{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T08:33:02Z","timestamp":1793781182538,"version":"4.6.1"},"reference-count":53,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"51","license":[{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hunan Provincial Department of Education Scientific Research Project","award":["22B0386"],"award-info":[{"award-number":["22B0386"]}]},{"name":"Hunan Province Traditional Chinese Medicine Research Project","award":["B2023043"],"award-info":[{"award-number":["B2023043"]}]},{"name":"Hunan University of Traditional Chinese Medicine Campus level Research Fund Project","award":["2022XJZKC004"],"award-info":[{"award-number":["2022XJZKC004"]}]}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,20]]},"abstract":"<jats:p>In order to take full advantage of traditional Chinese medicine (TCM) and western medicine, combined with machine learning technology, to study the risk factors and better risk prediction model of diabetic retinopathy (DR), and provide basis for the screening and treatment of it. Through a retrospective study of DR cases in the real world, the electronic medical records of patients who met screening criteria were collected. Moreover, Recursive Feature Elimination with Cross-Validation (RFECV) was used for feature selection. Then, the prediction model was built based on Gradient Boosting Machine (GBM) and it was compared with 4 other popular machine learning techniques, including Logistic Regression (LR), K-Nearest Neighbors (KNN), Random Forest, and Support Vector Machine (SVM). The models were evaluated with accuracy, precision, recall, F1 score, and area under the curve (AUC) value as indicators. In addition, grid search was used to optimize the model. To explain the results of the model more intuitively, the Shapley Additive exPlanation (SHAP) method was used. A total of 9034 type 2 diabetes mellitus (T2DM) patients meeting the screening criteria were included in this study, including 1118 patients with DR. 19 features were selected using RFECV in the model construction. We constructed 5 commonly used models, including GBM, LR, KNN, Random Forest, and SVM. By comparing model performance, GBM has the highest accuracy (0.85) and AUC value (0.934), which is the best prediction model. We also carried out hyperparameter optimization of grid search for this model, and the model accuracy reached 0.88, and the AUC value increased to 0.958. Through SHAP analysis, it was found that TCM syndrome types, albumin, low density lipoprotein, triglyceride, total protein, glycosylated hemoglobin were closely related to the increased risk of DR. It can be concluded that TCM syndrome type is the risk factor of DR. The GBM classifier based on grid search optimization, with relevant risk factors of TCM and western medicine as variables, can better predict the risk of DR.<\/jats:p>","DOI":"10.1097\/md.0000000000040896","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T20:04:20Z","timestamp":1734725060000},"page":"e40896","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":6,"title":["Risk prediction of integrated traditional Chinese and western medicine for diabetes retinopathy based on optimized gradient boosting classifier model"],"prefix":"10.1097","volume":"103","author":[{"given":"Li","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Chinese Medicine, Hunan University of Chinese Medicine, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4966-9488","authenticated-orcid":false,"given":"Lixuan","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Medicine, Hunan University of Chinese Medicine, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxuan","family":"Kuang","sequence":"additional","affiliation":[{"name":"Xiangtan Chinese Medicine Hospital, Xiangtan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijing","family":"Yang","sequence":"additional","affiliation":[{"name":"Hunan Provincial Key Laboratory for Prevention and Treatment of Ophthalmology and Otolaryngology Diseases with Chinese Medicine, Hunan University of Chinese Medicine, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Deng","sequence":"additional","affiliation":[{"name":"Hunan Provincial Key Laboratory for Prevention and Treatment