Ambulatory motor assessment in Parkinson's disease

Time-resolved quantification of fine hand movements as a proxy for evaluating bradykinesia-induced motor dysfunction

Bradykinesia is a behavioral manifestation that contributes to functional dependencies in later life. However, the current state of bradykinesia indexing primarily relies on subjective, time-averaged categorizations of motor deficits, which often yield poor reliability. Herein, we used time-resolved analyses of accelerometer recordings during standardized movements, data-driven factor analyses, and linear mixed effects models (LMEs) to quantitatively characterize general, task- and therapy-specific indices of motor impairment in people with Parkinson's disease (PwP) currently undergoing treatment for bradykinesia. Our results demonstrate that single-trial, accelerometer-based features of finger-tapping and rotational hand movements were significantly modulated by divergent therapeutic regimens. Further, these features corresponded well to current gold standards for symptom monitoring, with more precise predictive capacities of bradykinesia-specific declines achieved when considering kinematic features from diverse movement types together, rather than in isolation. Herein, we report data-driven, sample-specific kinematic profiles of diverse movement types along a continuous spectrum of motor impairment, which importantly, preserves the temporal scale for which biomechanical fluctuations in motor deficits evolve in humans. Therefore, this approach may prove useful for tracking bradykinesia-induced motor decline in aging populations the future.

Upper limb intention tremor assessment: opportunities and challenges in wearable technology

BACKGROUND

Tremors are involuntary rhythmic movements commonly present in neurological diseases such as Parkinson's disease, essential tremor, and multiple sclerosis. Intention tremor is a subtype associated with lesions in the cerebellum and its connected pathways, and it is a common symptom in diseases associated with cerebellar pathology. While clinicians traditionally use tests to identify tremor type and severity, recent advancements in wearable technology have provided quantifiable ways to measure movement and tremor using motion capture systems, app-based tasks and tools, and physiology-based measurements. However, quantifying intention tremor remains challenging due to its changing nature.

METHODOLOGY & RESULTS

This review examines the current state of upper limb tremor assessment technology and discusses potential directions to further develop new and existing algorithms and sensors to better quantify tremor, specifically intention tremor. A comprehensive search using PubMed and Scopus was performed using keywords related to technologies for tremor assessment. Afterward, screened results were filtered for relevance and eligibility and further classified into technology type. A total of 243 publications were selected for this review and classified according to their type: body function level: movement-based, activity level: task and tool-based, and physiology-based. Furthermore, each publication's methods, purpose, and technology are summarized in the appendix table.

CONCLUSIONS

Our survey suggests a need for more targeted tasks to evaluate intention tremors, including digitized tasks related to intentional movements, neurological and physiological measurements targeting the cerebellum and its pathways, and signal processing techniques that differentiate voluntary from involuntary movement in motion capture systems.

Coordination Rigidity in the Gait, Posture, and Speech of Persons with Parkinson's Disease

Parkinson's disease (PD) is associated with reduced coordination abilities. These can result either in random or rigid patterns of movement. The latter, described here as coordination rigidity (CR), have been studied less often. We explored whether CR was present in gait, quiet stance, and speech-tasks involving coordination among multiple joints and muscles. Kinematic and voice recordings were used to compute measures describing the dynamics of systems with multiple degrees of freedom and nonlinear interactions. After clinical evaluation, patients with moderate stage PD were compared against matched healthy participants. In the PD group, gait dynamics was associated with decreased dynamic divergence-lower instability-in the vertical axis. Postural fluctuations were associated with increased regularity in the anterior-posterior axis, and voice dynamics with increased predictability, all consistent with CR. The clinical relevance of CR was confirmed by showing that some of those features contribute to disease classification with supervised machine learning (82/81/85% accuracy/sensitivity/specificity).

