{"title":"A Klotho-based Machine Learning Model for Prediction of both Kidney and Cardiovascular Outcomes in Chronic Kidney Disease","authors":"Yating Wang, Yu Shi, Tangli Xiao, Xianjin Bi, Qingyu Huo, Shaobo Wang, Jiachuan Xiong, Jinghong Zhao","doi":"10.1159/000538510","DOIUrl":null,"url":null,"abstract":"Background: This study aimed to develop and validate a machine learning (ML) model based on serum Klotho for predicting end-stage kidney disease (ESKD) and cardiovascular disease (CVD) in patients with chronic kidney disease (CKD).\nMethods: Five different ML models were trained to predict the risk of ESKD and CVD at three different time points (3, 5, and 8-year) using a cohort of 400 non-dialysis CKD patients. The dataset was divided into a training set (70%) and an internal validation set (30%). These models were informed by data comprising 47 clinical features, including serum Klotho. The best-performing model was selected and used to identify risk factors for each outcome. Model performance was assessed using various metrics.\nResults: The findings showed that the Lasso regression model had the highest accuracy (C-index=0.71) in predicting ESKD. The features mainly included in this model were estimated glomerular filtration rate (eGFR), 24-hour urinary microalbumin, serum albumin, phosphate, parathyroid hormone, and serum Klotho, which achieved the highest area under the curve (AUC) of 0.930 (95% CI: 0.897-0.962). In addition, for the CVD risk prediction, the Random Survival Forest (RSF) model with the highest accuracy (C-index=0.66) was selected and achieved the highest AUC of 0.782 (95% CI: 0.633-0.930). The features mainly included in this model were age, history of primary hypertension, calcium, tumor necrosis factor-alpha, and serum Klotho.\nConclusion: We successfully developed and validated Klotho-based ML risk prediction models for CVD and ESKD in CKD patients with good performance, indicating their high clinical utility.","PeriodicalId":17830,"journal":{"name":"Kidney Diseases","volume":null,"pages":null},"PeriodicalIF":3.2000,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Kidney Diseases","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1159/000538510","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: This study aimed to develop and validate a machine learning (ML) model based on serum Klotho for predicting end-stage kidney disease (ESKD) and cardiovascular disease (CVD) in patients with chronic kidney disease (CKD).
Methods: Five different ML models were trained to predict the risk of ESKD and CVD at three different time points (3, 5, and 8-year) using a cohort of 400 non-dialysis CKD patients. The dataset was divided into a training set (70%) and an internal validation set (30%). These models were informed by data comprising 47 clinical features, including serum Klotho. The best-performing model was selected and used to identify risk factors for each outcome. Model performance was assessed using various metrics.
Results: The findings showed that the Lasso regression model had the highest accuracy (C-index=0.71) in predicting ESKD. The features mainly included in this model were estimated glomerular filtration rate (eGFR), 24-hour urinary microalbumin, serum albumin, phosphate, parathyroid hormone, and serum Klotho, which achieved the highest area under the curve (AUC) of 0.930 (95% CI: 0.897-0.962). In addition, for the CVD risk prediction, the Random Survival Forest (RSF) model with the highest accuracy (C-index=0.66) was selected and achieved the highest AUC of 0.782 (95% CI: 0.633-0.930). The features mainly included in this model were age, history of primary hypertension, calcium, tumor necrosis factor-alpha, and serum Klotho.
Conclusion: We successfully developed and validated Klotho-based ML risk prediction models for CVD and ESKD in CKD patients with good performance, indicating their high clinical utility.
期刊介绍:
''Kidney Diseases'' aims to provide a platform for Asian and Western research to further and support communication and exchange of knowledge. Review articles cover the most recent clinical and basic science relevant to the entire field of nephrological disorders, including glomerular diseases, acute and chronic kidney injury, tubulo-interstitial disease, hypertension and metabolism-related disorders, end-stage renal disease, and genetic kidney disease. Special articles are prepared by two authors, one from East and one from West, which compare genetics, epidemiology, diagnosis methods, and treatment options of a disease.