Abstract Objective To determine the frequency and stability over time of the subgroup characterization of the tremor dominant (TD) versus postural instability gait disorder dominant (PIGD) ...Parkinson's disease (PD) in de novo patients. Background There is a substantial body of literature on the clinical sub classification of PD into TD versus PIGD subtype. However, there are limited data on the stability of this classification especially in early disease. Methods Parkinson's Progression Markers Initiative (PPMI) is a longitudinal case control study of de novo, untreated PD participants at enrollment. Participants undergo a number of assessments including the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). TD versus PIGD subtype was defined based on the previously published formula. We report one-year analysis data. Results 320 of 423 PD recruited subjects had data on subtype classification at year 1 and were included in the analysis. 228 (71%) were classified as TD, 56 (18%) as PIGD and 36 (11%) as indeterminate at baseline. At 12 months, 39% PIGD and 18% TD shifted subtypes: 29% PIGD shifted to TD and 11% to Indeterminate; 10% TD shifted to PIGD and 8% to Indeterminate. The classification was not affected by the dopaminergic treatment (p = 0.59). Conclusions TD versus PIGD subtype classification has substantial variability over first year in PD de novo cohort specifically for PIGD subtype. Dopaminergic therapy does not impact the change of the PD subtype. This instability has to be taken into consideration specifically when establishing correlations with the biomarkers and for long term prognostication.
Parkinson's disease (PD) is a progressive neurological disease, with characteristic motor symptoms such as tremor and bradykinesia. There is a growing interest to continuously monitor these and other ...symptoms through body-worn sensor technology. However, limited battery life and memory capacity hinder the potential for continuous, long-term monitoring with these devices. There is little information available on the relative value of adding sensors, increasing sampling rate, or computing complex signal features, all of which may improve accuracy of symptom detection at the expense of computational resources. Here we build on a previous study to investigate the relationship between data measurement characteristics and accuracy when using wearable sensor data to classify tremor and bradykinesia in patients with PD.
Thirteen individuals with PD wore a flexible, skin-mounted sensor (collecting tri-axial accelerometer and gyroscope data) and a commercial smart watch (collecting tri-axial accelerometer data) on their predominantly affected hand. The participants performed a series of standardized motor tasks, during which a clinician scored the severity of tremor and bradykinesia in that limb. Machine learning models were trained on scored data to classify tremor and bradykinesia. Model performance was compared when using different types of sensors (accelerometer and/or gyroscope), different data sampling rates (up to 62.5 Hz), and different categories of pre-engineered features (up to 148 features). Performance was also compared between the flexible sensor and smart watch for each analysis.
First, there was no effect of device type for classifying tremor symptoms (p > 0.34), but bradykinesia models incorporating gyroscope data performed slightly better (up to 0.05 AUROC) than other models (p = 0.01). Second, model performance decreased with sampling frequency (p < 0.001) for tremor, but not bradykinesia (p > 0.47). Finally, model performance for both symptoms was maintained after substantially reducing the feature set.
Our findings demonstrate the ability to simplify measurement characteristics from body-worn sensors while maintaining performance in PD symptom detection. Understanding the trade-off between model performance and data resolution is crucial to design efficient, accurate wearable sensing systems. This approach may improve the feasibility of long-term, continuous, and real-time monitoring of PD symptoms by reducing computational burden on wearable devices.
Neurite orientation dispersion and density imaging (NODDI) uses a three‐compartment model to probe brain tissue microstructure, whereas free‐water (FW) imaging models two‐compartments. It is unknown ...if NODDI detects more disease‐specific effects related to neurodegeneration in Parkinson's disease (PD) and atypical Parkinsonism. We acquired multi‐ and single‐shell diffusion imaging at 3 Tesla across two sites. NODDI (using multi‐shell; isotropic volume Viso; intracellular volume Vic; orientation dispersion ODI) and FW imaging (using single‐shell; FW; free‐water corrected fractional anisotropy FAt) were compared with 44 PD, 21 multiple system atrophy Parkinsonian variant (MSAp), 26 progressive supranuclear palsy (PSP), and 24 healthy control subjects in the basal ganglia, midbrain/thalamus, cerebellum, and corpus callosum. There was elevated Viso in posterior substantia nigra across Parkinsonisms, and Viso, Vic, and ODI were altered in MSAp and PSP in the striatum, globus pallidus, midbrain, thalamus, cerebellum, and corpus callosum relative to controls. The mean effect size across regions for Viso was 0.163, ODI 0.131, Vic 0.122, FW 0.359, and FAt 0.125, with extracellular compartments having the greatest effect size. A key question addressed was if these techniques discriminate PD and atypical Parkinsonism. Both NODDI (AUC: 0.945) and FW imaging (AUC: 0.969) had high accuracy, with no significant difference between models. This study provides new evidence that NODDI and FW imaging offer similar discriminability between PD and atypical Parkinsonism, and FW had higher effect sizes for detecting Parkinsonism within regions across the basal ganglia and cerebellum.
