Artificial intelligence-enabled detection and assessment of Parkinson's disease using nocturnal breathing signals.

Autor: Yang Y; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA. yuzhe@mit.edu., Yuan Y; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA. miayuan@mit.edu., Zhang G; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA., Wang H; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA.; Department of Computer Science, Rutgers University, Piscataway, NJ, USA., Chen YC; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA., Liu Y; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA., Tarolli CG; Department of Neurology, University of Rochester Medical Center, Rochester, NY, USA.; Center for Health and Technology, University of Rochester Medical Center, Rochester, NY, USA., Crepeau D; Department of Neurology, Mayo Clinic, Rochester, MN, USA., Bukartyk J; Division of Cardiovascular Diseases, Mayo Clinic, Rochester, MN, USA., Junna MR; Department of Neurology and Center for Sleep Medicine, Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, MN, USA., Videnovic A; Divisions of Sleep Medicine and Movement Disorders, Massachusetts General Hospital, Boston, MA, USA., Ellis TD; Department of Physical Therapy and Athletic Training, Center for Neurorehabilitation, Boston University College of Health and Rehabilitation, Sargent College, Boston, MA, USA., Lipford MC; Department of Neurology and Center for Sleep Medicine, Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, MN, USA., Dorsey R; Department of Neurology, University of Rochester Medical Center, Rochester, NY, USA.; Center for Health and Technology, University of Rochester Medical Center, Rochester, NY, USA., Katabi D; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA.; Emerald Innovations, Inc., Cambridge, MA, USA.
Jazyk: angličtina
Zdroj: Nature medicine [Nat Med] 2022 Oct; Vol. 28 (10), pp. 2207-2215. Date of Electronic Publication: 2022 Aug 22.
DOI: 10.1038/s41591-022-01932-x
Abstrakt: There are currently no effective biomarkers for diagnosing Parkinson's disease (PD) or tracking its progression. Here, we developed an artificial intelligence (AI) model to detect PD and track its progression from nocturnal breathing signals. The model was evaluated on a large dataset comprising 7,671 individuals, using data from several hospitals in the United States, as well as multiple public datasets. The AI model can detect PD with an area-under-the-curve of 0.90 and 0.85 on held-out and external test sets, respectively. The AI model can also estimate PD severity and progression in accordance with the Movement Disorder Society Unified Parkinson's Disease Rating Scale (R = 0.94, P = 3.6 × 10 -25 ). The AI model uses an attention layer that allows for interpreting its predictions with respect to sleep and electroencephalogram. Moreover, the model can assess PD in the home setting in a touchless manner, by extracting breathing from radio waves that bounce off a person's body during sleep. Our study demonstrates the feasibility of objective, noninvasive, at-home assessment of PD, and also provides initial evidence that this AI model may be useful for risk assessment before clinical diagnosis.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz: