Accelerometric assessment of levodopa-induced dyskinesias in Parkinson's disease

Unveiling the Unpredictable in Parkinson's Disease: Sensor-Based Monitoring of Dyskinesias and Freezing of Gait in Daily Life

BACKGROUND

Dyskinesias and freezing of gait are episodic disorders in Parkinson's disease, characterized by a fluctuating and unpredictable nature. This cross-sectional study aims to objectively monitor Parkinsonian patients experiencing dyskinesias and/or freezing of gait during activities of daily living and assess possible changes in spatiotemporal gait parameters.

METHODS

Seventy-one patients with Parkinson's disease (40 with dyskinesias and 33 with freezing of gait) were continuously monitored at home for a minimum of 5 days using a single wearable sensor. Dedicated machine-learning algorithms were used to categorize patients based on the occurrence of dyskinesias and freezing of gait. Additionally, specific spatiotemporal gait parameters were compared among patients with and without dyskinesias and/or freezing of gait.

RESULTS

The wearable sensor algorithms accurately classified patients with and without dyskinesias as well as those with and without freezing of gait based on the recorded dyskinesias and freezing of gait episodes. Standard spatiotemporal gait parameters did not differ significantly between patients with and without dyskinesias or freezing of gait. Both the time spent with dyskinesias and the number of freezing of gait episodes positively correlated with the disease severity and medication dosage.

CONCLUSIONS

A single inertial wearable sensor shows promise in monitoring complex, episodic movement patterns, such as dyskinesias and freezing of gait, during daily activities. This approach may help implement targeted therapeutic and preventive strategies for Parkinson's disease.

Neural Control of REM Sleep and Motor Atonia: Current Perspectives

PURPOSE OF REVIEW

Since the formal discovery of rapid eye movement (REM) sleep in 1953, we have gained a vast amount of knowledge regarding the specific populations of neurons, their connections, and synaptic mechanisms regulating this stage of sleep and its accompanying features. This article discusses REM sleep circuits and their dysfunction, specifically emphasizing recent studies using conditional genetic tools.

RECENT FINDINGS

Sublaterodorsal nucleus (SLD) in the dorsolateral pons, especially the glutamatergic subpopulation in this region (SLDGlut), are shown to be indispensable for REM sleep. These neurons appear to be single REM generators in the rodent brain and may initiate and orchestrate all REM sleep events, including cortical and hippocampal activation and muscle atonia through distinct pathways. However, several cell groups in the brainstem and hypothalamus may influence SLDGlut neuron activity, thereby modulating REM sleep timing, amounts, and architecture. Damage to SLDGlut neurons or their projections involved in muscle atonia leads to REM behavior disorder, whereas the abnormal activation of this pathway during wakefulness may underlie cataplexy in narcolepsy. Despite some opposing views, it has become evident that SLDGlut neurons are the sole generators of REM sleep and its associated characteristics. Further research should prioritize a deeper understanding of their cellular, synaptic, and molecular properties, as well as the mechanisms that trigger their activation during cataplexy and make them susceptible in RBD.

Assessment of movement disorders using wearable sensors during upper limb tasks: A scoping review

Background: Studies aiming to objectively quantify movement disorders during upper limb tasks using wearable sensors have recently increased, but there is a wide variety in described measurement and analyzing methods, hampering standardization of methods in research and clinics. Therefore, the primary objective of this review was to provide an overview of sensor set-up and type, included tasks, sensor features and methods used to quantify movement disorders during upper limb tasks in multiple pathological populations. The secondary objective was to identify the most sensitive sensor features for the detection and quantification of movement disorders on the one hand and to describe the clinical application of the proposed methods on the other hand. Methods: A literature search using Scopus, Web of Science, and PubMed was performed. Articles needed to meet following criteria: 1) participants were adults/children with a neurological disease, 2) (at least) one sensor was placed on the upper limb for evaluation of movement disorders during upper limb tasks, 3) comparisons between: groups with/without movement disorders, sensor features before/after intervention, or sensor features with a clinical scale for assessment of the movement disorder. 4) Outcome measures included sensor features from acceleration/angular velocity signals. Results: A total of 101 articles were included, of which 56 researched Parkinson's Disease. Wrist(s), hand(s) and index finger(s) were the most popular sensor locations. Most frequent tasks were: finger tapping, wrist pro/supination, keeping the arms extended in front of the body and finger-to-nose. Most frequently calculated sensor features were mean, standard deviation, root-mean-square, ranges, skewness, kurtosis/entropy of acceleration and/or angular velocity, in combination with dominant frequencies/power of acceleration signals. Examples of clinical applications were automatization of a clinical scale or discrimination between a patient/control group or different patient groups. Conclusion: Current overview can support clinicians and researchers in selecting the most sensitive pathology-dependent sensor features and methodologies for detection and quantification of upper limb movement disorders and objective evaluations of treatment effects. Insights from Parkinson's Disease studies can accelerate the development of wearable sensors protocols in the remaining pathologies, provided that there is sufficient attention for the standardisation of protocols, tasks, feasibility and data analysis methods.

Co-evolution of machine learning and digital technologies to improve monitoring of Parkinson's disease motor symptoms

Parkinson's disease (PD) is a neurodegenerative disorder characterized by motor impairments such as tremor, bradykinesia, dyskinesia, and gait abnormalities. Current protocols assess PD symptoms during clinic visits and can be subjective. Patient diaries can help clinicians evaluate at-home symptoms, but can be incomplete or inaccurate. Therefore, researchers have developed in-home automated methods to monitor PD symptoms to enable data-driven PD diagnosis and management. We queried the US National Library of Medicine PubMed database to analyze the progression of the technologies and computational/machine learning methods used to monitor common motor PD symptoms. A sub-set of roughly 12,000 papers was reviewed that best characterized the machine learning and technology timelines that manifested from reviewing the literature. The technology used to monitor PD motor symptoms has advanced significantly in the past five decades. Early monitoring began with in-lab devices such as needle-based EMG, transitioned to in-lab accelerometers/gyroscopes, then to wearable accelerometers/gyroscopes, and finally to phone and mobile & web application-based in-home monitoring. Significant progress has also been made with respect to the use of machine learning algorithms to classify PD patients. Using data from different devices (e.g., video cameras, phone-based accelerometers), researchers have designed neural network and non-neural network-based machine learning algorithms to categorize PD patients across tremor, gait, bradykinesia, and dyskinesia. The five-decade co-evolution of technology and computational techniques used to monitor PD motor symptoms has driven significant progress that is enabling the shift from in-lab/clinic to in-home monitoring of PD symptoms.

Could New Generations of Sensors Reshape the Management of Parkinson’s Disease?

Parkinson's disease (PD) is a chronic neurologic disease that has a great impact on the patient’s quality of life. The natural course of the disease is characterized by an insidious onset of symptoms, such as rest tremor, shuffling gait, bradykinesia, followed by improvement with the initiation of dopaminergic therapy. However, this “honeymoon period” gradually comes to an end with the emergence of motor fluctuations and dyskinesia. PD patients need long-term treatments and monitoring throughout the day; however, clinical examinations in hospitals are often not sufficient for optimal management of the disease. Technology-based devices are a new comprehensive assessment method of PD patient’s symptoms that are easy to use and give unbiased measurements. This review article provides an exhaustive overview of motor complications of advanced PD and new approaches to the management of the disease using sensors.

Implementation of a Deep Learning Algorithm Based on Vertical Ground Reaction Force Time-Frequency Features for the Detection and Severity Classification of Parkinson's Disease

Conventional approaches to diagnosing Parkinson’s disease (PD) and rating its severity level are based on medical specialists’ clinical assessment of symptoms, which are subjective and can be inaccurate. These techniques are not very reliable, particularly in the early stages of the disease. A novel detection and severity classification algorithm using deep learning approaches was developed in this research to classify the PD severity level based on vertical ground reaction force (vGRF) signals. Different variations in force patterns generated by the irregularity in vGRF signals due to the gait abnormalities of PD patients can indicate their severity. The main purpose of this research is to aid physicians in detecting early stages of PD, planning efficient treatment, and monitoring disease progression. The detection algorithm comprises preprocessing, feature transformation, and classification processes. In preprocessing, the vGRF signal is divided into 10, 15, and 30 s successive time windows. In the feature transformation process, the time domain vGRF signal in windows with varying time lengths is modified into a time–frequency spectrogram using a continuous wavelet transform (CWT). Then, principal component analysis (PCA) is used for feature enhancement. Finally, different types of convolutional neural networks (CNNs) are employed as deep learning classifiers for classification. The algorithm performance was evaluated using k-fold cross-validation (kfoldCV). The best average accuracy of the proposed detection algorithm in classifying the PD severity stage classification was 96.52% using ResNet-50 with vGRF data from the PhysioNet database. The proposed detection algorithm can effectively differentiate gait patterns based on time–frequency spectrograms of vGRF signals associated with different PD severity levels.

Identification of Neurodegenerative Diseases Based on Vertical Ground Reaction Force Classification Using Time-Frequency Spectrogram and Deep Learning Neural Network Features

A novel identification algorithm using a deep learning approach was developed in this study to classify neurodegenerative diseases (NDDs) based on the vertical ground reaction force (vGRF) signal. The irregularity of NDD vGRF signals caused by gait abnormalities can indicate different force pattern variations compared to a healthy control (HC). The main purpose of this research is to help physicians in the early detection of NDDs, efficient treatment planning, and monitoring of disease progression. The detection algorithm comprises a preprocessing process, a feature transformation process, and a classification process. In the preprocessing process, the five-minute vertical ground reaction force signal was divided into 10, 30, and 60 s successive time windows. In the feature transformation process, the time-domain vGRF signal was modified into a time-frequency spectrogram using a continuous wavelet transform (CWT). Then, feature enhancement with principal component analysis (PCA) was utilized. Finally, a convolutional neural network, as a deep learning classifier, was employed in the classification process of the proposed detection algorithm and evaluated using leave-one-out cross-validation (LOOCV) and k-fold cross-validation (k-fold CV, k = 5). The proposed detection algorithm can effectively differentiate gait patterns based on a time-frequency spectrogram of a vGRF signal between HC subjects and patients with neurodegenerative diseases.

Dyskinesia estimation during activities of daily living using wearable motion sensors and deep recurrent networks

Levodopa-induced dyskinesias are abnormal involuntary movements experienced by the majority of persons with Parkinson's disease (PwP) at some point over the course of the disease. Choreiform as the most common phenomenology of levodopa-induced dyskinesias can be managed by adjusting the dose/frequency of PD medication(s) based on a PwP's motor fluctuations over a typical day. We developed a sensor-based assessment system to provide such information. We used movement data collected from the upper and lower extremities of 15 PwPs along with a deep recurrent model to estimate dyskinesia severity as they perform different activities of daily living (ADL). Subjects performed a variety of ADLs during a 4-h period while their dyskinesia severity was rated by the movement disorder experts. The estimated dyskinesia severity scores from our model correlated highly with the expert-rated scores (r = 0.87 (p < 0.001)), which was higher than the performance of linear regression that is commonly used for dyskinesia estimation (r = 0.81 (p < 0.001)). Our model provided consistent performance at different ADLs with minimum r = 0.70 (during walking) to maximum r = 0.84 (drinking) in comparison to linear regression with r = 0.00 (walking) to r = 0.76 (cutting food). These findings suggest that when our model is applied to at-home sensor data, it can provide an accurate picture of changes of dyskinesia severity facilitating effective medication adjustments.

Turning and sit-to-walk measures from the instrumented Timed Up and Go test return valid and responsive measures of dynamic balance in Parkinson's disease

BACKGROUND

Balance impairment is a hallmark of Parkinson's disease with dramatic effects for patients (e.g. falls). Its assessment is thus of paramount importance. The aim of this work is to assess which measures from the instrumented Timed Up and Go test (recorded with inertial sensors) are valid balance measures in Parkinson's disease and evaluate their responsiveness to rehabilitation.

METHODS

The Mini-BESTest (a criterion-standard balance measure) and the instrumented Timed Up and Go test (with inertial sensors secured to the trunk) were administered to 20 Parkinson's disease patients before and after inpatient rehabilitation (median [IQR]; 76.5 [8.25] years; 5 females; Hoehn and Yahr stage: 2.5 [0.5]). 81 parameters from the instrumented Timed Up and Go test were evaluated. Multiple factor analysis (a variant of principal component analysis for repeated measurements) and effect sizes were used to assess validity and responsiveness, respectively.

FINDINGS

Only the first component of the multiple factor analysis correlated with the Mini-BESTest, and 21 measures from the instrumented Timed Up and Go test had large loadings on this component. However, only three of these 21 measures also directly correlated with the Mini-BESTest (trunk angular velocities from sit-to-walk and turning; r = 0.46 to 0.50, P = 0.021 to 0.038). Sit-to-walk angular velocity showed greater responsiveness than the Mini-BESTest, while turning showed slightly less.

INTERPRETATION

Angular velocities from the turning and sit-to-walk phases of the Timed Up and Go test are valid balance measures in Parkinson's disease and are also responsive to rehabilitation.

