Fig. 2: ROC curves for the auxiliary language delay prediction task. | npj Digital Medicine

Fig. 2: ROC curves for the auxiliary language delay prediction task.

From: Multimodal AI for risk stratification in autism spectrum disorder: integrating voice and screening tools

Fig. 2: ROC curves for the auxiliary language delay prediction task.

These plots show the performance of the Stage 1 model on the secondary task of identifying language delay. The Receiver Operating Characteristic (ROC) curves are shown for five cross-validation folds, with each curve representing the model’s performance on a different held-out test set and the Area Under the Curve (AUC) for each fold displayed in the legend.

Back to article page