A Perspective on Wearable Sensor Measurements and Data Science for Parkinson's Disease

Interpretable video-based tracking and quantification of parkinsonism clinical motor states

Quantification of motor symptom progression in Parkinson's disease (PD) patients is crucial for assessing disease progression and for optimizing therapeutic interventions, such as dopaminergic medications and deep brain stimulation. Cumulative and heuristic clinical experience has identified various clinical signs associated with PD severity, but these are neither objectively quantifiable nor robustly validated. Video-based objective symptom quantification enabled by machine learning (ML) introduces a potential solution. However, video-based diagnostic tools often have implementation challenges due to expensive and inaccessible technology, and typical "black-box" ML implementations are not tailored to be clinically interpretable. Here, we address these needs by releasing a comprehensive kinematic dataset and developing an interpretable video-based framework that predicts high versus low PD motor symptom severity according to MDS-UPDRS Part III metrics. This data driven approach validated and robustly quantified canonical movement features and identified new clinical insights, not previously appreciated as related to clinical severity, including pinkie finger movements and lower limb and axial features of gait. Our framework is enabled by retrospective, single-view, seconds-long videos recorded on consumer-grade devices such as smartphones, tablets, and digital cameras, thereby eliminating the requirement for specialized equipment. Following interpretable ML principles, our framework enforces robustness and interpretability by integrating (1) automatic, data-driven kinematic metric evaluation guided by pre-defined digital features of movement, (2) combination of bi-domain (body and hand) kinematic features, and (3) sparsity-inducing and stability-driven ML analysis with simple-to-interpret models. These elements ensure that the proposed framework quantifies clinically meaningful motor features useful for both ML predictions and clinical analysis.

Continuous and Unconstrained Tremor Monitoring in Parkinson's Disease Using Supervised Machine Learning and Wearable Sensors

Background

Accurately assessing the severity and frequency of fluctuating motor symptoms is important at all stages of Parkinson's disease management. Contrarily to time-consuming clinical testing or patient self-reporting with uncertain reliability, recordings with wearable sensors show promise as a tool for continuously and objectively assessing PD symptoms. While wearables-based clinical assessments during standardised and scripted tasks have been successfully implemented, assessments during unconstrained activity remain a challenge.

Methods

We developed and implemented a supervised machine learning algorithm, trained and tested on tremor scores. We evaluated the algorithm on a 67-hour database comprising sensor data and clinical tremor scores for 24 Parkinson patients at four extremities for periods of about 3 hours. A random 25% subset of the labelled samples was used as test data, the remainder as training data. Based on features extracted from the sensor data, a Support Vector Machine was trained to predict tremor severity. Due to the inherent imbalance in tremor scores, we applied dataset rebalancing techniques.

Results

Our classifier demonstrated robust performance in detecting tremor events with a sensitivity of 0.90 on the test-portion of the resampled dataset. The overall classification accuracy was high at 0.88.

Conclusion

We implemented an accurate classifier for tremor monitoring in free-living environments that can be trained even with modestly sized and imbalanced datasets. This advancement offers significant clinical value in continuously monitoring Parkinson's disease symptoms beyond the hospital setting, paving the way for personalized management of PD, timely therapeutic adjustments, and improved patient quality of life.

Clinical Management of Movement Disorders

Movement disorders include a wide and heterogeneous variety of signs and syndromes, which are classified as hyperkinetic [...].

Classifying Tremor Dominant and Postural Instability and Gait Difficulty Subtypes of Parkinson's Disease from Full-Body Kinematics