Dyskinesia Severity Estimation in Patients with Parkinson's Disease Using Wearable Sensors and A Deep LSTM Network

Dyskinesias are abnormal involuntary movements that patients with mid-stage and advanced Parkinson's disease (PD) may suffer from. These troublesome motor impairments are reduced by adjusting the dose or frequency of medication levodopa. However, to make a successful adjustment, the treating physician needs information about the severity rating of dyskinesia as patients experience in their natural living environment. In this work, we used movement data collected from the upper and lower extremities of PD patients along with a deep model based on Long Short-Term Memory to estimate the severity of dyskinesia. We trained and validated our model on a dataset of 14 PD subjects with dyskinesia. The subjects performed a variety of daily living activities while their dyskinesia severity was rated by a neurologist. The estimated dyskinesia severity ratings from our developed model highly correlated with the neurologist-rated dyskinesia scores (r=0.86 (p<0.001) and 1.77 MAE (6%)) indicating the potential of the developed the approach in providing the information required for effective medication adjustments for dyskinesia management.

Evaluation of Vertical Ground Reaction Forces Pattern Visualization in Neurodegenerative Diseases Identification Using Deep Learning and Recurrence Plot Image Feature Extraction

To diagnose neurodegenerative diseases (NDDs), physicians have been clinically evaluating symptoms. However, these symptoms are not very dependable—particularly in the early stages of the diseases. This study has therefore proposed a novel classification algorithm that uses a deep learning approach to classify NDDs based on the recurrence plot of gait vertical ground reaction force (vGRF) data. The irregular gait patterns of NDDs exhibited by vGRF data can indicate different variations of force patterns compared with healthy controls (HC). The classification algorithm in this study comprises three processes: a preprocessing, feature transformation and classification. In the preprocessing process, the 5-min vGRF data divided into 10-s successive time windows. In the feature transformation process, the time-domain vGRF data are modified into an image using a recurrence plot. The total recurrence plots are 1312 plots for HC (16 subjects), 1066 plots for ALS (13 patients), 1230 plots for PD (15 patients) and 1640 plots for HD (20 subjects). The principal component analysis (PCA) is used in this stage for feature enhancement. Lastly, the convolutional neural network (CNN), as a deep learning classifier, is employed in the classification process and evaluated using the leave-one-out cross-validation (LOOCV). Gait data from HC subjects and patients with amyotrophic lateral sclerosis (ALS), Huntington’s disease (HD) and Parkinson’s disease (PD) obtained from the PhysioNet Gait Dynamics in Neurodegenerative disease were used to validate the proposed algorithm. The experimental results included two-class and multiclass classifications. In the two-class classification, the results included classification of the NDD and the HC groups and classification among the NDDs. The classification accuracy for (HC vs. ALS), (HC vs. HD), (HC vs. PD), (ALS vs. PD), (ALS vs. HD), (PD vs. HD) and (NDDs vs. HC) were 100%, 98.41%, 100%, 95.95%, 100%, 97.25% and 98.91%, respectively. In the multiclass classification, a four-class gait classification among HC, ALS, PD and HD was conducted and the classification accuracy of HC, ALS, PD and HD were 98.99%, 98.32%, 97.41% and 96.74%, respectively. The proposed method can achieve high accuracy compare to the existing results, but with shorter length of input signal (Input of existing literature using the same database is 5-min gait signal, but the proposed method only needs 10-s gait signal).

Multilevel Features for Sensor-Based Assessment of Motor Fluctuation in Parkinson's Disease Subjects

Motor fluctuations are a frequent complication in patients with Parkinson's disease (PD) where the response to medication fluctuates between ON states (medication working) and OFF states (medication has worn off). This paper describes a new data analysis approach that can be used along with two wearable IMU (inertial measurement units) sensors to continuously assess motor fluctuations in PD patients while moving in their natural environment. We hypothesized that joint analysis of the sensor data in its spectral, temporal and sensor domain could generate multilevel features that can be used to detect PD-related patterns successfully as the subject's motor state fluctuates between medication ON and OFF states. For this purpose, we utilized time-frequency (TF) representation and multiway data analysis tools (i.e., tensor decomposition) to decompose the TF representation of the two sensors' data into its multilevel structures, which were next used to extract multilevel features representing the PD symptoms in different medication states. The extracted multilevel features were used in a classification model based on support vector machine to detect medication ON and OFF states. For comparison purposes, we implemented a traditional feature extraction method. We also developed a hierarchical feature extraction method based on the combination of those two methods. The performances of the three methods were evaluated using a dataset of 19 PD subjects with a total duration of 17.54 hours. The multilevel features achieved 8.25% improvement in the accuracy over the traditional features, and the hierarchical features resulted in 10.73% improvement indicating that our approach holds great promise to continuously detect medication states from continuous monitoring of the subjects' movement. Such information can be used by the treating physician to tailor the adjustments to each subject's unique impairment(s), thereby improving therapeutic decision-making and patient outcomes.

Estimating dyskinesia severity in Parkinson's disease by using a waist-worn sensor: concurrent validity study

Our research team previously developed an accelerometry-based device, which can be worn on the waist during daily life activities and detects the occurrence of dyskinesia in patients with Parkinson’s disease. The goal of this study was to analyze the magnitude of correlation between the numeric output of the device algorithm and the results of the Unified Dyskinesia Rating Scale (UDysRS), administered by a physician. In this study, 13 Parkinson’s patients, who were symptomatic with dyskinesias, were monitored with the device at home, for an average period of 30 minutes, while performing normal daily life activities. Each patient’s activity was simultaneously video-recorded. A physician was in charge of reviewing the recorded videos and determining the severity of dyskinesia through the UDysRS for every patient. The sensor device yielded only one value for dyskinesia severity, which was calculated by averaging the recorded device readings. Correlation between the results of physician’s assessment and the sensor output was analyzed with the Spearman’s correlation coefficient. The correlation coefficient between the sensor output and UDysRS result was 0.70 (CI 95%: 0.33–0.88; p = 0.01). Since the sensor was located on the waist, the correlation between the sensor output and the results of the trunk and legs scale sub-items was calculated: 0.91 (CI 95% 0.76–0.97: p < 0.001). The conclusion is that the magnitude of dyskinesia, as measured by the tested device, presented good correlation with that observed by a physician.

How do patients improve their timed up and go test? Responsiveness to rehabilitation of the TUG test in elderly neurological patients

BACKGROUND

The timed up and go (TUG) test is widely used for assessing treatments effectiveness on elderly mobility. Although the TUG test consists of different tasks (e.g. walking and turning), the total TUG duration (TTD) is usually the only outcome measure, with TTD shortening indicating the patient's improvement.

RESEARCH QUESTION

Does TTD shortening reflect the improvement of each TUG tasks or does it reflect the improvement of only some of them?

METHODS

This retrospective study recruited 120 elderly patients (mean, SD: 76.9, 6.6 years) admitted to inpatient rehabilitation because of an acute or chronic neurological disease (acute patients, AP; chronic patients, CP). TTD and TUG tasks duration was measured on admission and discharge (five trials/session) by means of the instrumental TUG test (ITUG). Likelihood ratios (LRs) were used for inferring TUG tasks improvement from TTD improvement. TTD and TUG tasks have improved if at least four measurements on discharge were shorter than the shortest measurement on admission.

