Optimized Identification of Advanced Chronic Kidney Disease and Absence of Kidney Disease by Combining Different Electronic Health Data Resources and by Applying Machine Learning Strategies
Open Access
- 12 September 2020
- journal article
- research article
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 9 (9) , 2955
Abstract
Automated identification of advanced chronic kidney disease (CKD ≥ III) and of no known kidney disease (NKD) can support both clinicians and researchers. We hypothesized that identification of CKD and NKD can be improved, by combining information from different electronic health record (EHR) resources, comprising laboratory values, discharge summaries and ICD-10 billing codes, compared to using each component alone. We included EHRs from 785 elderly multimorbid patients, hospitalized between 2010 and 2015, that were divided into a training and a test (n = 156) dataset. We used both the area under the receiver operating characteristic (AUROC) and under the precision-recall curve (AUCPR) with a 95% confidence interval for evaluation of different classification models. In the test dataset, the combination of EHR components as a simple classifier identified CKD ≥ III (AUROC 0.96[0.93–0.98]) and NKD (AUROC 0.94[0.91–0.97]) better than laboratory values (AUROC CKD 0.85[0.79–0.90], NKD 0.91[0.87–0.94]), discharge summaries (AUROC CKD 0.87[0.82–0.92], NKD 0.84[0.79–0.89]) or ICD-10 billing codes (AUROC CKD 0.85[0.80–0.91], NKD 0.77[0.72–0.83]) alone. Logistic regression and machine learning models improved recognition of CKD ≥ III compared to the simple classifier if only laboratory values were used (AUROC 0.96[0.92–0.99] vs. 0.86[0.81–0.91], p < 0.05) and improved recognition of NKD if information from previous hospital stays was used (AUROC 0.99[0.98–1.00] vs. 0.95[0.92–0.97]], p < 0.05). Depending on the availability of data, correct automated identification of CKD ≥ III and NKD from EHRs can be improved by generating classification models based on the combination of different EHR components.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (KI 564/2-1, HA 2079/8-1)
This publication has 48 references indexed in Scilit:
- Recognizing clinical entities in hospital discharge summaries using Structural Support Vector Machines with word representation featuresBMC Medical Informatics and Decision Making, 2013
- Derivation and Validation of Automated Electronic Search Strategies to Extract Charlson Comorbidities From Electronic Medical RecordsMayo Clinic Proceedings, 2012
- Impact of data fragmentation across healthcare centers on the accuracy of a high-throughput clinical phenotyping algorithm for specifying subjects with type 2 diabetes mellitusJournal of the American Medical Informatics Association, 2012
- pROC: an open-source package for R and S+ to analyze and compare ROC curvesBMC Bioinformatics, 2011
- Definition of chronic kidney disease and measurement of kidney function in original research papers: a review of the literatureNephrology Dialysis Transplantation, 2011
- Validity of Administrative Database Coding for Kidney Disease: A Systematic ReviewAmerican Journal of Kidney Diseases, 2011
- Under-documentation of chronic kidney disease in the electronic health record in outpatientsJournal of the American Medical Informatics Association, 2010
- Prevalence of CKD and Comorbid Illness in Elderly Patients in the United States: Results From the Kidney Early Evaluation Program (KEEP)American Journal of Kidney Diseases, 2010
- Failure of ICD‐9‐CM Codes to Identify Patients with Comorbid Chronic Kidney Disease in DiabetesHealth Services Research, 2005
- ROCR: visualizing classifier performance in RBioinformatics, 2005