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

Multi-Shared-Task Self-Supervised CNN-LSTM for Monitoring Free-Body Movement UPDRS-III Using Wearable Sensors

The Unified Parkinson's Disease Rating Scale (UPDRS) is used to recognize patients with Parkinson's disease (PD) and rate its severity. The rating is crucial for disease progression monitoring and treatment adjustment. This study aims to advance the capabilities of PD management by developing an innovative framework that integrates deep learning with wearable sensor technology to enhance the precision of UPDRS assessments. We introduce a series of deep learning models to estimate UPDRS Part III scores, utilizing motion data from wearable sensors. Our approach leverages a novel Multi-shared-task Self-supervised Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) framework that processes raw gyroscope signals and their spectrogram representations. This technique aims to refine the estimation accuracy of PD severity during naturalistic human activities. Utilizing 526 min of data from 24 PD patients engaged in everyday activities, our methodology demonstrates a strong correlation of 0.89 between estimated and clinically assessed UPDRS-III scores. This model outperforms the benchmark set by single and multichannel CNN, LSTM, and CNN-LSTM models and establishes a new standard in UPDRS-III score estimation for free-body movements compared to recent state-of-the-art methods. These results signify a substantial step forward in bioengineering applications for PD monitoring, providing a robust framework for reliable and continuous assessment of PD symptoms in daily living settings.

Devices for remote continuous monitoring of people with Parkinson's disease: a systematic review and cost-effectiveness analysis

Background

Parkinson's disease is a brain condition causing a progressive loss of co ordination and movement problems. Around 145,500 people have Parkinson's disease in the United Kingdom. Levodopa is the most prescribed treatment for managing motor symptoms in the early stages. Patients should be monitored by a specialist every 6-12 months for disease progression and treatment of adverse effects. Wearable devices may provide a novel approach to management by directly monitoring patients for bradykinesia, dyskinesia, tremor and other symptoms. They are intended to be used alongside clinical judgement.

Objectives

To determine the clinical and cost-effectiveness of five devices for monitoring Parkinson's disease: Personal KinetiGraph, Kinesia 360, KinesiaU, PDMonitor and STAT-ON.

Methods

We performed systematic reviews of all evidence on the five devices, outcomes included: diagnostic accuracy, impact on decision-making, clinical outcomes, patient and clinician opinions and economic outcomes. We searched MEDLINE and 12 other databases/trial registries to February 2022. Risk of bias was assessed. Narrative synthesis was used to summarise all identified evidence, as the evidence was insufficient for meta-analysis. One included trial provided individual-level data, which was re-analysed. A de novo decision-analytic model was developed to estimate the cost-effectiveness of Personal KinetiGraph and Kinesia 360 compared to standard of care in the UK NHS over a 5-year time horizon. The base-case analysis considered two alternative monitoring strategies: one-time use and routine use of the device.

Results

Fifty-seven studies of Personal KinetiGraph, 15 of STAT-ON, 3 of Kinesia 360, 1 of KinesiaU and 1 of PDMonitor were included. There was some evidence to suggest that Personal KinetiGraph can accurately measure bradykinesia and dyskinesia, leading to treatment modification in some patients, and a possible improvement in clinical outcomes when measured using the Unified Parkinson's Disease Rating Scale. The evidence for STAT-ON suggested it may be of value for diagnosing symptoms, but there is currently no evidence on its clinical impact. The evidence for Kinesia 360, KinesiaU and PDMonitor is insufficient to draw any conclusions on their value in clinical practice. The base-case results for Personal KinetiGraph compared to standard of care for one-time and routine use resulted in incremental cost-effectiveness ratios of £67,856 and £57,877 per quality-adjusted life-year gained, respectively, with a beneficial impact of the Personal KinetiGraph on Unified Parkinson's Disease Rating Scale domains III and IV. The incremental cost-effectiveness ratio results for Kinesia 360 compared to standard of care for one-time and routine use were £38,828 and £67,203 per quality-adjusted life-year gained, respectively.

Limitations

The evidence was limited in extent and often low quality. For all devices, except Personal KinetiGraph, there was little to no evidence on the clinical impact of the technology.