RESULTS

TTD improvement per se is not enough to claim that all the TUG tasks have improved (LR⁺_AP = 1.32; LR⁺_CP = 1.85). Conversely, if TTD has not improved, not even a single TUG task has improved (LR^-_AP = 0.13; LR^-_CP = 0.19). If TTD has improved, there is at least one TUG task that actually improved (LR⁺_AP = 3.17; LR⁺_CP = 9.54). The improvement of all TUG tasks can be only inferred in the (unusual) event of a large TTD shortening (AP: >39%, LR⁺_AP = 6.26; CP: >30%, LR⁺_CP = 9.0).

SIGNIFICANCE

In most cases, TTD improvement is not associated with the improvement of all TUG tasks. Moreover, when TTD has improved there is at least a TUG task that has improved, but that remains unknown. To actually understand how treatments ameliorate patients' mobility, ITUG with TUG task duration measurement should be preferred to TTD.

Data-Driven Based Approach to Aid Parkinson's Disease Diagnosis

This article presents a machine learning methodology for diagnosing Parkinson's disease (PD) based on the use of vertical Ground Reaction Forces (vGRFs) data collected from the gait cycle. A classification engine assigns subjects to healthy or Parkinsonian classes. The diagnosis process involves four steps: data pre-processing, feature extraction and selection, data classification and performance evaluation. The selected features are used as inputs of each classifier. Feature selection is achieved through a wrapper approach established using the random forest algorithm. The proposed methodology uses both supervised classification methods including K-nearest neighbour (K-NN), decision tree (DT), random forest (RF), Naïve Bayes (NB), support vector machine (SVM) and unsupervised classification methods such as K-means and the Gaussian mixture model (GMM). To evaluate the effectiveness of the proposed methodology, an online dataset collected within three different studies is used. This data set includes vGRF measurements collected from eight force sensors placed under each foot of the subjects. Ninety-three patients suffering from Parkinson's disease and 72 healthy subjects participated in the experiments. The obtained performances are compared with respect to various metrics including accuracy, precision, recall and F-measure. The classification performance evaluation is performed using the leave-one-out cross validation. The results demonstrate the ability of the proposed methodology to accurately differentiate between PD subjects and healthy subjects. For the purpose of validation, the proposed methodology is also evaluated with an additional dataset including subjects with neurodegenerative diseases (Amyotrophic Lateral Sclerosis (ALS) and Huntington's disease (HD)). The obtained results show the effectiveness of the proposed methodology to discriminate PD subjects from subjects with other neurodegenerative diseases with a relatively high accuracy.

Monitoring Motor Symptoms During Activities of Daily Living in Individuals With Parkinson's Disease

This literature review addressed wearable sensor systems to monitor motor symptoms in individuals with Parkinson's disease (PD) during activities of daily living (ADLs). Specifically, progress in monitoring tremor, freezing of gait, dyskinesia, bradykinesia, and hypokinesia was reviewed. Twenty-seven studies were found that met the criteria of measuring symptoms in a home or home-like setting, with some studies examining multiple motor disorders. Accelerometers, gyroscopes, and electromyography sensors were included, with some studies using more than one type of sensor. Five studies measured tremor, five studies examined bradykinesia or hypokinesia, thirteen studies included devices to measure dyskinesia or motor fluctuations, and ten studies measured akinesia or freezing of gait. Current sensor technology can detect the presence and severity of each of these symptoms; however, most systems require sensors on multiple body parts, which is challenging for remote or ecologically valid observation. Different symptoms are detected by different sensor placement, suggesting that the goal of detecting all symptoms with a reduced set of sensors may not be achievable. For the goal of monitoring motor symptoms during ADLs in a home setting, the measurement system should be simple to use, unobtrusive to the wearer and easy for an individual with PD to put on and take off. Machine learning algorithms such as neural networks appear to be the most promising way to detect symptoms using a small number of sensors. More work should be done validating the systems during unscripted and unconstrained ADLs rather than in scripted motions.

Wearable sensors for Parkinson's disease: which data are worth collecting for training symptom detection models

Machine learning algorithms that use data streams captured from soft wearable sensors have the potential to automatically detect PD symptoms and inform clinicians about the progression of disease. However, these algorithms must be trained with annotated data from clinical experts who can recognize symptoms, and collecting such data are costly. Understanding how many sensors and how much labeled data are required is key to successfully deploying these models outside of the clinic. Here we recorded movement data using 6 flexible wearable sensors in 20 individuals with PD over the course of multiple clinical assessments conducted on 1 day and repeated 2 weeks later. Participants performed 13 common tasks, such as walking or typing, and a clinician rated the severity of symptoms (bradykinesia and tremor). We then trained convolutional neural networks and statistical ensembles to detect whether a segment of movement showed signs of bradykinesia or tremor based on data from tasks performed by other individuals. Our results show that a single wearable sensor on the back of the hand is sufficient for detecting bradykinesia and tremor in the upper extremities, whereas using sensors on both sides does not improve performance. Increasing the amount of training data by adding other individuals can lead to improved performance, but repeating assessments with the same individuals—even at different medication states—does not substantially improve detection across days. Our results suggest that PD symptoms can be detected during a variety of activities and are best modeled by a dataset incorporating many individuals.

Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab

The use of wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the accuracy achievable with such technology is highly reliant on separating the useful from irrelevant sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety of practical challenges, such as recording unexpected user behaviors. These behaviors often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab and affect the accuracy of the subsequent data analysis and scientific conclusions. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data that are sufficiently reliable for further analysis. Combining both parametric and nonparametric signal processing and machine learning techniques, we demonstrate that across 100 subjects and 300 clinimetric tests from three different types of behavioral clinimetric protocols, the system shows an average segmentation accuracy of around 90%. By extracting reliable sensor data, it is possible to strip the data of confounding factors in the environment that may threaten reproducibility and replicability.

Automated vision-based analysis of levodopa-induced dyskinesia with deep learning

Levodopa is the gold standard therapy for Parkinson's disease (PD), but its prolonged usage leads to additional motor complications, namely levodopa-induced dyskinesia (LID). To assess LID and adjust drug regimens for optimal relief, patients attend regular clinic visits. However, the intermittent nature of these visits can fail to capture important changes in a person's condition. With the recent emergence of deep learning achieving impressive results in a wide array of fields including computer vision, there is an opportunity for video analysis to be used for automated assessment of LID. Deep learning for pose estimation was studied as a viable means of extracting body movements from PD assessment videos. Movement features were computed from joint trajectories. Results show that features derived from vision-based analysis have moderate to good correlation with clinician ratings of dyskinesia severity. This study presents the first application of deep learning to video analysis in PD, and demonstrates promise for future development of a non-contact system for objective PD assessment.