Characterizing motor subtypes of Parkinson's disease (PD) is an important aspect of clinical care that is useful for prognosis and medical management. Although all PD cases involve the loss of dopaminergic neurons in the brain, individual cases may present with different combinations of motor signs, which may indicate differences in underlying pathology and potential response to treatment. However, the conventional method for distinguishing PD motor subtypes involves resource-intensive physical examination by a movement disorders specialist. Moreover, the standardized rating scales for PD rely on subjective observation, which requires specialized training and unavoidable inter-rater variability. In this work, we propose a system that uses machine learning models to automatically and objectively identify some PD motor subtypes, specifically Tremor-Dominant (TD) and Postural Instability and Gait Difficulty (PIGD), from 3D kinematic data recorded during walking tasks for patients with PD (MDS-UPDRS-III Score, 34.7 ± 10.5, average disease duration 7.5 ± 4.5 years). This study demonstrates a machine learning model utilizing kinematic data that identifies PD motor subtypes with a 79.6% F1 score (N = 55 patients with parkinsonism). This significantly outperformed a comparison model using classification based on gait features (19.8% F1 score). Variants of our model trained to individual patients achieved a 95.4% F1 score. This analysis revealed that both temporal, spectral, and statistical features from lower body movements are helpful in distinguishing motor subtypes. Automatically assessing PD motor subtypes simply from walking may reduce the time and resources required from specialists, thereby improving patient care for PD treatments. Furthermore, this system can provide objective assessments to track the changes in PD motor subtypes over time to implement and modify appropriate treatment plans for individual patients as needed.

User-centered design of feedback regarding health-related behaviors derived from wearables: An approach targeting older adults and persons living with neurodegenerative disease

Objective

There has been tremendous growth in wearable technologies for health monitoring but limited efforts to optimize methods for sharing wearables-derived information with older adults and clinical cohorts. This study aimed to co-develop, design and evaluate a personalized approach for information-sharing regarding daily health-related behaviors captured with wearables.

Methods

A participatory research approach was adopted with: (a) iterative stakeholder, and evidence-led development of feedback reporting; and (b) evaluation in a sample of older adults (n  =  15) and persons living with neurodegenerative disease (NDD) (n  =  25). Stakeholders included persons with lived experience, healthcare providers, health charity representatives and individuals involved in aging/NDD research. Feedback report information was custom-derived from two limb-mounted inertial measurement units and a mobile electrocardiography device worn by participants for 7-10 days. Mixed methods were used to evaluate reporting 2 weeks following delivery. Data were summarized using descriptive statistics for the group and stratified by cohort and cognitive status.

Results

Participants (n  =  40) were 60% female (median 72 (60-87) years). A total of 82.5% found the report easy to read or understand, 80% reported the right amount of information was shared, 90% found the information helpful, 92% shared the information with a family member or friend and 57.5% made a behavior change. Differences emerged in sub-group comparisons. A range of participant profiles existed in terms of interest, uptake and utility.

Conclusions

The reporting approach was generally well-received with perceived value that translated into enhanced self-awareness and self-management of daily health-related behaviors. Future work should examine potential for scale, and the capacity for wearables-derived feedback to influence longer-term behavior change.

An Auxiliary Diagnostic System for Parkinson's Disease Based on Wearable Sensors and Genetic Algorithm Optimized Random Forest

Parkinson's disease (PD) is a neurodegenerative disorder characterized mainly by motor-related impairment, an accurate, quantitative, and objective diagnosis is an effective way to slow the disease deterioration process. In this paper, a user-friendly auxiliary diagnostic system for PD is constructed based on the upper limb movement conditions of 100 subjects consisting of 50 PD patients and 50 healthy subjects. This system includes wearable sensors that collect upper limb movement data, host computer for data processing and classification, and graphic user interface (GUI). The genetic algorithm optimized random forest classifier is introduced to classify PD and normal states based on the selected optimal features, and the 50 trials leave-one-out cross-validation is used to evaluate the performance of the classifier, with the highest accuracy of 94.4%. The classification accuracy among different upper limb movement tasks and with the different number of sensors are compared, results show that the task with only alternation hand movement also has satisfactory classification accuracy, and sensors on both wrists performance better than one sensor on a single wrist. The utility of the proposed system is illustrated by neurologists with a deployed GUI during the clinical inquiry, opening the possibility for a wide range of applications in the auxiliary diagnosis of PD.

