author":"Lundberg","year":"2017"},{"key":"B49","doi-asserted-by":"publisher","first-page":"103470","DOI":"10.1016\/j.redox.2024.103470","article-title":"Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants","volume":"79","author":"Qi","year":"2025","journal-title":"Redox Biol"},{"key":"B50","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/s10115-010-0399-9","article-title":"Explaining prediction models and individual predictions with feature contributions","volume":"34","author":"Strumbelj","year":"2010","journal-title":"Knowl Inf Syst"},{"key":"B51","first-page":"142","article-title":"Feature importance explanation using Shapley values in machine learning","volume":"27","author":"Chen","year":"2018","journal-title":"J Comput Sci"},{"key":"B52","first-page":"1509","article-title":"Consistent individualized feature attribution for tree ensembles","author":"Lundberg","year":"2018","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"B53","volume-title":"Interpretable Machine Learning: A Guide for Making Black Box Models Explainable","author":"Molnar","year":"2020"},{"key":"B54","first-page":"8745","article-title":"The many Shapley values for model explanation","author":"Sundararajan","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1806349\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T13:40:56Z","timestamp":1779111656000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1806349\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":54,"alternative-id":["10.3389\/fmed.2026.1806349"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1806349","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]},"article-number":"1806349"}}