Conclusions

Personal KinetiGraph could reasonably be used in practice to monitor patient symptoms and modify treatment where required. There is too little evidence on STAT-ON, Kinesia 360, KinesiaU or PDMonitor to be confident that they are clinically useful. The cost-effectiveness of remote monitoring appears to be largely unfavourable with incremental cost-effectiveness ratios in excess of £30,000 per quality-adjusted life-year across a range of alternative assumptions. The main driver of cost-effectiveness was the durability of improvements in patient symptoms.

Study registration

This study is registered as PROSPERO CRD42022308597.

Funding

This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR135437) and is published in full in Health Technology Assessment; Vol. 28, No. 30. See the NIHR Funding and Awards website for further award information.

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.

Overview on wearable sensors for the management of Parkinson's disease

Parkinson's disease (PD) is affecting about 1.2 million patients in Europe with a prevalence that is expected to have an exponential increment, in the next decades. This epidemiological evolution will be challenged by the low number of neurologists able to deliver expert care for PD. As PD is better recognized, there is an increasing demand from patients for rigorous control of their symptoms and for therapeutic education. In addition, the highly variable nature of symtoms between patients and the fluctuations within the same patient requires innovative tools to help doctors and patients monitor the disease in their usual living environment and adapt treatment in a more relevant way. Nowadays, there are various body-worn sensors (BWS) proposed to monitor parkinsonian clinical features, such as motor fluctuations, dyskinesia, tremor, bradykinesia, freezing of gait (FoG) or gait disturbances. BWS have been used as add-on tool for patients' management or research purpose. Here, we propose a practical anthology, summarizing the characteristics of the most used BWS for PD patients in Europe, focusing on their role as tools to improve treatment management. Consideration regarding the use of technology to monitor non-motor features is also included. BWS obviously offer new opportunities for improving management strategy in PD but their precise scope of use in daily routine care should be clarified.

Objective measurement versus clinician-based assessment for Parkinson's disease

INTRODUCTION

Although clinician-based assessment through standardized clinical rating scales is currently the gold standard for quantifying motor impairment in Parkinson's disease (PD), it is not without limitations, including intra- and inter-rater variability and a degree of approximation. There is increasing evidence supporting the use of objective motion analyses to complement clinician-based assessment. Objective measurement tools hold significant potential for improving the accuracy of clinical and research-based evaluations of patients.

AREAS COVERED

The authors provide several examples from the literature demonstrating how different motion measurement tools, including optoelectronics, contactless and wearable systems allow for both the objective quantification and monitoring of key motor symptoms (such as bradykinesia, rigidity, tremor, and gait disturbances), and the identification of motor fluctuations in PD patients. Furthermore, they discuss how, from a clinician's perspective, objective measurements can help in various stages of PD management.

EXPERT OPINION

In our opinion, sufficient evidence supports the assertion that objective monitoring systems enable accurate evaluation of motor symptoms and complications in PD. A range of devices can be utilized not only to support diagnosis but also to monitor motor symptom during the disease progression and can become relevant in the therapeutic decision-making process.

Real-time detection of freezing of gait in Parkinson's disease using multi-head convolutional neural networks and a single inertial sensor

BACKGROUND

Freezing of gait (FOG) is one of the most disabling symptoms of Parkinson's disease (PD), contributing to poor quality of life and increased risk of falls. Wearable sensors represent a valuable means for detecting FOG in the home environment. Moreover, real-time feedback has proven to help reduce the duration of FOG episodes. This work proposes a robust real-time FOG detection algorithm, which is easy to implement in stand-alone devices working in non-supervised conditions.

METHOD

Data from three different data sets were used in this study, with two employed as independent test sets. Acceleration recordings from 118 PD patients and 21 healthy elderly subjects were collected while they performed simulated daily living activities. A single inertial sensor was attached to the waist of each subject. More than 17 h of valid data and a total number of 1110 FOG episodes were analyzed in this study. The implemented algorithm consisted of a multi-head convolutional neural network, which exploited different spatial resolutions in the analysis of inertial data. The architecture and the model parameters were designed to provide optimal performance while reducing computational complexity and testing time.

RESULTS

The developed algorithm demonstrated good to excellent classification performance, with more than 50% (30%) of FOG episodes predicted on average 3.1 s (1.3 s) before the actual onset in the main (independent) data set. Around 50% of FOG was detected with an average delay of 0.8 s (1.1 s) in the main (independent) data set. Moreover, a specificity above 88% (93%) was obtained when testing the algorithm on the main (independent) test set, while 100% specificity was obtained on healthy elderly subjects.

