Screening the influence of features for metabolic syndrome in occupational population based on Lasso and Elastic Net algorithms

Abstract

Abstract Funding Acknowledgements None. Objective Screening features associated with metabolic syndrome (MetS) is essential for early detection in the occupational population. In this study, we utilized two machine learning algorithms to screen MetS features and compared the performance of models constructed from these screened features. Method A total of 3,077 workers’examination records were considered from our hospital. However, 233 records were excluded due to incompleteness and errors, resulting in a final dataset of 2,844 workers’examination records used for the study. We collected and analyzed available data to extract usable indicators initially. Then, we applied the Least Absolute Shrinkage and Selection Operator (Lasso) algorithm and Elastic Net algorithm to identify features related to MetS. Subsequently, different models, namely K-Nearest Neighbors (KNN), Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM),were established using these two groups of features to predict the probability of MetS in the occupational population. The performance of these models was evaluated using the Area Under the Receiver Operating Characteristic Curve (AUC), Calibration Curve, and Decision Curve Analysis (DCA). Results It was indicated that features screened by the Elastic Net algorithm were more stable and demonstrated better predictive performance compared to LASSO, particularly when the data had high dimensionality and correlations. Furthermore, this study presents the first application of the Elastic Net algorithm in screening features related to MetS and establishing a risk prediction model for routine physical examinations of the occupational population. Conclusion Notably, Elastic Net demonstrated improved stability when dealing with multiple indicators exhibiting high dimensional correlations. This enhanced stability allowed for a more accurate prediction of MetS, providing a basis for utilizing common universal indicators in health screening for the general occupational population.Study the basic characteristics of the p(a) AUC performance of 9 features screen