Machine Learning Prediction Models for Chronic Kidney Disease Using National Health Insurance Claim Data in Taiwan
Open Access
- 7 May 2021
- journal article
- research article
- Published by MDPI AG in Healthcare
- Vol. 9 (5), 546
- https://doi.org/10.3390/healthcare9050546
Abstract
Chronic kidney disease (CKD) represents a heavy burden on the healthcare system because of the increasing number of patients, high risk of progression to end-stage renal disease, and poor prognosis of morbidity and mortality. The aim of this study is to develop a machine-learning model that uses the comorbidity and medication data obtained from Taiwan’s National Health Insurance Research Database to forecast the occurrence of CKD within the next 6 or 12 months before its onset, and hence its prevalence in the population. A total of 18,000 people with CKD and 72,000 people without CKD diagnosis were selected using propensity score matching. Their demographic, medication and comorbidity data from their respective two-year observation period were used to build a predictive model. Among the approaches investigated, the Convolutional Neural Networks (CNN) model performed best with a test set AUROC of 0.957 and 0.954 for the 6-month and 12-month predictions, respectively. The most prominent predictors in the tree-based models were identified, including diabetes mellitus, age, gout, and medications such as sulfonamides and angiotensins. The model proposed in this study could be a useful tool for policymakers in predicting the trends of CKD in the population. The models can allow close monitoring of people at risk, early detection of CKD, better allocation of resources, and patient-centric management.Funding Information
- H2020 Health (727560)
- ARRS (P2-0209)
- Ministry of Science and Technology, Taiwan (106-3805-018-110)
This publication has 22 references indexed in Scilit:
- XGBoostPublished by Association for Computing Machinery (ACM) ,2016
- Present Status of Renal Replacement Therapy in Asian CountriesBlood Purification, 2015
- Epidemiology of GoutRheumatic Disease Clinics of North America, 2014
- Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation.2013
- Prediction of Kidney-Related Outcomes in Patients With Type 2 DiabetesAmerican Journal of Kidney Diseases, 2012
- An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational StudiesMultivariate Behavioral Research, 2011
- Who Should Be Targeted for CKD Screening? Impact of Diabetes, Hypertension, and Cardiovascular DiseaseAmerican Journal of Kidney Diseases, 2009
- Stochastic analysis of file-swarming systemsPerformance Evaluation, 2007
- Epidemiological Features of CKD in TaiwanAmerican Journal of Kidney Diseases, 2007
- High Prevalence and Low Awareness of CKD in Taiwan: A Study on the Relationship Between Serum Creatinine and Awareness From a Nationally Representative SurveyAmerican Journal of Kidney Diseases, 2006