CONCLUSION

The algorithm proved robust, with low computational complexity and processing time, thus paving the way to a real-time implementation in a stand-alone device that can be used in non-supervised environments.

Deep Clinical Phenotyping of Parkinson's Disease: Towards a New Era of Research and Clinical Care

Despite recent advances in technology, clinical phenotyping of Parkinson's disease (PD) has remained relatively limited as current assessments are mainly based on empirical observation and subjective categorical judgment at the clinic. A lack of comprehensive, objective, and quantifiable clinical phenotyping data has hindered our capacity to diagnose, assess patients' conditions, discover pathogenesis, identify preclinical stages and clinical subtypes, and evaluate new therapies. Therefore, deep clinical phenotyping of PD patients is a necessary step towards understanding PD pathology and improving clinical care. In this review, we present a growing community consensus and perspective on how to clinically phenotype this disease, that is, to phenotype the entire course of disease progression by integrating capacity, performance, and perception approaches with state-of-the-art technology. We also explore the most studied aspects of PD deep clinical phenotypes, namely, bradykinesia, tremor, dyskinesia and motor fluctuation, gait impairment, speech impairment, and non-motor phenotypes.

Sensor Verification and Analytical Validation of Algorithms to Measure Gait and Balance and Pronation/Supination in Healthy Volunteers

Numerous studies have sought to demonstrate the utility of digital measures of motor function in Parkinson’s disease. Frameworks, such as V3, document digital measure development: technical verification, analytical and clinical validation. We present the results of a study to (1) technically verify accelerometers in an Apple iPhone 8 Plus and ActiGraph GT9X versus an oscillating table and (2) analytically validate software tasks for walking and pronation/supination on the iPhone plus passively detect walking measures with the ActiGraph in healthy volunteers versus human raters. In technical verification, 99.4% of iPhone and 91% of ActiGraph tests show good or excellent agreement versus the oscillating table as the gold standard. For the iPhone software task and algorithms, intraclass correlation coefficients (ICCs) > 0.75 are achieved versus the human raters for measures when walking distance is >10 s and pronation/supination when the arm is rotated more than two times. Passively detected walking start and end time was accurate to approx. 1 s and walking measures were accurate to one unit, e.g., one step. The results suggest that the Apple iPhone and ActiGraph GT9X accelerometers are fit for purpose and that task and passively collected measures are sufficiently analytically valid to assess usability and clinical validity in Parkinson’s patients.

Hands-feet wireless devices: Test-retest reliability and discriminant validity of motor measures in Parkinson's disease telemonitoring

BACKGROUND

Telemonitoring, a branch of telemedicine, involves the use of technological tools to remotely detect clinical data and evaluate patients. Telemonitoring of patients with Parkinson's disease (PD) should be performed using reliable and discriminant motor measures. Furthermore, the method of data collection and transmission, and the type of subjects suitable for telemonitoring must be well defined.

OBJECTIVE

To analyze differences in patients with PD and healthy controls (HC) with the wearable inertial device SensHands-SensFeet (SH-SF), adopting a standardized acquisition mode, to verify if motor measures provided by SH-SF have a high discriminating capacity and high intraclass correlation coefficient (ICC).

METHODS

Altogether, 64 patients with mild-to-moderate PD and 50 HC performed 14 standardized motor activities for assessing bradykinesia, postural and resting tremors, and gait parameters. SH-SF inertial devices were used to acquire movements and calculate objective motor measures of movement (total: 75). For each motor task, five or more biomechanical parameters were measured twice. The results were compared between patients with PD and HC.

RESULTS

Fifty-eight objective motor measures significantly differed between patients with PD and HC; among these, 32 demonstrated relevant discrimination power (Cohen's d > 0.8). The test-retest reliability was excellent in patients with PD (median ICC = 0.85 right limbs, 0.91 left limbs) and HC (median ICC = 0.78 right limbs, 0.82 left limbs).

CONCLUSION

In a supervised environment, the SH-SF device provides motor measures with good results in terms of reliability and discriminant ability. The reliability of SH-SF measurements should be evaluated in an unsupervised home setting in future studies.

