Session Information
Date: Tuesday, June 21, 2016
Session Title: Technology
Session Time: 12:30pm-2:00pm
Location: Exhibit Hall located in Hall B, Level 2
Objective: To determine if 24-hour tri-axial accelerometer and heart rate measurements can (1) discriminate Parkinson’s disease (PD) from healthy controls and (2) monitor severity of motor and non-motor deficits associated with cognitive impairment, apathy and depression.
Background: PD is one of the most common neurodegenerative disorders resulting in both motor and non-motor symptoms. Despite its prevalence, there are currently no definitive objective diagnostic methods. Diagnosis and monitoring of disease severity currently relies on subjective clinical evaluation, sometimes in combination with expensive tests.
Methods: 41 patients with idiopathic PD and 26 control participants wore an inexpensive and non-invasive tri-axial accelerometer and single lead ECG monitor for 24 hours. Motor severity was established using clinical examination and a battery of standard assessments were performed to index apathy, depression and cognitive function. To quantify different patterns of movement, a range of time and frequency domain features were extracted from the accelerometer recordings. Using a random forest classifier, applied in a ‘leave-one-subject-out’ cross-validation design, we identified discriminatory patterns in the extracted features in order to replicate clinical assessments as accurately as possible.
Results: From our data set, PD vs controls can be predicted with a mean sensitivity of 90% and mean specificity of 77% (average overall accuracy 84%). This method was significantly better than randomized determination analysis (p<0.05). Importantly, significant correlations and mutual information existed between accelerometer features and clinical assessments of motivation, motor severity, mood and cognitive function (p<0.05).
Conclusions: Using inexpensive accelerometer and heart rate measurements over a 24-hour period it may be possible to discriminate PD from healthy controls, and objectively assess the severity of motor and non-motor dysfunction. The reliability of such measures requires further assessment on larger data sets but provides a promising start for further research.
To cite this abstract in AMA style:
K. Muhammed, S. Arora, M. Hu, M. Husain. Diagnostic sensitivity and remote monitoring of motor and non-motor dysfunction in Parkinson’s disease [abstract]. Mov Disord. 2016; 31 (suppl 2). https://www.mdsabstracts.org/abstract/diagnostic-sensitivity-and-remote-monitoring-of-motor-and-non-motor-dysfunction-in-parkinsons-disease/. Accessed November 2, 2024.« Back to 2016 International Congress
MDS Abstracts - https://www.mdsabstracts.org/abstract/diagnostic-sensitivity-and-remote-monitoring-of-motor-and-non-motor-dysfunction-in-parkinsons-disease/