Now that wearable sensors have become more commonplace, it is possible to monitor individual healthcare-related activity outside the clinic, unleashing potential for early detection of events in ...diseases such as Parkinson’s disease (PD). However, the unsupervised and “open world” nature of this type of data collection make such applications difficult to develop. In this proof-of-concept study, we used inertial sensor data from Verily Study Watches worn by individuals for up to 23 h per day over several months to distinguish between seven subjects with PD and four without. Since motor-related PD symptoms such as bradykinesia and gait abnormalities typically present when a PD subject is walking, we initially used human activity recognition (HAR) techniques to identify walk-like activity in the unconstrained, unlabeled data. We then used these “walk-like” events to train one-dimensional convolutional neural networks (1D-CNNs) to determine the presence of PD. We report classification accuracies near 90% on single 5-s walk-like events and 100% accuracy when taking the majority vote over single-event classifications that span a duration of one day. Though based on a small cohort, this study shows the feasibility of leveraging unconstrained wearable sensor data to accurately detect the presence or absence of PD.
Neurodegenerative diseases, such as Parkinson's disease (PD), necessitate frequent clinical visits and monitoring to identify changes in motor symptoms and provide appropriate care. By applying ...machine learning techniques to video data, automated video analysis has emerged as a promising approach to track and analyze motor symptoms, which could facilitate more timely intervention. However, existing solutions often rely on specialized equipment and recording procedures, which limits their usability in unstructured settings like the home. In this study, we developed a method to detect PD symptoms from unstructured videos of clinical assessments, without the need for specialized equipment or recording procedures.
Twenty-eight individuals with Parkinson's disease completed a video-recorded motor examination that included the finger-to-nose and hand pronation-supination tasks. Clinical staff provided ground truth scores for the level of Parkinsonian symptoms present. For each video, we used a pre-existing model called PIXIE to measure the location of several joints on the person's body and quantify how they were moving. Features derived from the joint angles and trajectories, designed to be robust to recording angle, were then used to train two types of machine-learning classifiers (random forests and support vector machines) to detect the presence of PD symptoms.
The support vector machine trained on the finger-to-nose task had an F1 score of 0.93 while the random forest trained on the same task yielded an F1 score of 0.85. The support vector machine and random forest trained on the hand pronation-supination task had F1 scores of 0.20 and 0.33, respectively.
These results demonstrate the feasibility of developing video analysis tools to track motor symptoms across variable perspectives. These tools do not work equally well for all tasks, however. This technology has the potential to overcome barriers to access for many individuals with degenerative neurological diseases like PD, providing them with a more convenient and timely method to monitor symptom progression, without requiring a structured video recording procedure. Ultimately, more frequent and objective home assessments of motor function could enable more precise telehealth optimization of interventions to improve clinical outcomes inside and outside of the clinic.
Research-based exercise interventions improve health-related quality of life (HRQL) and mobility in people with Parkinson's disease (PD).
To examine whether exercise habits were associated with ...changes in HRQL and mobility over two years.
We identified a cohort of National Parkinson Foundation Quality Improvement Initiative (NPF-QII) participants with three visits. HRQL and mobility were measured with the Parkinson's Disease Questionnaire (PDQ-39) and Timed Up and Go (TUG). We compared self-reported regular exercisers (≥2.5 hours/week) with people who did not exercise 2.5 hours/week. Then we quantified changes in HRQL and mobility associated with 30-minute increases in exercise, across PD severity, using mixed effects regression models.
Participants with three observational study visits (n = 3408) were younger, with milder PD, than participants with fewer visits. After 2 years, consistent exercisers and people who started to exercise regularly after their baseline visit had smaller declines in HRQL and mobility than non-exercisers (p < 0.05). Non-exercisers worsened by 1.37 points on the PDQ-39 and a 0.47 seconds on the TUG per year. Increasing exercise by 30 minutes/week was associated with slower declines in HRQL (-0.16 points) and mobility (-0.04 sec). The benefit of exercise on HRQL was greater in advanced PD (-0.41 points) than mild PD (-0.14 points; p < 0.02).
Consistently exercising and starting regular exercise after baseline were associated with small but significant positive effects on HRQL and mobility changes over two years. The greater association of exercise with HRQL in advanced PD supports improving encouragement and facilitation of exercise in advanced PD.