Fig. 1: Performance of the stacked ML models for predicting obesity. | npj Digital Medicine

Fig. 1: Performance of the stacked ML models for predicting obesity.

From: A machine learning-derived polygenic risk score reveals that healthy lifestyle counteracts obesity-related mortality

Fig. 1: Performance of the stacked ML models for predicting obesity.The alternative text for this image may have been generated using AI.

a The MSE of different numbers of SNPs revealed by the LASSO model in the training cohort. A dotted vertical line is drawn at the optimal lambda values by minimum criteria, which is 1048. The lambda.min means the lambda at which the minimal MSE is achieved through 5-fold cross-validation. b LASSO coefficient profiles of SNPs. c The ROC analyses for predicting obesity in the training cohort with the stacked ML models. d The ROC analyses for predicting obesity in the internal test cohort with the stacked ML models. e The ROC analyses for predicting obesity in the external test cohort with the stacked ML models. MSE mean square error, SNP single nucleotide polymorphism, LASSO least absolute shrinkage and selection operator, ROC receiver-operator characteristic. This graph was generated by R and Python.

Back to article page