AUTHOR=Zhang WeiGuang , Liu XiaoMin , Dong ZheYi , Wang Qian , Pei ZhiYong , Chen YiZhi , Zheng Ying , Wang Yong , Chen Pu , Feng Zhe , Sun XueFeng , Cai Guangyan , Chen XiangMei 

TITLE=New Diagnostic Model for the Differentiation of Diabetic Nephropathy From Non-Diabetic Nephropathy in Chinese Patients

JOURNAL=Frontiers in Endocrinology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2022.913021

DOI=10.3389/fendo.2022.913021

ISSN=1664-2392

ABSTRACT=Background: The disease pathology for diabetes mellitus patients with chronic kidney disease (CKD) may be diabetic nephropathy (DN), non-diabetic renal disease (NDRD), or DN combined with NDRD. Considering that the prognosis and treatment of DN and NDRD differ, their differential diagnosis is of significance. Renal pathological biopsy is the gold standard for diagnosing DN and NDRD. However, it is invasive and cannot be implemented in many patients due to contraindications. This article aimed to construct a new noninvasive evaluation model for the differentiation of DN and NDRD. 
Methods: We retrospectively screened 1030 patients with type 2 diabetes who underwent kidney biopsy from January 2005 to March 2017 in single center. Variables were ranked according to importance, and the machine learning method (random forest, RF and support vector machine, SVM) were then used to construct the model. The final model was validated with an external group (338 patients, April 2017-April 2019).
Results: In total, 929 patients were assigned, 10 variables were selected for model development. The areas under the receiver operating characteristic curves (AUCROCs) for the RF and SVM methods were 0.953 and 0.947, respectively. Additionally, 329 patients were analyzed for external validation. The AUCROCs for the external validation of the RF and SVM methods were 0.920 and 0.911, respectively. 
Conclusion: We successfully constructed a predictive model for DN and NDRD using the machine learning methods, which were better than our regression methods.