Rapid Dynamic Naturalistic Monitoring of Bradykinesia in Parkinson's Disease Using a Wrist-Worn Accelerometer

Motor fluctuations in Parkinson’s disease are characterized by unpredictability in the timing and duration of dopaminergic therapeutic benefits on symptoms, including bradykinesia and rigidity. These fluctuations significantly impair the quality of life of many Parkinson’s patients. However, current clinical evaluation tools are not designed for the continuous, naturalistic (real-world) symptom monitoring needed to optimize clinical therapy to treat fluctuations. Although commercially available wearable motor monitoring, used over multiple days, can augment neurological decision making, the feasibility of rapid and dynamic detection of motor fluctuations is unclear. So far, applied wearable monitoring algorithms are trained on group data. In this study, we investigated the influence of individual model training on short timescale classification of naturalistic bradykinesia fluctuations in Parkinson’s patients using a single-wrist accelerometer. As part of the Parkinson@Home study protocol, 20 Parkinson patients were recorded with bilateral wrist accelerometers for a one hour OFF medication session and a one hour ON medication session during unconstrained activities in their own homes. Kinematic metrics were extracted from the accelerometer data from the bodyside with the largest unilateral bradykinesia fluctuations across medication states. The kinematic accelerometer features were compared over the 1 h duration of recording, and medication-state classification analyses were performed on 1 min segments of data. Then, we analyzed the influence of individual versus group model training, data window length, and total number of training patients included in group model training, on classification. Statistically significant areas under the curves (AUCs) for medication induced bradykinesia fluctuation classification were seen in 85% of the Parkinson patients at the single minute timescale using the group models. Individually trained models performed at the same level as the group trained models (mean AUC both 0.70, standard deviation respectively 0.18 and 0.10) despite the small individual training dataset. AUCs of the group models improved as the length of the feature windows was increased to 300 s, and with additional training patient datasets. We were able to show that medication-induced fluctuations in bradykinesia can be classified using wrist-worn accelerometry at the time scale of a single minute. Rapid, naturalistic Parkinson motor monitoring has the clinical potential to evaluate dynamic symptomatic and therapeutic fluctuations and help tailor treatments on a fast timescale.

A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction

Freezing of Gait (FOG) is an impairment that affects the majority of patients in the advanced stages of Parkinson's Disease (PD). FOG can lead to sudden falls and injuries, negatively impacting the quality of life for the patients and their families. Rhythmic Auditory Stimulation (RAS) can be used to help patients recover from FOG and resume normal gait. RAS might be ineffective due to the latency between the start of a FOG event, its detection and initialization of RAS. We propose a system capable of both FOG prediction and detection using signals from tri-axial accelerometer sensors that will be useful in initializing RAS with minimal latency. We compared the performance of several time frequency analysis techniques, including moving windows extracted from the signals, handcrafted features, Recurrence Plots (RP), Short Time Fourier Transform (STFT), Discreet Wavelet Transform (DWT) and Pseudo Wigner Ville Distribution (PWVD) with Deep Learning (DL) based Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN). We also propose three Ensemble Network Architectures that combine all the time frequency representations and DL architectures. Experimental results show that our ensemble architectures significantly improve the performance compared with existing techniques. We also present the results of applying our method trained on a publicly available dataset to data collected from patients using wearable sensors in collaboration with A.T. Still University.

Automatic Resting Tremor Assessment in Parkinson's Disease Using Smartwatches and Multitask Convolutional Neural Networks

Resting tremor in Parkinson's disease (PD) is one of the most distinctive motor symptoms. Appropriate symptom monitoring can help to improve management and medical treatments and improve the patients' quality of life. Currently, tremor is evaluated by physical examinations during clinical appointments; however, this method could be subjective and does not represent the full spectrum of the symptom in the patients' daily lives. In recent years, sensor-based systems have been used to obtain objective information about the disease. However, most of these systems require the use of multiple devices, which makes it difficult to use them in an ambulatory setting. This paper presents a novel approach to evaluate the amplitude and constancy of resting tremor using triaxial accelerometers from consumer smartwatches and multitask classification models. These approaches are used to develop a system for an automated and accurate symptom assessment without interfering with the patients' daily lives. Results show a high agreement between the amplitude and constancy measurements obtained from the smartwatch in comparison with those obtained in a clinical assessment. This indicates that consumer smartwatches in combination with multitask convolutional neural networks are suitable for providing accurate and relevant information about tremor in patients in the early stages of the disease, which can contribute to the improvement of PD clinical evaluation, early detection of the disease, and continuous monitoring.