Fuzzy inference model evaluating turn for Parkinson's disease patients

Parkinson's disease is a chronic illness that affects motor skills. The Unified Parkinson's Disease Rating Scale sponsored by the Movement Disorder Society (MDS-UPDRS) quantifies the current state of the disease based on clinician's observations. In this scale, turning is part of the gait assessment, yet specific guidelines on which features to observe and rate are still unclear. What is more, only visual impairment detection is used as the main subjective rating tool. In this respect, four biomechanical features are extracted from sensors worn on the lower limbs in this work. Afterwards, a turning assessment score is computed by means of a fuzzy inference model constructed based on the examiners knowledge. Overall, 46 patients with varying motor impairment severity underwent a full MDS-UPDRS motor examination and were monitored using a measurement system that includes inertial sensors on each ankle. Turning rating scores computed are reasonably consistent with examiners opinions. Nevertheless, the model proposed herein will always output the same score given the same inputs; whereas the subjective nature of examiners observations translates into uncertainty and variability in the rating scores. Furthermore, the continuous scale implemented in this work prevents the floor/ceiling effect inherent of discrete scales.

Machine learning for large-scale wearable sensor data in Parkinson's disease: Concepts, promises, pitfalls, and futures

For the treatment and monitoring of Parkinson's disease (PD) to be scientific, a key requirement is that measurement of disease stages and severity is quantitative, reliable, and repeatable. The last 50 years in PD research have been dominated by qualitative, subjective ratings obtained by human interpretation of the presentation of disease signs and symptoms at clinical visits. More recently, "wearable," sensor-based, quantitative, objective, and easy-to-use systems for quantifying PD signs for large numbers of participants over extended durations have been developed. This technology has the potential to significantly improve both clinical diagnosis and management in PD and the conduct of clinical studies. However, the large-scale, high-dimensional character of the data captured by these wearable sensors requires sophisticated signal processing and machine-learning algorithms to transform it into scientifically and clinically meaningful information. Such algorithms that "learn" from data have shown remarkable success in making accurate predictions for complex problems in which human skill has been required to date, but they are challenging to evaluate and apply without a basic understanding of the underlying logic on which they are based. This article contains a nontechnical tutorial review of relevant machine-learning algorithms, also describing their limitations and how these can be overcome. It discusses implications of this technology and a practical road map for realizing the full potential of this technology in PD research and practice. © 2016 International Parkinson and Movement Disorder Society.

Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer

BACKGROUND

After several years of treatment, patients with Parkinson's disease (PD) tend to have, as a side effect of the medication, dyskinesias. Close monitoring may benefit patients by enabling doctors to tailor a personalised medication regimen. Moreover, dyskinesia monitoring can help neurologists make more informed decisions in patient's care.

OBJECTIVE

To design and validate an algorithm able to be embedded into a system that PD patients could wear during their activities of daily living with the purpose of registering the occurrence of dyskinesia in real conditions.

MATERIALS AND METHODS

Data from an accelerometer positioned in the waist are collected at the patient's home and are annotated by experienced clinicians. Data collection is divided into two parts: a main database gathered from 92 patients used to partially train and to evaluate the algorithms based on a leave-one-out approach and, on the other hand, a second database from 10 patients which have been used to also train a part of the detection algorithm.

RESULTS

Results show that, depending on the severity and location of dyskinesia, specificities and sensitivities higher than 90% are achieved using a leave-one-out methodology. Although mild dyskinesias presented on the limbs are detected with 95% specificity and 39% sensitivity, the most important types of dyskinesia (any strong dyskinesia and trunk mild dyskinesia) are assessed with 95% specificity and 93% sensitivity.

CONCLUSION

The presented algorithmic method and wearable device have been successfully validated in monitoring the occurrence of strong dyskinesias and mild trunk dyskinesias during activities of daily living.

A data mining methodology for predicting early stage Parkinson's disease using non-invasive, high-dimensional gait sensor data

Parkinson's disease (PD) is the second most common neurological disorder after Alzheimer's disease. Key clinical features of PD are motor-related and are typically assessed by healthcare providers based on qualitative visual inspection of a patient's movement/gait/posture. More advanced diagnostic techniques such as computed tomography scans that measure brain function, can be cost prohibitive and may expose patients to radiation and other harmful effects. To mitigate these challenges, and open a pathway to remote patient-physician assessment, the authors of this work propose a data mining driven methodology that uses low cost, non-invasive sensors to model and predict the presence (or lack therefore) of PD movement abnormalities and model clinical subtypes. The study presented here evaluates the discriminative ability of non-invasive hardware and data mining algorithms to classify PD cases and controls. A 10-fold cross validation approach is used to compare several data mining algorithms in order to determine that which provides the most consistent results when varying the subject gait data. Next, the predictive accuracy of the data mining model is quantified by testing it against unseen data captured from a test pool of subjects. The proposed methodology demonstrates the feasibility of using non-invasive, low cost, hardware and data mining models to monitor the progression of gait features outside of the traditional healthcare facility, which may ultimately lead to earlier diagnosis of emerging neurological diseases.

Wearable accelerometry-based technology capable of assessing functional activities in neurological populations in community settings: a systematic review

BACKGROUND

Integrating rehabilitation services through wearable systems has the potential to accurately assess the type, intensity, duration, and quality of movement necessary for procuring key outcome measures.

OBJECTIVES

This review aims to explore wearable accelerometry-based technology (ABT) capable of assessing mobility-related functional activities intended for rehabilitation purposes in community settings for neurological populations. In this review, we focus on the accuracy of ABT-based methods, types of outcome measures, and the implementation of ABT in non-clinical settings for rehabilitation purposes.

DATA SOURCES

Cochrane, PubMed, Web of Knowledge, EMBASE, and IEEE Xplore. The search strategy covered three main areas, namely wearable technology, rehabilitation, and setting.

STUDY SELECTION

Potentially relevant studies were categorized as systems either evaluating methods or outcome parameters.

METHODS

Methodological qualities of studies were assessed by two customized checklists, depending on their categorization and rated independently by three blinded reviewers.

RESULTS

Twelve studies involving ABT met the eligibility criteria, of which three studies were identified as having implemented ABT for rehabilitation purposes in non-clinical settings. From the twelve studies, seven studies achieved high methodological quality scores. These studies were not only capable of assessing the type, quantity, and quality measures of functional activities, but could also distinguish healthy from non-healthy subjects and/or address disease severity levels.

CONCLUSION

While many studies support ABT's potential for telerehabilitation, few actually utilized it to assess mobility-related functional activities outside laboratory settings. To generate more appropriate outcome measures, there is a clear need to translate research findings and novel methods into practice.

