Nomogram for prediction of diabetic retinopathy in patients with type 2 diabetes mellitus: A retrospective study |
| |
| Institution: | 1. Department of Epidemiology and Statistics, School of Public Health, Lanzhou University, Lanzhou 730000, China;2. Hebei Province Key Laboratory of Basic Medicine for Diabetes/Shijiazhuang Second Hospital, Shijiazhuang 050051, China;1. Department of Endocrinology, Diabetes and Metabolic Disease, University Medical Centre Ljubljana, Zaloska 7, 1000 Ljubljana, Slovenia;2. Faculty of Medicine, University of Ljubljana, Vrazov trg 2, 1000 Ljubljana, Slovenia;3. School of Medicine, Department of Health Promotion, Mother and Child Care, Internal Medicine and Medical Specialties (Promise), University of Palermo, Italy;1. Department of Medicine, University Hospitals Cleveland Medical Center, Cleveland, OH, United States of America;2. Harrington Heart and Vascular Institute, University Hospitals Cleveland Medical Center, Cleveland, OH, United States of America;3. Houston Methodist Hospital, Houston, TX, United States of America;1. Department of Endocrinology, The First Hospital of Jilin University, Jilin, China;2. Department of Neurosurgery, The People''s Hospital of Jilin Province, Jilin, China;3. Sargodha Medical College, Sargodha, Punjab, Pakistan;1. Endocrinology, Diabetes and Metabolism Institute, Cleveland Clinic, Cleveland, OH 44195, United States of America;2. Quantitative Health Sciences, Cleveland Clinic, Cleveland, OH 44195, United States of America;1. Department of Internal Medicine, School of Health Sciences, Faculty of Medicine, University of Ioannina, Ioannina, Greece;2. Laboratory of Clinical Chemistry, School of Health Sciences, Faculty of Medicine, University of Ioannina, Ioannina, Greece;3. Department of Internal Medicine, General Hospital of Ioannina “G. Hatzikosta”, Ioannina, Greece;1. Reproductive Endocrinology Research Center, Research Institute for Endocrine Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran;3. Endocrine Research Center, Research Institute for Endocrine Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran |
| |
| Abstract: | ObjectiveTo develop a nomogram for the risk of diabetic retinopathy (DR) among type 2 diabetes mellitus (T2DM).MethodsQuestionnaires, physical examinations and biochemical tests were performed on 5900 T2DM patients in the Second Hospital of Shijiazhuang. The least absolute shrinkage and selection operator regression was used to optimize feature selection, and the importance of selected features was analyzed by random forest. Logistic regression was performed with selected features, and the nomogram was established based on the results. The Harrell's C-statistic, bootstrap-corrected C-statistic, area under curve (AUC), calibration curve, decision curve analysis (DCA) and clinical impact curve (CIC) were used to validate the discrimination, calibration and clinical usefulness of the nomogram, and further assessment was running by external validation.ResultsPredictors included duration of diabetes, diabetic neuropathy, diabetic kidney disease, diabetic foot, hyperlipidemia, hypoglycemic drugs, glycated albumin, Lactate dehydrogenase. The model displayed medium predictive power with a Harrell's C-statistic of 0.820, bootstrap-corrected C-statistic of 0.813 and AUC of 0.820 in the training set, and which was respectively 0.842, 0.835 and 0.842 in the validation set. The calibration curve displayed good agreement (P > 0.05). The DCA and CIC showed that the nomogram could be applied clinically if the risk threshold is between 2 % and 75 % and 2 %–88 % in validation set.ConclusionsThis nomogram incorporating 8 features is useful to predict the risk of DR in T2DM patients. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
