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

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.

A systematic review of prediction accuracy as an evaluation measure for determining machine learning model performance in healthcare systems

“…Additional research to identify advanced chronic kidney diseases with ML techniques; generalized linear model network, random forest, artificial neural network and natural language processing through a combination of different datasets [37] showed improved prediction performance in accuracy scores as reported. Prediction accuracy scores for the used ML techniques were; both for training data and testing data: Logistic regression 81.8% and 81.9%, Random forest 91.3% and 82.1%, Decision tree 86.0% and 82.1%.…”

“…This, we believe is not exhaustive, other evaluation assessments for its applicability in context will be examined in future research studies. Breast cancer risk prediction Support vector machine accuracy 97.13 [29] Breast cancer diagnosis Support vector machine, Random Forest, Logistic Regression, Decision tree (C4.5) and K-Nearest Neighbors accuracy 97.2 [31] Treatment trend prediction for hypothyrodism Extra trees accuracy 84 [32] Chronic kidney disease prediction Random forest, support vector machine, decision tree accuracy 99.8, 95.5, 98.6 [33] Chronic disease progression (sclerosis) K-nearest neighbor, support vector machine, decision tree, logistic regression auc [34] Chronic kidney disease detection K-nearest neighbor, random forest, neural networks accuracy 0.993 [35] Advanced chronic kidney disease prediction Logistic regression, random forest, decision tree accuracy 81.9, 82.1, 82.1 [36] Prediction of hypertension Deep neural network, decision tree accuracy 0.75, 0.69 [37] Risk prediction (hypertension) k-nearest neighbor, multi-layer perceptron accuracy 82.47 [38] Prediction of hypertension Artificial neural network accuracy 82 [39] Heart disease risk prediction [40] Hypertension prediction extreme Gradient Boosting, Gradient Boosting Machine, Logistic Regression, Random forest, Decision tree and Linear Discriminant Analysis accuracy 83-90% [41] Spam detection Naive Bayes, decision tree, neural networks, random forest, support vector machine accuracy 96.9-99.66 [42] Spam detection ensemble accuracy 99.91 [43] Malicious spam in mails Naive Bayes, support vector machine, logistic regression and random forest accuracy 96.15, 96.15, 98.08, 95.38 [44] Sms spam classification Naive Bayes, BayesNet, C4.5, J48, Self-organizing map and Decision tree accuracy 89.64, 91.11, 80.24, 79.2, 88.24, 75.76 [45] Junk email detection Support vector, random forest accuracy 93.52, 91.41 [46] Email spam detection Bagging, random forest, decision tree (J48) accuracy 98 [47] Credit…”

Prediction of early clinical response in patients receiving tofacitinib in the OCTAVE Induction 1 and 2 studies

“…Comparison of logistic regression and random forest analyses has been done in very large datasets, 26 as well as in the prediction of outcomes for other disease states. 27,28 Specifically, one study determined that logistic regression and machine learning techniques could accurately determine if patients did or did not have chronic kidney failure based solely on data available within electronic health records. 27 Furthermore, a machine learning algorithm successfully identified early clinical variables able to predict prolonged acute hypoxaemic respiratory failure in influenza-infected and critically ill children admitted to hospital.…”

“…27,28 Specifically, one study determined that logistic regression and machine learning techniques could accurately determine if patients did or did not have chronic kidney failure based solely on data available within electronic health records. 27 Furthermore, a machine learning algorithm successfully identified early clinical variables able to predict prolonged acute hypoxaemic respiratory failure in influenza-infected and critically ill children admitted to hospital. 28 Our current study adds to the body of literature showing that machine learning techniques can be very beneficial to potentially improving the quality of care by providing additional inputs to clinical decision-making.…”

A Hybrid Risk Factor Evaluation Scheme for Metabolic Syndrome and Stage 3 Chronic Kidney Disease Based on Multiple Machine Learning Techniques

“…Existing studies that utilize ML methods to perform CKD data analysis mostly analyze the patients directly [ 16 , 17 , 20 , 31 , 32 , 33 , 34 ], and few studies have discussed the predictive models and important risk factors for CKD patients with MetS. Several studies have constructed predictive models for MetS patients, as well as their risk factors.…”