Quantitative assessment of levodopa-induced dyskinesia using automated motion sensing technology

The objective was to capture levodopa-induced dyskinesia (LID) in patients with Parkinson's disease (PD) using body-worn motion sensors. Dopaminergic treatment in PD can induce abnormal involuntary movements, including choreatic dyskinesia (brief, rapid, irregular movements). Adjustments in medication to reduce LID often sacrifice control of motor symptoms, and balancing this tradeoff poses a significant challenge for management of advanced PD. Fifteen PD subjects with known LID were recruited and instructed to perform two stationary motor tasks while wearing a compact wireless motion sensor unit positioned on each hand over the course of a levodopa dose cycle. Videos of subjects performing the motor tasks were later scored by expert clinicians to assess global dyskinesia using the modified Abnormal Involuntary Rating Scale (m-AIMS). Kinematic features were extracted from motion data in different frequency bands (1-3Hz and 3-8Hz) to quantify LID severity and to distinguish between LID and PD tremor. Receiver operator characteristic analysis was used to determine thresholds for individual features to detect the presence of LID. A sensitivity of 0.73 and specificity of 1.00 were achieved. A neural network was also trained to output dyskinesia severity on a 0 to 4 scale, similar to the m-AIMS. The model generalized well to new data (coefficient of determination= 0.85 and mean squared error= 0.3). This study demonstrated that hand-worn motion sensors can be used to assess global dyskinesia severity independent of PD tremor over the levodopa dose cycle.

Combined analysis of sensor data from hand and gait motor function improves automatic recognition of Parkinson's disease

Objective and rater independent analysis of movement impairment is one of the most challenging tasks in medical engineering. Especially assessment of motor symptoms defines the clinical diagnosis in Parkinson's disease (PD). A sensor-based system to measure the movement of the upper and lower extremities would therefore complement the clinical evaluation of PD. In this study two different sensor-based systems were combined to assess movement of 18 PD patients and 17 healthy controls. First, hand motor function was evaluated using a sensor pen with integrated accelerometers and pressure sensors, and second, gait function was assessed using a sports shoe with attached inertial sensors (gyroscopes,accelerometers).Subjects performed standardized tests for both extremities.Features were calculated from sensor signals to differentiate between patients and controls. For the latter, pattern recognition methods were used and the performance of four classifiers was compared. In a first step classification was done for every single system and in a second step for combined features of both systems. Combination of both motor task assessments substantially improved classification rates to 97%using the AdaBoost classifier for the experiment patients vs.controls.The combination of two different analysis systems led to enhanced, more stable, objective, and rater independent recognition of motor impairment. The method can be used as a complementary diagnostic tool for movement disorders.

Full body gait analysis with Kinect

Human gait is an important indicator of health, with applications ranging from diagnosis, monitoring, and rehabilitation. In practice, the use of gait analysis has been limited. Existing gait analysis systems are either expensive, intrusive, or require well-controlled environments such as a clinic or a laboratory. We present an accurate gait analysis system that is economical and non-intrusive. Our system is based on the Kinect sensor and thus can extract comprehensive gait information from all parts of the body. Beyond standard stride information, we also measure arm kinematics, demonstrating the wide range of parameters that can be extracted. We further improve over existing work by using information from the entire body to more accurately measure stride intervals. Our system requires no markers or battery-powered sensors, and instead relies on a single, inexpensive commodity 3D sensor with a large preexisting install base. We suggest that the proposed technique can be used for continuous gait tracking at home.

High-resolution tracking of motor disorders in Parkinson's disease during unconstrained activity

Parkinson's disease (PD) can present with a variety of motor disorders that fluctuate throughout the day, making assessment a challenging task. Paper-based measurement tools can be burdensome to the patient and clinician and lack the temporal resolution needed to accurately and objectively track changes in motor symptom severity throughout the day. Wearable sensor-based systems that continuously monitor PD motor disorders may help to solve this problem, although critical shortcomings persist in identifying multiple disorders at high temporal resolution during unconstrained activity. The purpose of this study was to advance the current state of the art by (1) introducing hybrid sensor technology to concurrently acquire surface electromyographic (sEMG) and accelerometer data during unconstrained activity and (2) analyzing the data using dynamic neural network algorithms to capture the evolving temporal characteristics of the sensor data and improve motor disorder recognition of tremor and dyskinesia. Algorithms were trained (n=11 patients) and tested (n=8 patients; n=4 controls) to recognize tremor and dyskinesia at 1-second resolution based on sensor data features and expert annotation of video recording during 4-hour monitoring periods of unconstrained daily activity. The algorithms were able to make accurate distinctions between tremor, dyskinesia, and normal movement despite the presence of diverse voluntary activity. Motor disorder severity classifications averaged 94.9% sensitivity and 97.1% specificity based on 1 sensor per symptomatic limb. These initial findings indicate that new sensor technology and software algorithms can be effective in enhancing wearable sensor-based system performance for monitoring PD motor disorders during unconstrained activities.

IEEE802.15.6 -based multi-accelerometer WBAN system for monitoring Parkinson's disease

In this paper we present a detailed example of a wireless body area network (WBAN) scenario utilizing the recent IEEE802.15.6 standard as applied to a multi-accelerometer system for monitoring Parkinson's disease and fall detection. Ultra wideband physical layer and standard security protocols are applied to meet application requirements for data rate and security.

Validating an objective video-based dyskinesia severity score in Parkinson's disease patients

Dyskinesia is a common side effect of prolonged dopaminergic therapy in Parkinson's disease patients. Assessing the severity of dyskinesia could help develop better pharmacological and surgical interventions. We have developed a semi-automatic video-based objective dyskinesia quantifying measure called the severity score (SVS) that was evaluated on 35 patient videos. We present a study to evaluate the utility of our severity score and compare its performance to clinical ratings of neurologists. In addition to the Unified Dyskinesia Rating Scale (UDysRS) score for each video, four neurologists provided three sets of time lapsed ratings and rankings of the 35 videos using a specifically developed protocol. The statistical analysis of our data using Kendall's tau-b and intra-class correlations shows that (a) ranking patient videos based on severity is suitable for studying the utility of the SVS, and (b) SVS exhibits moderate utility to quantify dyskinesia severity when compared to manual assessment of dyskinesia by neurologists using the UDysRS. These results support the effective use of SVS as an objective measure to quantify dyskinesia and the rationale for a ranking system that complements traditional rating scales.

Deficits in scaling of gait force and cycle in parkinsonian gait identified by long-term monitoring of acceleration with the portable gait rhythmogram

To examine the range of gait acceleration and cycle in daily walking of patients with Parkinson's disease (PD), we compared the gait of 40 patients with PD and 17 normal controls by using a newly developed long-term monitoring device that extracts gait-related accelerations from overall movements-related accelerations. The range of change in gait acceleration, relative to the control, was less than 75% in 12 patients. The range of change in gait cycle was less than 75% in 8 patients. The range of changes in both parameters was less than 75% in 4 patients. The results suggest narrow changes in gait parameters in PD.