New Sensor and Wearable Technologies to Aid in the Diagnosis and Treatment Monitoring of Parkinson's Disease

Parkinson's disease (PD) is a degenerative disorder of the brain characterized by the impairment of the nigrostriatal system. This impairment leads to specific motor manifestations (i.e., bradykinesia, tremor, and rigidity) that are assessed through clinical examination, scales, and patient-reported outcomes. New sensor-based and wearable technologies are progressively revolutionizing PD care by objectively measuring these manifestations and improving PD diagnosis and treatment monitoring. However, their use is still limited in clinical practice, perhaps because of the absence of external validation and standards for their continuous use at home. In the near future, these systems will progressively complement traditional tools and revolutionize the way we diagnose and monitor patients with PD.

Fuzzy inference model based on triaxial signals for pronation and supination assessment in Parkinson's disease patients

Nowadays, the Unified Parkinson Disease Rating Scale supported by the Movement Disorder Society (MDS-UPDRS), is a standardized and widely accepted instrument to rate Parkinson's disease (PD). This work presents a thorough analysis of item 3.6 of the MDS-UPDRS scale which corresponds to the pronation and supination hand movements. The motivation for this work lies in the objective quantification of motor affectations not covered by the MDS-UPDRS scale such as unsteady oscillations and velocity decrements during the motor exploration. Overall, 12 different bio-mechanical features were quantified based on measurements performed by inertial measurement units (IMUs). After a feature selection process, the selected bio-mechanical features were used as inputs for a fuzzy inference model that predicts the stage of development of the disease in each patient. In addition to this model's output, the scores of three different expert examiners and the output of a fuzzy inference model which covers affectations strictly attached the MDS-UPDRS guidelines, were also considered to obtain an integrated computational model. The proposed integrated model was incorporated using the Analytic Hierarchy Process (AHP), which gives the novelty of a combined score that helps expert examiners to give a broader assessment of the disease that covers both affectations mentioned in the MDS-UPDRS guidelines and affectations not covered by it in an objective manner.

Using an unbiased symbolic movement representation to characterize Parkinson's disease states

Unconstrained human movement can be broken down into a series of stereotyped motifs or 'syllables' in an unsupervised fashion. Sequences of these syllables can be represented by symbols and characterized by a statistical grammar which varies with external situational context and internal neurological state. By first constructing a Markov chain from the transitions between these syllables then calculating the stationary distribution of this chain, we estimate the overall severity of Parkinson's symptoms by capturing the increasingly disorganized transitions between syllables as motor impairment increases. Comparing stationary distributions of movement syllables has several advantages over traditional neurologist administered in-clinic assessments. This technique can be used on unconstrained at-home behavior as well as scripted in-clinic exercises, it avoids differences across human evaluators, and can be used continuously without requiring scripted tasks be performed. We demonstrate the effectiveness of this technique using movement data captured with commercially available wrist worn sensors in 35 participants with Parkinson's disease in-clinic and 25 participants monitored at home.

Deep Learning Approaches for Detecting Freezing of Gait in Parkinson's Disease Patients through On-Body Acceleration Sensors

Freezing of gait (FOG) is one of the most incapacitating motor symptoms in Parkinson's disease (PD). The occurrence of FOG reduces the patients' quality of live and leads to falls. FOG assessment has usually been made through questionnaires, however, this method can be subjective and could not provide an accurate representation of the severity of this symptom. The use of sensor-based systems can provide accurate and objective information to track the symptoms' evolution to optimize PD management and treatments. Several authors have proposed specific methods based on wearables and the analysis of inertial signals to detect FOG in laboratory conditions, however, its performance is usually lower when being used at patients' homes. This study presents a new approach based on a recurrent neural network (RNN) and a single waist-worn triaxial accelerometer to enhance the FOG detection performance to be used in real home-environments. Also, several machine and deep learning approaches for FOG detection are evaluated using a leave-one-subject-out (LOSO) cross-validation. Results show that modeling spectral information of adjacent windows through an RNN can bring a significant improvement in the performance of FOG detection without increasing the length of the analysis window (required to using it as a cue-system).

