Risk Management and Healthcare Policy (Apr 2022)
Comparison Between Statistical Model and Machine Learning Methods for Predicting the Risk of Renal Function Decline Using Routine Clinical Data in Health Screening
Abstract
Xia Cao,1– 3 Yanhui Lin,1– 3 Binfang Yang,1– 3 Ying Li,1– 3 Jiansong Zhou4 1Health Management Center, The Third Xiangya Hospital, Central South University, Changsha, Hunan, People’s Republic of China; 2Health Management Research Center, Central South University, Changsha, Hunan, People’s Republic of China; 3Hunan Chronic Disease Health Management Medical Research Center, Central South University, Changsha, Hunan, People’s Republic of China; 4National Clinical Research Center for Mental Disorders, and Department of Psychiatry, The Second Xiangya Hospital, Central South University, Changsha, Hunan, People’s Republic of ChinaCorrespondence: Jiansong Zhou, National Clinical Research Center for Mental Disorders, and Department of Psychiatry, The Second Xiangya Hospital, Central South University, Changsha, 410011, People’s Republic of China, Tel/Fax +86 073188618573, Email [email protected]: Using machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk factors. Therefore, we evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for predicting the risk of renal function decline (RFD) using routine clinical data.Patients and Methods: This retrospective cohort study includes datasets from 2166 subjects, aged 35– 74 years old, provided by an adult health screening follow-up program between 2010 and 2020. Seven different ML models were considered – random forest, gradient boosting, multilayer perceptron, support vector machine, K-nearest neighbors, adaptive boosting, and decision tree - and were compared with standard logistic regression. There were 24 independent variables, and the baseline estimate glomerular filtration rate (eGFR) was used as the predictive variable.Results: A total of 2166 participants (mean age 49.2± 11.2 years old, 63.3% males) were enrolled and randomly divided into a training set (n=1732) and a test set (n=434). The area under receiver operating characteristic curve (AUROC) for detecting RFD corresponding to the different models were above 0.85 during the training phase. The gradient boosting algorithms exhibited the best average prediction accuracy (AUROC: 0.914) among all algorithms validated in this study. Based on AUROC, the ML algorithms improved the RFD prediction performance, compared to logistic regression model (AUROC:0.882), except the K-nearest neighbors and decision tree algorithms (AUROC:0.854 and 0.824, respectively). However, the improvement differences with logistic regression were small (less than 4%) and nonsignificant.Conclusion: Our results indicate that the proposed health screening dataset-based RFD prediction model using ML algorithms is readily applicable, produces validated results. But logistic regression yields as good performance as ML models to predict the risk of RFD with simple clinical predictors.Keywords: deep learning, chronic kidney disease, algorithm, health examination