BDNF Val66Met and spontaneous dyskinesias in non-clinical psychosis

BACKGROUND

Evidence indicating that symptoms of non-clinical psychosis (NCP) occur in 6-8% of the general population suggests that psychosis may occur across a continuum. Although a number of studies have examined environmental contributors, to date there have been few investigations of biological/genetic factors in this integral population. A recent study observed spontaneous dyskinetic movements (reflecting an innervated striatal system) in individuals reporting NCP. The present investigation is designed to replicate this finding and determine if brain-derived neurotrophic factor (BDNF) (implicated in striatal dopamine function) is associated with dyskinesias.

METHOD

A total of 68 young-adult participants reporting High and Low-NCP were assessed for dyskinetic movements using a sensitive instrumental measure of force variability. Saliva from the participants was genotyped for val66met (rs6265), a common functional polymorphism of the BDNF gene (the Met allele is associated with lower activity-dependent release of BDNF).

RESULTS

Participants in the High-NCP group showed significantly elevated levels of force variability. Met allele carriers exhibited significantly higher levels of force variability when compared with the Val homozygotes. Logistic regression indicated that the odds of membership in the High-NCP group were significantly higher given the presence of dyskinesias (OR=2.32; CI: 1.25-4.28).

CONCLUSION

Findings of elevated force variability suggest that individuals with NCP exhibit subtle signs of striatal vulnerability, reflected more dramatically as jerking and hyperkinetic movements in patients with formal psychosis. The results are consistent with a larger literature implicating BDNF as a critical factor underlying abnormal movements, and suggest that specific candidate genes underlie putative markers across a psychosis continuum.

Quantitative measurement of motor symptoms in Parkinson's disease: a study with full-body motion capture data

Recent advancements in the portability and affordability of optical motion capture systems have opened the doors to various clinical applications. In this paper, we look into the potential use of motion capture data for the quantitative analysis of motor symptoms in Parkinson's Disease (PD). The standard of care, human observer-based assessments of the motor symptoms, can be very subjective and are often inadequate for tracking mild symptoms. Motion capture systems, on the other hand, can potentially provide more objective and quantitative assessments. In this pilot study, we perform full-body motion capture of Parkinson's patients with deep brain stimulator off-drugs and with stimulators on and off. Our experimental results indicate that the quantitative measure on spatio-temporal statistics learnt from the motion capture data reveal distinctive differences between mild and severe symptoms. We used a Support Vector Machine (SVM) classifier for discriminating mild vs. severe symptoms with an average accuracy of approximately 90%. Finally, we conclude that motion capture technology could potentially be an accurate, reliable and effective tool for statistical data mining on motor symptoms related to PD. This would enable us to devise more effective ways to track the progression of neurodegenerative movement disorders.

Wearable medical systems for p-Health

Driven by the growing aging population, prevalence of chronic diseases, and continuously rising healthcare costs, the healthcare system is undergoing a fundamental transformation, from the conventional hospital-centered system to an individual-centered system. Current and emerging developments in wearable medical systems will have a radical impact on this paradigm shift. Advances in wearable medical systems will enable the accessibility and affordability of healthcare, so that physiological conditions can be monitored not only at sporadic snapshots but also continuously for extended periods of time, making early disease detection and timely response to health threats possible. This paper reviews recent developments in the area of wearable medical systems for p-Health. Enabling technologies for continuous and noninvasive measurements of vital signs and biochemical variables, advances in intelligent biomedical clothing and body area networks, approaches for motion artifact reduction, strategies for wearable energy harvesting, and the establishment of standard protocols for the evaluation of wearable medical devices are presented in this paper with examples of clinical applications of these technologies.

Objective measure of upper extremity motor impairment in Parkinson's disease with inertial sensors

Functional motor impairment caused by Parkinson's disease and other movement disorders is currently measured with rating scales such as the Unified Parkinson's Disease Rating Scale (UPDRS). These are typically comprised of a series of simple tasks that are visually scored by a trained rater. We developed a method to objectively quantify three upper extremity motor tasks directly with a wearable inertial sensor. Specifically, we used triaxial gyroscopes and adaptive filters to quantify how predictable and regular the signals were. We found that simply using the normalized mean squared error (NMSE) as a test statistic permitted us to distinguish between subjects with and without Parkinson's disease who were matched for age, height, and weight. A forward linear predictor based on the Kalman filter was able to attain areas under the curve (AUC) in receiver operator characteristic (ROC) curves in the range of 0.76 to 0.83. Further studies and development are warranted. This technology has the potential to more accurately measure the motor signs of Parkinson's disease. This may reduce statistical bias and variability of rating scales, which could lead to trials with fewer subjects, less cost, and shorter duration.

An automated methodology for levodopa-induced dyskinesia: assessment based on gyroscope and accelerometer signals

OBJECTIVE

In this study, a methodology is presented for an automated levodopa-induced dyskinesia (LID) assessment in patients suffering from Parkinson's disease (PD) under real-life conditions.

METHODS AND MATERIAL

The methodology is based on the analysis of signals recorded from several accelerometers and gyroscopes, which are placed on the subjects' body while they were performing a series of standardised motor tasks as well as voluntary movements. Sixteen subjects were enrolled in the study. The recordings were analysed in order to extract several features and, based on these features, a classification technique was used for LID assessment, i.e. detection of LID symptoms and classification of their severity.

RESULTS

The results were compared with the clinical annotation of the signals, provided by two expert neurologists. The analysis was performed related to the number and topology of sensors used; several different experimental settings were evaluated while a 10-fold stratified cross validation technique was employed in all cases. Moreover, several different classification techniques were examined. The ability of the methodology to be generalised was also evaluated using leave-one-patient-out cross validation. The sensitivity and positive predictive values (average for all LID severities) were 80.35% and 76.84%, respectively.

CONCLUSIONS

The proposed methodology can be applied in real-life conditions since it can perform LID assessment in recordings which include various PD symptoms (such as tremor, dyskinesia and freezing of gait) of several motor tasks and random voluntary movements.

Movement abnormalities and psychotic-like experiences in childhood: markers of developing schizophrenia?

BACKGROUND

Both involuntary dyskinetic movements and psychotic-like experiences (PLEs) are reported to be antecedents of schizophrenia that may reflect dysfunctional dopaminergic activity in the striatum. The present study compared dyskinetic movement abnormalities displayed by children with multiple antecedents of schizophrenia (ASz), including speech and/or motor developmental lags or problems, internalising/externalising problems in the clinical range, and PLEs, with those displayed by children with no antecedents (noASz).

METHOD

The sample included 21 ASz and 31 noASz children, aged 9-12 years old. None had taken psychotropic medication or had relatives with psychosis. The antecedents of schizophrenia were assessed using questionnaires completed by children and caregivers. A trained rater, blind to group status, coded dyskinetic movement abnormalities using a validated tool from videotapes of interviews with the children.