Leap motion controlled video game-based therapy for upper limb rehabilitation in patients with Parkinson's disease: a feasibility study

BACKGROUND

Non-immersive video games are currently being used as technological rehabilitation tools for individuals with Parkinson's disease (PD). The aim of this feasibility study was to evaluate the effectiveness of the Leap Motion Controller® (LMC) system used with serious games designed for the upper limb (UL), as well as the levels of satisfaction and compliance among patients in mild-to-moderate stages of the disease.

METHODS

A non-probabilistic sampling of non-consecutive cases was performed. 23 PD patients, in stages II-IV of the Hoehn & Yahr scale, were randomized into two groups: an experimental group (n = 12) who received treatment based on serious games designed by the research team using the LMC system for the UL, and a control group (n = 11) who received a specific intervention for the UL. Grip muscle strength, coordination, speed of movements, fine and gross UL dexterity, as well as satisfaction and compliance, were assessed in both groups pre-treatment and post-treatment.

RESULTS

Within the experimental group, significant improvements were observed in all post-treatment assessments, except for Box and Blocks test for the less affected side. Clinical improvements were observed for all assessments in the control group. Statistical intergroup analysis showed significant improvements in coordination, speed of movements and fine motor dexterity scores on the more affected side of patients in the experimental group.

CONCLUSIONS

The LMC system and the serious games designed may be a feasible rehabilitation tool for the improvement of coordination, speed of movements and fine UL dexterity in PD patients. Further studies are needed to confirm these preliminary findings.

Identifying balance impairments in people with Parkinson's disease using video and wearable sensors

BACKGROUND

Falls and near falls are common among people with Parkinson's (PwP). To date, most wearable sensor research focussed on fall detection, few studies explored if wearable sensors can detect instability.

RESEARCH QUESTION

Can instability (caution or near-falls) be detected using wearable sensors in comparison to video analysis?

METHODS

Twenty-four people (aged 60-86) with and without Parkinson's were recruited from community groups. Movements (e.g. walking, turning, transfers and reaching) were observed in the gait laboratory and/or at home; recorded using clinical measures, video and five wearable sensors (attached on the waist, ankles and wrists). After defining 'caution' and 'instability', two researchers evaluated video data and a third the raw wearable sensor data; blinded to each other's evaluations. Agreement between video and sensor data was calculated on stability, timing, step count and strategy.

RESULTS

Data was available for 117 performances: 82 (70%) appeared stable on video. Ratings agreed in 86/117 cases (74%). Highest agreement was noted for chair transfer, timed up and go test and 3 m walks. Video analysts noted caution (slow, contained movements, safety-enhancing postures and concentration) and/or instability (saving reactions, stopping after stumbling or veering) in 40/134 performances (30%): raw wearable sensor data identified 16/35 performances rated cautious or unstable (sensitivity 46%) and 70/82 rated stable (specificity 85%). There was a 54% chance that a performance identified from wearable sensors as cautious/unstable was so; rising to 80% for stable movements.

SIGNIFICANCE

Agreement between wearable sensor and video data suggested that wearable sensors can detect subtle instability and near-falls. Caution and instability were observed in nearly a third of performances, suggesting that simple, mildly challenging actions, with clearly defined start- and end-points, may be most amenable to monitoring during free-living at home. Using the genuine near-falls recorded, work continues to automatically detect subtle instability using algorithms.

Quantifying Motor Impairment in Movement Disorders

Until recently the assessment of many movement disorders has relied on clinical rating scales that despite careful design are inherently subjective and non-linear. This makes accurate and truly observer-independent quantification difficult and limits the use of sensitive parametric statistical methods. At last, devices capable of measuring neurological problems quantitatively are becoming readily available. Examples include the use of oculometers to measure eye movements and accelerometers to measure tremor. Many applications are being developed for use on smartphones. The benefits include not just more accurate disease quantification, but also consistency of data for longitudinal studies, accurate stratification of patients for entry into trials, and the possibility of automated data capture for remote follow-up. In this mini review, we will look at movement disorders with a particular focus on Parkinson's disease, describe some of the limitations of existing clinical evaluation tools, and illustrate the ways in which objective metrics have already been successful.

Post hoc support vector machine learning for impedimetric biosensors based on weak protein–ligand interactions

We develop a simple, open source machine learning algorithm for analyzing impedimetric biosensor data using a mobile phone.