Comparison of the effects of imputation methods for missing data in predictive modelling of cohort study datasets.

ABSTRACT

BACKGROUND: Missing data is frequently an inevitable issue in cohort studies and it can adversely affect the study's findings. We assess the effectiveness of eight frequently utilized statistical and machine learning (ML) imputation methods for dealing with missing data in predictive modelling of cohort study datasets. This evaluation is based on real data and predictive models for cardiovascular disease (CVD) risk. METHODS: The data is from a real-world cohort study in Xinjiang, China. It includes personal information, physical examination data, questionnaires, and laboratory biochemical results from 10,164 subjects with a total of 37 variables. Simple imputation (Simple), regression imputation (Regression), expectation-maximization(EM), multiple imputation (MICE) , K nearest neighbor classification (KNN), clustering imputation (Cluster), random forest (RF), and decision tree (Cart) were the chosen imputation methods. Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are utilised to assess the performance of different methods for missing data imputation at a missing rate of 20%. The datasets processed with different missing data imputation methods were employed to construct a CVD risk prediction model utilizing the support vector machine (SVM). The predictive performance was then compared using the area under the curve (AUC). RESULTS: The most effective imputation results were attained by KNN (MAE 0.2032, RMSE 0.7438, AUC 0.730, CI 0.719-0.741) and RF (MAE 0.3944, RMSE 1.4866, AUC 0.777, CI 0.769-0.785). The subsequent best performances were achieved by EM, Cart, and MICE, while Simple, Regression, and Cluster attained the worst performances. The CVD risk prediction model was constructed using the complete data (AUC0.804, CI0.796-0.812) in comparison with all other models with p<0.05. CONCLUSION: KNN and RF exhibit superior performance and are more adept at imputing missing data in predictive modelling of cohort study datasets.