of Ophthalmology and Otolaryngology Diseases with Chinese Medicine, Hunan University of Chinese Medicine, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Lu","sequence":"additional","affiliation":[{"name":"Hunan Provincial Engineering and Technological Research Center for Prevention and Treatment of Ophthalmology and Otolaryngology Diseases with Chinese Medicine and Protecting Visual Function, Hunan University of Chinese Medicine, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghua","family":"Peng","sequence":"additional","affiliation":[{"name":"Hunan Provincial Key Laboratory for Prevention and Treatment of Ophthalmology and Otolaryngology Diseases with Chinese Medicine, Hunan University of Chinese Medicine, Changsha, China"},{"name":"Hunan Provincial Engineering and Technological Research Center for Prevention and Treatment of Ophthalmology and Otolaryngology Diseases with Chinese Medicine and Protecting Visual Function, Hunan University of Chinese Medicine, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfeng","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Informatics, Hunan University of Chinese Medicine, Changsha, China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20250503","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1111\/jdi.13480","article-title":"Update in the epidemiology, risk factors, screening, and treatment of diabetic retinopathy.","volume":"12","author":"Lin","year":"2021","journal-title":"J Diabetes Investig"},{"key":"R2-20250503","doi-asserted-by":"crossref","first-page":"110852","DOI":"10.1016\/j.biopha.2020.110852","article-title":"A review of traditional Chinese medicine on treatment of diabetic retinopathy and involved mechanisms.","volume":"132","author":"Ai","year":"2020","journal-title":"Biomed Pharmacother"},{"key":"R3-20250503","doi-asserted-by":"crossref","first-page":"e19102","DOI":"10.1097\/MD.0000000000019102","article-title":"Traditional Chinese medicine for diabetic retinopathy: a systematic review and meta-analysis.","volume":"99","author":"Pang","year":"2020","journal-title":"Medicine (Baltimore)"},{"key":"R4-20250503","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.18240\/ijo.2021.08.18","article-title":"Visualizing the intellectual structure and recent research trends of diabetic retinopathy.","volume":"14","author":"Xiao","year":"2021","journal-title":"Int J Ophthalmol"},{"key":"R5-20250503","doi-asserted-by":"crossref","first-page":"773881","DOI":"10.3389\/fmed.2021.773881","article-title":"Usefulness of machine learning for identification of referable diabetic retinopathy in a large-scale population-based study.","volume":"8","author":"Yang","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"R6-20250503","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1186\/1472-6947-13-106","article-title":"Diabetic retinopathy risk prediction for fundus examination using sparse learning: a cross-sectional study.","volume":"13","author":"Oh","year":"2013","journal-title":"BMC Med Inform Decis Mak"},{"key":"R7-20250503","first-page":"983","article-title":"Machine learning approaches for detecting diabetic retinopathy from clinical and public health records.","volume":"2015","author":"Ogunyemi","year":"2015","journal-title":"AMIA Annu Symp Proc"},{"key":"R8-20250503","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1186\/s12859-018-2277-0","article-title":"Predicting diabetic retinopathy and identifying interpretable biomedical features using machine learning algorithms.","volume":"19","author":"Tsao","year":"2018","journal-title":"BMC Bioinf"},{"key":"R9-20250503","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/j.dcmed.2022.12.003","article-title":"Artificial intelligence and its application for cardiovascular diseases in Chinese medicine.","volume":"5","author":"Chen","year":"2022","journal-title":"Digit Chin Med"},{"key":"R10-20250503","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.3233\/JAD-201254","article-title":"Recursive support vector machine biomarker selection for Alzheimer\u2019s disease.","volume":"79","author":"Zhang","year":"2021","journal-title":"J Alzheimers Dis"},{"key":"R11-20250503","doi-asserted-by":"crossref","first-page":"105400","DOI":"10.1016\/j.cmpb.2020.105400","article-title":"Decision