Dataset Information

Predicting motor, cognitive & functional impairment in Parkinson's.

ABSTRACT:

Objective

We recently demonstrated that 998 features derived from a simple 7-minute smartphone test could distinguish between controls, people with Parkinson's and people with idiopathic Rapid Eye Movement sleep behavior disorder, with mean sensitivity/specificity values of 84.6-91.9%. Here, we investigate whether the same smartphone features can be used to predict future clinically relevant outcomes in early Parkinson's.

Methods

A total of 237 participants with Parkinson's (mean (SD) disease duration 3.5 (2.2) years) in the Oxford Discovery cohort performed smartphone tests in clinic and at home. Each test assessed voice, balance, gait, reaction time, dexterity, rest, and postural tremor. In addition, standard motor, cognitive and functional assessments and questionnaires were administered in clinic. Machine learning algorithms were trained to predict the onset of clinical outcomes provided at the next 18-month follow-up visit using baseline smartphone recordings alone. The accuracy of model predictions was assessed using 10-fold and subject-wise cross validation schemes.

Results

Baseline smartphone tests predicted the new onset of falls, freezing, postural instability, cognitive impairment, and functional impairment at 18 months. For all outcome predictions AUC values were greater than 0.90 for 10-fold cross validation using all smartphone features. Using only the 30 most salient features, AUC values greater than 0.75 were obtained.

Interpretation

We demonstrate the ability to predict key future clinical outcomes using a simple smartphone test. This work has the potential to introduce individualized predictions to routine care, helping to target interventions to those most likely to benefit, with the aim of improving their outcome.

SUBMITTER: Lo C

PROVIDER: S-EPMC6689691 | biostudies-literature | 2019 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting motor, cognitive & functional impairment in Parkinson's.

Lo Christine C Arora Siddharth S Baig Fahd F Lawton Michael A MA El Mouden Claire C Barber Thomas R TR Ruffmann Claudio C Klein Johannes C JC Brown Peter P Ben-Shlomo Yoav Y de Vos Maarten M Hu Michele T MT

Annals of clinical and translational neurology 20190726 8

<h4>Objective</h4>We recently demonstrated that 998 features derived from a simple 7-minute smartphone test could distinguish between controls, people with Parkinson's and people with idiopathic Rapid Eye Movement sleep behavior disorder, with mean sensitivity/specificity values of 84.6-91.9%. Here, we investigate whether the same smartphone features can be used to predict future clinically relevant outcomes in early Parkinson's.<h4>Methods</h4>A total of 237 participants with Parkinson's (mean ...[more]

PMID: 31402628

Similar Datasets

Project description:ObjectiveCognitive impairment occurs frequently in Parkinson's disease (PD) and negatively impacts the patient's quality of life. However, its pathophysiological mechanism remains unclear, hindering the development of new therapies. Changes in brain connectivity are related to cognitive impairment in patients with PD, with the dorsolateral prefrontal cortex (DLPFC) being considered the essential region related to PD cognitive impairment. Nevertheless, few studies have focused on the global connectivity responsible for communication with the DLPFC node, the posterior division of the middle frontal gyrus (PMFG) in patients with PD; this was the focus of this study.MethodsWe applied resting-state electroencephalography (EEG) and calculated a reliable functional connectivity measurement, the debiased weighted phase lag index (dWPLI), to examine inter-regional functional connectivity in 68 patients with PD who were classified into two groups according to their cognitive condition.ResultsWe observed that altered left and right PMFG-based functional connectivity associated with cognitive impairment in patients with PD in the theta frequency bands under the eyes closed condition (r = -0.426, p < 0.001 and r = -0.437, p < 0.001, respectively). Exploratory results based on the MoCA subdomains indicated that poorer visuospatial function was associated with higher right PMFG-based functional connectivity (r = -0.335, p = 0.005), and poorer attention function was associated with higher left and right PMFG-based functional connectivity (r = -0.380, p = 0.001 and r = -0.256, p = 0.035, respectively). Further analysis using logistic regression and receiver operating characteristic (ROC) curves found that this abnormal functional connectivity was an independent risk factor for cognitive impairment [odds ratio (OR): 2.949, 95% confidence interval (CI): 1.294-6.725, p = 0.01 for left PMFG; OR: 11.278, 95% CI: 2.578-49.335, p = 0.001 for right PMFG, per 0.1 U], and provided moderate classification power to discriminate between cognitive abilities in patients with PD [area under the ROC curve (AUC) = 0.770 for left PMFG; AUC = 0.809 for right PMFG].ConclusionThese preliminary findings indicate that abnormal PMFG-based functional connectivity patterns associated with cognitive impairment in the theta frequency bands under the eyes closed condition and altered functional connectivity patterns have the potential to act as reliable biomarkers for identifying cognitive impairment in patients with PD.

Project description:Objective: The effects of the COVID-19 lockdown on subjects with prodromal phases of dementia are unknown. The aim of this study was to evaluate the motor, cognitive, and behavioral changes during the COVID-19 lockdown in Italy in patients with Parkinson's disease (PD) with and without mild cognitive impairment (PD-MCI and PD-NC) and in patients with MCI not associated with PD (MCInoPD). Methods: A total of 34 patients with PD-NC, 31 PD-MCI, and 31 MCInoPD and their caregivers were interviewed 10 weeks after the COVID-19 lockdown in Italy, and changes in cognitive, behavioral, and motor symptoms were examined. Modified standardized scales, including the Neuropsychiatric Inventory (NPI) and the Movement Disorder Society, Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Parts I and II, were administered. Multivariate logistic regression was used to evaluate associated covariates by comparing PD-NC vs. PD-MCI and MCInoPD vs. PD-MCI. Results: All groups showed a worsening of cognitive (39.6%), pre-existing (37.5%), and new (26%) behavioral symptoms, and motor symptoms (35.4%) during the COVID-19 lockdown, resulting in an increased caregiver burden in 26% of cases. After multivariate analysis, PD-MCI was significantly and positively associated with the IADL lost during quarantine (OR 3.9, CI 1.61-9.58), when compared to PD-NC. In the analysis of MCInoPD vs. PD-MCI, the latter showed a statistically significant worsening of motor symptoms than MCInoPD (OR 7.4, CI 1.09-45.44). Regarding NPI items, nighttime behaviors statistically differed in MCInoPD vs. PD-MCI (16.1% vs. 48.4%, p = 0.007). MDS-UPDRS parts I and II revealed that PD-MCI showed a significantly higher frequency of cognitive impairment (p = 0.034), fatigue (p = 0.036), and speech (p = 0.013) than PD-NC. On the contrary, PD-MCI showed significantly higher frequencies in several MDS-UPDRS items compared to MCInoPD, particularly regarding pain (p = 0.001), turning in bed (p = 0.006), getting out of bed (p = 0.001), and walking and balance (p = 0.003). Conclusion: The COVID-19 quarantine is associated with the worsening of cognitive, behavioral, and motor symptoms in subjects with PD and MCI, particularly in PD-MCI. There is a need to implement specific strategies to contain the effects of quarantine in patients with PD and cognitive impairment and their caregivers.

Dataset Information

Predicting motor, cognitive & functional impairment in Parkinson's.

Objective

Methods

Results

Interpretation

Publications

Predicting motor, cognitive & functional impairment in Parkinson's.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets