{"title":"A Machine Learning Model for Predicting Diabetic Nephropathy Based on TG/Cys-C Ratio and Five Clinical Indicators.","authors":"Dongmei Zhou, Lingyu Shao, Libo Yang, Yongkang Chen, Yue Zhang, Feng Yue, Weipeng Gu, Shuyi Li, Shuyan Li, Jing Wei","doi":"10.2147/DMSO.S502649","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Distinguishing diabetic nephropathy (DN) from non-diabetic renal disease (NDRD) remains challenging. This study developed and validated a machine learning model for differential diagnosis of DN and NDRD.</p><p><strong>Methods: </strong>We included 100 type 2 diabetes mellitus (T2DM) patients with proteinuria from four Xuzhou hospitals (2013-2021), divided into DN (n=50) and NDRD (n=50) groups based on renal biopsy. Clinical data were used to build a predictive model. External validation was performed on 55 patients from The Affiliated Taian City Central Hospital of Qingdao University (2019-2023). Models were constructed using Python's scikit-learn library (v1.4.2), with feature selection via Recursive Feature Elimination (RFE).</p><p><strong>Results: </strong>Compared to NDRD, DN patients had lower TG/Cys-c ratio [1.45 (0.75, 1.99) vs 2.78 (1.81, 4.48)], higher systolic blood pressure (156.80 ± 20.14 vs 137.66 ± 17.67), longer diabetes duration [78 (24, 120) vs 18 (6, 48) months], higher diabetic retinopathy prevalence (60% vs 40%), higher HbA1c [7.98 (6.50, 10.40) vs 7.10 (6.70, 7.90)], and lower hemoglobin (115.66 ± 22.20 vs 135.64 ± 18.59). The logistic regression (LR) model, incorporating TG/Cys-c ratio, SBP, diabetes duration, DR, HbA1c, and Hb, achieved an AUC of 0.9305, accuracy of 0.8333, sensitivity of 0.8283, and specificity of 0.8701. External validation showed an AUC of 0.9642, accuracy of 0.9455, sensitivity of 0.9615, and specificity of 0.9310. We named this method PDN (Prediction of Diabetic Nephropathy) and developed an online platform: http://cppdd.cn/service/PDN.</p><p><strong>Conclusion: </strong>This machine learning-based method effectively differentiates DN from NDRD, aiding clinicians in diagnosis and treatment planning.</p>","PeriodicalId":11116,"journal":{"name":"Diabetes, Metabolic Syndrome and Obesity: Targets and Therapy","volume":"18 ","pages":"955-967"},"PeriodicalIF":3.0000,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11970525/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Diabetes, Metabolic Syndrome and Obesity: Targets and Therapy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2147/DMSO.S502649","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0
Abstract
Objective: Distinguishing diabetic nephropathy (DN) from non-diabetic renal disease (NDRD) remains challenging. This study developed and validated a machine learning model for differential diagnosis of DN and NDRD.
Methods: We included 100 type 2 diabetes mellitus (T2DM) patients with proteinuria from four Xuzhou hospitals (2013-2021), divided into DN (n=50) and NDRD (n=50) groups based on renal biopsy. Clinical data were used to build a predictive model. External validation was performed on 55 patients from The Affiliated Taian City Central Hospital of Qingdao University (2019-2023). Models were constructed using Python's scikit-learn library (v1.4.2), with feature selection via Recursive Feature Elimination (RFE).
Results: Compared to NDRD, DN patients had lower TG/Cys-c ratio [1.45 (0.75, 1.99) vs 2.78 (1.81, 4.48)], higher systolic blood pressure (156.80 ± 20.14 vs 137.66 ± 17.67), longer diabetes duration [78 (24, 120) vs 18 (6, 48) months], higher diabetic retinopathy prevalence (60% vs 40%), higher HbA1c [7.98 (6.50, 10.40) vs 7.10 (6.70, 7.90)], and lower hemoglobin (115.66 ± 22.20 vs 135.64 ± 18.59). The logistic regression (LR) model, incorporating TG/Cys-c ratio, SBP, diabetes duration, DR, HbA1c, and Hb, achieved an AUC of 0.9305, accuracy of 0.8333, sensitivity of 0.8283, and specificity of 0.8701. External validation showed an AUC of 0.9642, accuracy of 0.9455, sensitivity of 0.9615, and specificity of 0.9310. We named this method PDN (Prediction of Diabetic Nephropathy) and developed an online platform: http://cppdd.cn/service/PDN.
Conclusion: This machine learning-based method effectively differentiates DN from NDRD, aiding clinicians in diagnosis and treatment planning.
目的：区分糖尿病肾病（DN）与非糖尿病肾病（NDRD）仍然具有挑战性。本研究开发并验证了DN和NDRD鉴别诊断的机器学习模型。方法：选取徐州四所医院2013-2021年收治的2型糖尿病（T2DM）蛋白尿患者100例，根据肾活检分为DN组（n=50）和NDRD组（n=50）。利用临床资料建立预测模型。对2019-2023年青岛大学附属泰安市中心医院55例患者进行外部验证。使用Python的scikit-learn库（v1.4.2）构建模型，通过递归特征消除（RFE）进行特征选择。结果：与NDRD相比，DN患者TG/Cys-c比值较低[1.45 (0.75,1.99)vs 2.78(1.81, 4.48)]，收缩压较高（156.80±20.14 vs 137.66±17.67），糖尿病病程较长[78 (24,120)vs 18（6,48）个月]，糖尿病视网膜病变患病率较高（60% vs 40%）， HbA1c较高[7.98 (6.50,10.40)vs 7.10(6.70, 7.90)]，血红蛋白较低（115.66±22.20 vs 135.64±18.59）。纳入TG/Cys-c比值、收缩压、糖尿病病程、DR、HbA1c和Hb的logistic回归（LR）模型的AUC为0.9305，准确度为0.8333，敏感性为0.8283，特异性为0.8701。外部验证的AUC为0.9642，准确度为0.9455，灵敏度为0.9615，特异性为0.9310。我们将这种方法命名为PDN （Prediction of diabetes Nephropathy，糖尿病肾病预测），并开发了一个在线平台：http://cppdd.cn/service/PDN.Conclusion。这种基于机器学习的方法可以有效区分DN和NDRD，帮助临床医生进行诊断和治疗计划。
期刊介绍：
An international, peer-reviewed, open access, online journal. The journal is committed to the rapid publication of the latest laboratory and clinical findings in the fields of diabetes, metabolic syndrome and obesity research. Original research, review, case reports, hypothesis formation, expert opinion and commentaries are all considered for publication.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