tree-based diagnosis of coronary artery disease: cart model.","volume":"192","author":"Ghiasi","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"R12-20250503","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1186\/s12911-019-0918-5","article-title":"A data-driven approach to predicting diabetes and cardiovascular disease with machine learning.","volume":"19","author":"Dinh","year":"2019","journal-title":"BMC Med Inform Decis Mak"},{"key":"R13-20250503","doi-asserted-by":"crossref","first-page":"22381","DOI":"10.1038\/s41598-022-26958-6","article-title":"A new strategy for the early detection of Alzheimer disease stages using multifractal geometry analysis based on K-nearest neighbor algorithm.","volume":"12","author":"Elgammal","year":"2022","journal-title":"Sci Rep"},{"key":"R14-20250503","first-page":"68","article-title":"A unified approach to interpreting model predictions.","volume":"47","author":"Lundberg","year":"2017","journal-title":"Can J Cardiol"},{"issue":"Suppl 1","key":"R15-20250503","doi-asserted-by":"crossref","first-page":"19","DOI":"10.2337\/dc23-S002","article-title":"2. Classification and diagnosis of diabetes: standards of care in diabetes-2023.","volume":"46","author":"ElSayed","year":"2023","journal-title":"Diabetes Care"},{"key":"R16-20250503","doi-asserted-by":"crossref","first-page":"08","DOI":"10.1016\/j.ophtha.2018.04.007","article-title":"Guidelines on diabetic eye care: the international council of ophthalmology recommendations for screening, follow-up, referral, and treatment based on resource settings.","volume":"125","author":"Wong","year":"2018","journal-title":"Ophthalmology"},{"key":"R17-20250503","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1016\/j.cjca.2020.11.010","article-title":"Missing data in clinical research: a tutorial on multiple imputation.","volume":"37","author":"Austin","year":"2021","journal-title":"Can J Cardiol"},{"key":"R18-20250503","doi-asserted-by":"crossref","first-page":"1528","DOI":"10.1109\/JBHI.2021.3107518","article-title":"Data pre-processing using neural processes for modeling personalized vital-sign time-series data.","volume":"26","author":"Sharma","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"R19-20250503","doi-asserted-by":"crossref","first-page":"7354081","DOI":"10.1155\/2018\/7354081","article-title":"Deep convolutional neural network based Ecg classification system using information fusion and one-hot encoding techniques.","volume":"2018","author":"Li","year":"2018","journal-title":"Math Probl Eng"},{"key":"R20-20250503","doi-asserted-by":"crossref","first-page":"042178","DOI":"10.1088\/1755-1315\/267\/4\/042178","article-title":"The research of BP neural network based on one-hot encoding and principle component analysis in determining the therapeutic effect of diabetes mellitus.","volume":"267","author":"Qiao","year":"2019","journal-title":"IOP Conf Ser: Earth Environ Sci"},{"key":"R22-20250503","first-page":"148","article-title":"Guide to traditional Chinese medicine prevention and treatment of diabetes (in Chinese).","volume":"9","author":"Tong","year":"2011","journal-title":"Chin Med Mod Distance Educ China"},{"key":"R23-20250503","doi-asserted-by":"crossref","first-page":"e050989","DOI":"10.1136\/bmjopen-2021-050989","article-title":"Predictive model and risk analysis for diabetic retinopathy using machine learning: a retrospective cohort study in China.","volume":"11","author":"Li","year":"2021","journal-title":"BMJ Open"},{"key":"R24-20250503","first-page":"86","article-title":"Establishment of a prognostic model for non-nephrotic membranous nephropathy based on unbalanced data.","volume":"103","author":"Liu","year":"2023","journal-title":"Zhonghua Yi Xue Za Zhi"},{"key":"R25-20250503","doi-asserted-by":"crossref","first-page":"2225","DOI":"10.1016\/j.patrec.2010.03.014","article-title":"Variable selection using random forests.","volume":"31","author":"Genuer","year":"2010","journal-title":"Pattern Recognit Lett"},{"key":"R26-20250503","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine.","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann Stat"},{"key":"R27-20250503","doi-asserted-by":"crossref","first-page":"9391136","DOI":"10.1155\/2022\/9391136","article-title":"Survival