Early prediction of end-stage kidney disease using electronic health record data: a machine learning approach with a 2-year horizon

Author:

Petousis Panayiotis1ORCID,Wilson James M2,Gelvezon Alex V3,Alam Shafiul3,Jain Ankur3,Prichard Laura3,Elashoff David A4,Raja Naveen5,Bui Alex A T6

Affiliation:

1. UCLA Health Clinical and Translational Science Institute, David Geffen School of Medicine, University of California Los Angeles (UCLA) , Los Angeles, CA 90024-2943, United States

2. Department of Medicine, David Geffen School of Medicine, University of California Los Angeles (UCLA) , Los Angeles, CA 90024-2943, United States

3. UCLA Health Office of Health Informatics and Analytics, David Geffen School of Medicine, University of California Los Angeles (UCLA) , Los Angeles, CA 90024-2943, United States

4. Biostatistics and Computational Medicine, University of California Los Angeles (UCLA) , Los Angeles, CA 90024-2943, United States

5. UCLA Health Faculty Practice Group and the Department of Medicine, David Geffen School of Medicine at University of California Los Angeles (UCLA) , Los Angeles, CA 90024-2943, United States

6. Medical & Imaging Informatics (MII) Group, Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles (UCLA) , Los Angeles, CA 90024-2943, United States

Abstract

Abstract Objectives In the United States, end-stage kidney disease (ESKD) is responsible for high mortality and significant healthcare costs, with the number of cases sharply increasing in the past 2 decades. In this study, we aimed to reduce these impacts by developing an ESKD model for predicting its occurrence in a 2-year period. Materials and Methods We developed a machine learning (ML) pipeline to test different models for the prediction of ESKD. The electronic health record was used to capture several kidney disease-related variables. Various imputation methods, feature selection, and sampling approaches were tested. We compared the performance of multiple ML models using area under the ROC curve (AUCROC), area under the Precision-Recall curve (PR-AUC), and Brier scores for discrimination, precision, and calibration, respectively. Explainability methods were applied to the final model. Results Our best model was a gradient-boosting machine with feature selection and imputation methods as additional components. The model exhibited an AUCROC of 0.97, a PR-AUC of 0.33, and a Brier score of 0.002 on a holdout test set. A chart review analysis by expert physicians indicated clinical utility. Discussion and Conclusion An ESKD prediction model can identify individuals at risk for ESKD and has been successfully deployed within our health system.

Funder

UCLA Health

David Geffen School of Medicine

UCLA Clinical and Translational Science Institute

Publisher

Oxford University Press (OUP)

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3