Home-Based Measurements of Dystonia in Cerebral Palsy Using Smartphone-Coupled Inertial Sensor Technology and Machine Learning: A Proof-of-Concept Study

Accurate and reliable measurement of the severity of dystonia is essential for the indication, evaluation, monitoring and fine-tuning of treatments. Assessment of dystonia in children and adolescents with dyskinetic cerebral palsy (CP) is now commonly performed by visual evaluation either directly in the doctor’s office or from video recordings using standardized scales. Both methods lack objectivity and require much time and effort of clinical experts. Only a snapshot of the severity of dyskinetic movements (i.e., choreoathetosis and dystonia) is captured, and they are known to fluctuate over time and can increase with fatigue, pain, stress or emotions, which likely happens in a clinical environment. The goal of this study was to investigate whether it is feasible to use home-based measurements to assess and evaluate the severity of dystonia using smartphone-coupled inertial sensors and machine learning. Video and sensor data during both active and rest situations from 12 patients were collected outside a clinical setting. Three clinicians analyzed the videos and clinically scored the dystonia of the extremities on a 0–4 scale, following the definition of amplitude of the Dyskinesia Impairment Scale. The clinical scores and the sensor data were coupled to train different machine learning models using cross-validation. The average F1 scores (0.67 ± 0.19 for lower extremities and 0.68 ± 0.14 for upper extremities) in independent test datasets indicate that it is possible to detected dystonia automatically using individually trained models. The predictions could complement standard dyskinetic CP measures by providing frequent, objective, real-world assessments that could enhance clinical care. A generalized model, trained with data from other subjects, shows lower F1 scores (0.45 for lower extremities and 0.34 for upper extremities), likely due to a lack of training data and dissimilarities between subjects. However, the generalized model is reasonably able to distinguish between high and lower scores. Future research should focus on gathering more high-quality data and study how the models perform over the whole day.

A New Paradigm in Parkinson's Disease Evaluation With Wearable Medical Devices: A Review of STAT-ONTM

In the past decade, the use of wearable medical devices has been a great breakthrough in clinical practice, trials, and research. In the Parkinson's disease field, clinical evaluation is time limited, and healthcare professionals need to rely on retrospective data collected through patients' self-filled diaries and administered questionnaires. As this often leads to inaccurate evaluations, a more objective system for symptom monitoring in a patient's daily life is claimed. In this regard, the use of wearable medical devices is crucial. This study aims at presenting a review on STAT-ONTM, a wearable medical device Class IIa, which provides objective information on the distribution and severity of PD motor symptoms in home environments. The sensor analyzes inertial signals, with a set of validated machine learning algorithms running in real time. The device was developed for 12 years, and this review aims at gathering all the results achieved within this time frame. First, a compendium of the complete journey of STAT-ONTM since 2009 is presented, encompassing different studies and developments in funded European and Spanish national projects. Subsequently, the methodology of database construction and machine learning algorithms design and development is described. Finally, clinical validation and external studies of STAT-ONTM are presented.

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.

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.

Body-Worn Sensors for Remote Monitoring of Parkinson's Disease Motor Symptoms: Vision, State of the Art, and Challenges Ahead

The increasing prevalence of neurodegenerative conditions such as Parkinson's disease (PD) and related mobility issues places a serious burden on healthcare systems. The COVID-19 pandemic has reinforced the urgent need for better tools to manage chronic conditions remotely, as regular access to clinics may be problematic. Digital health technology in the form of remote monitoring with body-worn sensors offers significant opportunities for transforming research and revolutionizing the clinical management of PD. Significant efforts are being invested in the development and validation of digital outcomes to support diagnosis and track motor and mobility impairments "off-line". Imagine being able to remotely assess your patient, understand how well they are functioning, evaluate the impact of any recent medication/intervention, and identify the need for urgent follow-up before overt, irreparable change takes place? This could offer new pragmatic solutions for personalized care and clinical research. So the question remains: how close are we to achieving this? Here, we describe the state-of-the-art based on representative papers published between 2017 and 2020. We focus on remote (i.e., real-world, daily-living) monitoring of PD using body-worn sensors (e.g., accelerometers, inertial measurement units) for assessing motor symptoms and their complications. Despite the tremendous potential, existing challenges exist (e.g., validity, regulatory) that are preventing the widespread clinical adoption of body-worn sensors as a digital outcome. We propose a roadmap with clear recommendations for addressing these challenges and future directions to bring us closer to the implementation and widespread adoption of this important way of improving the clinical care, evaluation, and monitoring of PD.

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.