prediction of children undergoing hematopoietic stem cell transplantation using different machine learning classifiers by performing chi-square test and hyperparameter optimization: a retrospective analysis.","volume":"2022","author":"Ratul","year":"2022","journal-title":"Comput Math Methods Med"},{"key":"R28-20250503","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1038\/s41746-020-0222-x","article-title":"Lymelight: forecasting Lyme disease risk using web search data.","volume":"3","author":"Sadilek","year":"2020","journal-title":"NPJ Digit Med"},{"key":"R29-20250503","doi-asserted-by":"crossref","first-page":"3125","DOI":"10.3390\/jcm11113125","article-title":"Variability of grading DR screening images among non-trained retina specialists.","volume":"11","author":"Grzybowski","year":"2022","journal-title":"J Clin Med"},{"key":"R30-20250503","first-page":"731","article-title":"Soothing the liver and invigorating the spleen treating diabetes experience (in Chinese).","volume":"24","author":"Li","year":"2009","journal-title":"Guangming J Chin Med"},{"key":"R31-20250503","first-page":"1","article-title":"Research on the prevention and treatment of diabetic vasculopathy in traditional Chinese medicine (in Chinese).","volume":"34","author":"Fang","year":"2022","journal-title":"Clin J Tradit Chin Med"},{"key":"R32-20250503","first-page":"1652","article-title":"Clinical observation on Bushen Mingmu capsules for 40 cases of diabetic retinopathy (in Chinese).","volume":"55","author":"Zhang","year":"2014","journal-title":"J Tradit Chin Med"},{"key":"R33-20250503","first-page":"64","article-title":"Analysis of related factors of fundus lesions in early diabetic patients (in Chinese).","volume":"15","author":"Wu","year":"1999","journal-title":"Chin J Endocrinol Metab"},{"key":"R34-20250503","first-page":"110","article-title":"Treatment of diabetic nephropathy from theory of liver and kidney sharing the same origin (in Chinese).","volume":"40","author":"Yu","year":"2016","journal-title":"J Shandong Univ Tradit Chin Med"},{"key":"R35-20250503","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.immuni.2021.12.013","article-title":"Inflammation in obesity, diabetes, and related disorders.","volume":"55","author":"Rohm","year":"2022","journal-title":"Immunity"},{"key":"R36-20250503","first-page":"2058","article-title":"Yi and Gui are derived from the same origin: recognition of the integrated control measures for diabetic disease with eyes and kidney microangiopathy (in Chinese).","volume":"28","author":"Ma","year":"2013","journal-title":"China J Tradit Chin Med Pharm"},{"key":"R37-20250503","first-page":"34","article-title":"Observation of therapy for invigorating the kidney and clearing liver dispersing blood stasis and improving eyesight on diabetic retinopathy (in Chinese).","volume":"32","author":"Lian","year":"2010","journal-title":"Hebei J Tradit Chin Med"},{"key":"R38-20250503","first-page":"531","article-title":"Clinical research of efficacy of Spanish needles herb on non-proliferative diabetic retinopathy (in Chinese).","volume":"33","author":"Shao","year":"2013","journal-title":"Recent Adv Ophthalmol"},{"key":"R39-20250503","doi-asserted-by":"crossref","first-page":"279037","DOI":"10.1155\/2012\/279037","article-title":"Leukocyte adhesion molecules in diabetic retinopathy.","volume":"2012","author":"Noda","year":"2012","journal-title":"J Ophthalmol"},{"key":"R40-20250503","doi-asserted-by":"crossref","first-page":"564077","DOI":"10.3389\/fimmu.2020.564077","article-title":"Microglia and inflammatory responses in diabetic retinopathy.","volume":"11","author":"Kinuthia","year":"2020","journal-title":"Front Immunol"},{"key":"R41-20250503","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.jneuroim.2017.02.010","article-title":"Inhibition of AGEs\/RAGE\/Rho\/ROCK pathway suppresses non-specific neuroinflammation by regulating BV2 microglial M1\/M2 polarization through the NF-\u03baB pathway.","volume":"305","author":"Chen","year":"2017","journal-title":"J Neuroimmunol"},{"key":"R42-20250503","first-page":"794","article-title":"Correlation between TCM syndrome types of diabetic retinopathy and