RESULTS

ASz children reported, on average, 'certain experience' of 2.5 PLEs, while noASz children, by definition, reported none. The ASz children, as compared with noASz children, displayed significantly more dyskinetic movement abnormalities in total, and in the facial and the upper-body regions, after controlling for sex and age. Receiver operator characteristics analyses yielded high area under the curve values for the total score (0.94), facial score (0.91) and upper-body score (0.86), indicating that these scores distinguished between the ASz and noASz children with great accuracy.

CONCLUSIONS

Brief questionnaires identified children with multiple antecedents of schizophrenia who displayed significantly more involuntary dyskinetic movement abnormalities than children without antecedents. The presence of PLEs and dyskinesias could reflect early disruption of striatal dopamine circuits.

Validation of 24-hour ambulatory gait assessment in Parkinson's disease with simultaneous video observation

Background

Parkinson's disease (PD) is a neurodegenerative disorder resulting in motor disturbances that can impact normal gait. Although PD initially responds well to pharmacological treatment, as the disease progresses efficacy often fluctuates over the course of the day, and clinical management would benefit from long-term objective measures of gait. We have previously described a small device worn on the shank that uses acceleration and angular velocity sensors to calculate stride length and identify freezing of gait in PD patients. In this study we extend validation of the gait monitor to 24-h using simultaneous video observation of PD patients.

Methods

A sleep laboratory was adapted to perform 24-hr video monitoring of patients while wearing the device. Continuous video monitoring of a sleep lab, hallway, kitchen and conference room was performed using a 4-camera security system and recorded to hard disk. Subjects (3) wore the gait monitor on the left shank (just above the ankle) for a 24-h period beginning around 5 pm in the evening. Accuracy of stride length measures were assessed at the beginning and end of the 24-h epoch. Two independent observers rated the video logs to identify when subjects were walking or lying down.

Results

The mean error in stride length at the start of recording was 0.05 m (SD 0) and at the conclusion of the 24 h epoch was 0.06 m (SD 0.026). There was full agreement between observer coding of the video logs and the output from the gait monitor software; that is, for every video observation of the subject walking there was a corresponding pulse in the monitor data that indicated gait.

Conclusions

The accuracy of ambulatory stride length measurement was maintained over the 24-h period, and there was 100% agreement between the autonomous detection of locomotion by the gait monitor and video observation.

On automated assessment of Levodopa-induced dyskinesia in Parkinson's disease

A method for the analysis of accelerometer and gyroscope signals in order to automatically assess the Levodopa-induced dyskinesia (LID) in patients with Parkinson's disease is presented in this paper. Several accelerometers and gyroscopes are placed on certain positions on the subject's body and the obtained signals are analyzed in order to extract several features that depict the energy distribution over the frequency spectrum and the non-linear properties of the signal. These features are fed into an artificial neural network which is used for LID detection and severity classification. The method has been evaluated using a group of 29 subjects. Results are presented related to the body locations that the accelerometers and the gyroscopes are placed. The obtained results indicate high classification ability (84.3% average classification accuracy).

Ambulatory monitoring of activities and motor symptoms in Parkinson's disease

Ambulatory monitoring of motor symptoms in Parkinsons disease (PD) can improve our therapeutic strategies, especially in patients with motor fluctuations. Previously published monitors usually assess only one or a few basic aspects of the cardinal motor symptoms in a laboratory setting. We developed a novel ambulatory monitoring system that provides a complete motor assessment by simultaneously analyzing current motor activity of the patient (e.g. sitting, walking) and the severity of many aspects related to tremor, bradykinesia, and hypokinesia. The monitor consists of a set of four inertial sensors. Validity of our monitor was established in seven healthy controls and six PD patients treated with deep brain stimulation (DBS) of the subthalamic nucleus. Patients were tested at three different levels of DBS treatment. Subjects were monitored while performing different tasks, including motor tests of the Unified Parkinsons Disease Rating Scale (UPDRS). Output of the monitor was compared to simultaneously recorded videos. The monitor proved very accurate in discriminating between several motor activities. Monitor output correlated well with blinded UPDRS ratings during different DBS levels. The combined analysis of motor activity and symptom severity by our PD monitor brings true ambulatory monitoring of a wide variety of motor symptoms one step closer..

Intra- and inter-limb coherency during stance in non-dyskinetic and dyskinetic patients with Parkinson's disease

OBJECTIVE

Examine the level of intra- and inter-limb coherency in non-dyskinetic and dyskinetic patients with Parkinson's disease (PD).

PATIENTS & METHODS

Using a magnetic tracking system, whole-body 3D movements were assessed in 10 dyskinetic patients with clear monophasic peak-dose levodopa-induced dyskinesia (LID), in 10 non-dyskinetic patients and in 10 control subjects, standing with their arms out. Patients were tested during their best ON period. Coherency in the kinematics of pairs of body segments was assessed by spectral analysis. For each pair examined, we calculated the highest coherency between 0.5 and 3.0Hz and the frequency at which this maximum coherency occurred.

RESULTS

Analysis of variance showed that for 34 out of the 44 (77.3%) comparisons we studied, there were significant differences between the means of coherencies of the groups. Typically, the control group had the highest coherency and the patients with LID had the lowest. Patients with LID also tended to have their maximum coherency at higher frequencies than the control and non-dyskinetic patient groups (30 out of 44 comparisons were significant). These trends appeared in all types of inter-segment comparisons, including bilaterally symmetric segments, biomechanically linked segments (in which coherencies were higher overall in all groups, but still different between groups) and in other comparisons, but the trends were not so clear for comparisons involving the feet.

CONCLUSION

LID is indeed incoherent in the frequency domain, suggesting that body segments may be driven by different neural outputs. The challenges of dealing with these incoherent involuntary movements when planning and executing voluntary movements must certainly play a role in motor difficulties observed in patients with LID. The fact that both dyskinetic and non-dyskinetic patients showed less coherency than controls suggests that levodopa may alter postural control by decreasing stiffness and increasing limb independence.

24-hour recording of parkinsonian gait using a portable gait rhythmogram

OBJECTIVE

In the advanced stage of Parkinson's disease (PD), motor fluctuation is a frequent and a disabling problem. Despite its importance, motor fluctuation has received little scientific analysis probably due to limitation in objective assessment. Here, we focused on gait disorders to estimate motor fluctuation in daily activities.

PATIENTS AND METHODS

Using a new device, the portable gait rhythmogram, we recorded gait rhythm continuously over 24 hours in 22 patients with PD and in 11 normal controls, for quantitative evaluation of motor fluctuation. The duration of one gait cycle was measured.

RESULTS

Continuous 24-hour recording identified changes in gait rhythm, which correlated with fluctuation of PD symptoms. Different motor fluctuations were observed; a shift to a faster gait cycle was noted in patients with short-step walking, festination or freezing of gait, whereas a shift to a slower gait cycle was observed in patients with bradykinesia or instability.

CONCLUSION

Characterization of motor fluctuation using this device could help in the selection of appropriate anti-PD medications.