PAT model score

1. PAT model score predicts REM sleep behavior disorder in humans (AUC = 0.956).

   “In the PD-RBD versus PD-noRBD classification task, the PAT model again outperformed the other models (AUC = 0.956, sensitivity = 84.4% and specificity = 92.9%).”

   Humansin patients with PD (PD-RBD vs PD-noRBD)

   Actigraphy Meets AI: A Digital Biomarker for Parkinson's Disease and Isolated REM Sleep Behaviour Disorder

   Journal of sleep research·7 Jul 2026

More on REM sleep behavior disorder

1. PAT model score predicts Parkinson's disease in humans (AUC = 0.937).

   “In PD versus control classification, the PAT model performed best (AUC = 0.937, sensitivity = 80.5%, specificity = 92.9%)”

   Humansdistinguishing PD from non-neurodegenerative controls

   Actigraphy Meets AI: A Digital Biomarker for Parkinson's Disease and Isolated REM Sleep Behaviour Disorder

   Journal of sleep research·7 Jul 2026

More on Parkinson's disease