sensitive indexes of renal damage (in Chinese).","volume":"31","author":"Kang","year":"2021","journal-title":"China J Chin Ophthalmol"},{"key":"R43-20250503","first-page":"632","article-title":"Chinese medicine diagnosis and treatment criteria for diabetic retinopathy (in Chinese).","volume":"6","author":"Duan","year":"2011","journal-title":"World J Integr Tradit West Med"},{"key":"R44-20250503","doi-asserted-by":"crossref","first-page":"273","DOI":"10.4093\/dmj.2015.39.4.273","article-title":"Glycemic variability: how do we measure it and why is it important?","volume":"39","author":"Suh","year":"2015","journal-title":"Diabetes Metab J"},{"key":"R45-20250503","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1196\/annals.1333.090","article-title":"High-dose thiamine therapy counters dyslipidemia and advanced glycation of plasma protein in streptozotocin-induced diabetic rats.","volume":"1043","author":"Karachalias","year":"2005","journal-title":"Ann N Y Acad Sci"},{"key":"R46-20250503","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1111\/dom.13538","article-title":"Worsening of diabetic retinopathy with rapid improvement in systemic glucose control: a review.","volume":"21","author":"Bain","year":"2019","journal-title":"Diabetes Obes Metab"},{"key":"R47-20250503","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1016\/j.jdiacomp.2019.05.022","article-title":"Hba1c variability and long-term glycemic control are linked to diabetic retinopathy and glomerular filtration rate in patients with type 1 diabetes and multiethnic background.","volume":"33","author":"Rosa","year":"2019","journal-title":"J Diabetes Complications"},{"key":"R48-20250503","first-page":"13","article-title":"Prognostic factors for the development and progression of proliferative diabetic retinopathy in people with diabetic retinopathy.","volume":"2","author":"Perais","year":"2023","journal-title":"Cochrane Database Syst Rev"},{"key":"R49-20250503","doi-asserted-by":"crossref","first-page":"e0154411","DOI":"10.1371\/journal.pone.0154411","article-title":"The accuracy of diagnostic methods for diabetic retinopathy: a systematic review and meta-analysis.","volume":"11","author":"Mart\u00ednez-Vizca\u00edno","year":"2016","journal-title":"PLoS One"},{"issue":"Suppl 1","key":"R50-20250503","first-page":"14","article-title":"2. Classification and diagnosis of diabetes: standards of medical care in diabetes-2020.","volume":"43","year":"2020","journal-title":"Diabetes Care"},{"key":"R51-20250503","doi-asserted-by":"crossref","first-page":"e001387","DOI":"10.1136\/bmjdrc-2020-001387","article-title":"Socioeconomic deprivation and development of diabetic retinopathy in patients with type 1 diabetes mellitus.","volume":"8","author":"Alvarez-Ramos","year":"2020","journal-title":"BMJ Open Diabetes Res Care"},{"key":"R52-20250503","doi-asserted-by":"crossref","first-page":"2288","DOI":"10.1007\/s00125-011-2199-0","article-title":"Incidence and progression of diabetic retinopathy in Japanese adults with type 2 diabetes: 8 year follow-up study of the Japan diabetes complications study (JDCS).","volume":"54","author":"Kawasaki","year":"2011","journal-title":"Diabetologia"},{"key":"R53-20250503","doi-asserted-by":"crossref","first-page":"30","DOI":"10.2337\/dc16-0430","article-title":"Influence of Hba1c and BMI on lipid trajectories in youths and young adults with type 1 diabetes.","volume":"40","author":"Katz","year":"2017","journal-title":"Diabetes Care"},{"key":"R54-20250503","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1111\/jdi.13756","article-title":"Non\u2010alcoholic fatty liver disease and type 2 diabetes: an update.","volume":"13","author":"Lee","year":"2022","journal-title":"J Diabetes Investig"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000040896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T00:29:35Z","timestamp":1746318575000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000040896"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,20]]},"references-count":53,"journal-issue":{"issue":"51","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000040896","relation":{},"ISSN":["1536-5964"],"issn-type":[{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,20]]}}}