Fig. 1: ROC curves for LASSO, logistic regression, random forest, and XG boost models predicting incident dementia at approximately 10-year follow-up among participants alive and assessed at Wave 6. | npj Dementia

Fig. 1: ROC curves for LASSO, logistic regression, random forest, and XG boost models predicting incident dementia at approximately 10-year follow-up among participants alive and assessed at Wave 6.

From: Machine learning models for dementia risk prediction: evidence from the Sydney Memory and Ageing Study

Fig. 1: ROC curves for LASSO, logistic regression, random forest, and XG boost models predicting incident dementia at approximately 10-year follow-up among participants alive and assessed at Wave 6.The alternative text for this image may have been generated using AI.

LASSO demonstrated the highest discrimination (AUC = 0.752), followed by logistic regression (AUC = 0.707), random forest (AUC = 0.657), and XGBoost (AUC = 0.589). The diagonal line indicates no-discrimination (AUC = 0.50).

Back to article page