Extended Data Fig. 4: Performance of the AI model on differentiating subjects with Parkinson’s disease (PD) from subjects with Alzheimer’s disease (AD). | Nature Medicine

Extended Data Fig. 4: Performance of the AI model on differentiating subjects with Parkinson’s disease (PD) from subjects with Alzheimer’s disease (AD).

From: Artificial intelligence-enabled detection and assessment of Parkinson’s disease using nocturnal breathing signals

Extended Data Fig. 4

a, The model’s output scores differentiate PD subjects from AD subjects (p = 3.52e-16, one-tailed Wilcoxon rank-sum test). b, Receiver operating characteristic (ROC) curves for detecting PD subjects against AD subjects (n = 148). The model achieves high AUC for differentiating PD from AD (AUC = 0.895).

Back to article page