RDDI Screening: A Noninvasive Pathological Prediction Model in Chronic Kidney Diseases

Abstract

Here, we proposed a predictive model of discriminating pathological types in chronic kidney diseases (CKD) patients with mild lesion in glomeruli (ML), focal segmental glomerulosclerosis (FSGS), membranous nephropathy (MN) or immunoglobulin A nephropathy (IgA) based on the previous study. In the model, a statistical function defined as renal diseases development index (RDDI) was introduced, and was calculated by the first onset age X (Duration+Compensation Duration) X adjustment coefficient in CKD patient, used to screen preliminarily pathological types of CKD patients. Based on the screening of RDDI, another differential judgement model proposed by the previous study was combined to establish a predictive model of noninvasive judgement in CKD pathological types. Intriguingly, the predictive model showed higher identification efficiency and better availability than the previous study, especially for the discrimination of FSGS type. In conclusion, the model of RDDI screening provides an alternative reference of statistical predicting CKD pathological types when renal puncture is unfeasible. Funding: This work was sponsored by “Big Data of Chronic Kidney Diseases” Project of Central South University (2013-2018), Natural Science Foundations of China (Grant: 81430077, U1812403). Declaration of Interest: The authors declare that they have no competing interests. Ethical Approval: The study is classified as a exploration of statistical method and is approved by medical ethics committee of the Second Xiangya Hospital in China.