Machine Learning and Wearable Sensors for the Early Detection of Balance Disorders in Parkinson's Disease

Dynamic posturography combined with wearable sensors has high sensitivity in recognizing subclinical balance abnormalities in patients with Parkinson's disease (PD). However, this approach is burdened by a high analytical load for motion analysis, potentially limiting a routine application in clinical practice. In this study, we used machine learning to distinguish PD patients from controls, as well as patients under and not under dopaminergic therapy (i.e., ON and OFF states), based on kinematic measures recorded during dynamic posturography through portable sensors. We compared 52 different classifiers derived from Decision Tree, K-Nearest Neighbor, Support Vector Machine and Artificial Neural Network with different kernel functions to automatically analyze reactive postural responses to yaw perturbations recorded through IMUs in 20 PD patients and 15 healthy subjects. To identify the most efficient machine learning algorithm, we applied three threshold-based selection criteria (i.e., accuracy, recall and precision) and one evaluation criterion (i.e., goodness index). Twenty-one out of 52 classifiers passed the three selection criteria based on a threshold of 80%. Among these, only nine classifiers were considered "optimum" in distinguishing PD patients from healthy subjects according to a goodness index ≤ 0.25. The Fine K-Nearest Neighbor was the best-performing algorithm in the automatic classification of PD patients and healthy subjects, irrespective of therapeutic condition. By contrast, none of the classifiers passed the three threshold-based selection criteria in the comparison of patients in ON and OFF states. Overall, machine learning is a suitable solution for the early identification of balance disorders in PD through the automatic analysis of kinematic data from dynamic posturography.

Objective quantification of the severity of postural tremor based on kinematic parameters: A multi-sensory fusion study

BACKGROUND

Current clinical assessments of essential tremor (ET) are primarily based on expert consultation combined with reviewing patient complaints, physician expertise, and diagnostic experience. Thus, traditional evaluation methods often lead to biased diagnostic results. There is a clinical demand for a method that can objectively quantify the severity of the patient's disease.

METHODS

This study aims to develop an artificial intelligence-aided diagnosis method based on multi-sensory fusion wearables. The experiment relies on a rigorous clinical trial paradigm to collect multi-modal fusion of signals from 98 ET patients. At the same time, three clinicians scored independently, and the consensus score obtained was used as the ground truth for the machine learning models.

RESULTS

Sixty kinematic parameters were extracted from the signals recorded by the nine-axis inertial measurement unit (IMU). The results showed that most of the features obtained by IMU could effectively characterize the severity of the tremors. The accuracy of the optimal model for three tasks classifying five severity levels was 97.71%, 97.54%, and 97.72%, respectively.

CONCLUSIONS

This paper reports the first attempt to combine multiple feature selection and machine learning algorithms for fine-grained automatic quantification of postural tremor in ET patients. The promising results showed the potential of the proposed approach to quantify the severity of ET objectively.

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.

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.

Improving Medication Regimen Recommendation for Parkinson's Disease Using Sensor Technology

Parkinson's disease medication treatment planning is generally based on subjective data obtained through clinical, physician-patient interactions. The Personal KinetiGraph™ (PKG) and similar wearable sensors have shown promise in enabling objective, continuous remote health monitoring for Parkinson's patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to cluster patients based on levodopa regimens and response. The resulting clusters are then used to enhance treatment planning by providing improved initial treatment estimates to supplement a physician's initial assessment. We apply k-means clustering to a dataset of within-subject Parkinson's medication changes-clinically assessed by the MDS-Unified Parkinson's Disease Rating Scale-III (MDS-UPDRS-III) and the PKG sensor for movement staging. A random forest classification model was then used to predict patients' cluster allocation based on their respective demographic information, MDS-UPDRS-III scores, and PKG time-series data. Clinically relevant clusters were partitioned by levodopa dose, medication administration frequency, and total levodopa equivalent daily dose-with the PKG providing similar symptomatic assessments to physician MDS-UPDRS-III scores. A random forest classifier trained on demographic information, MDS-UPDRS-III scores, and PKG time-series data was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 86.9%, an F1 score of 90.7%, and an AUC of 0.871. A model that relied solely on demographic information and PKG time-series data provided the next best performance with an accuracy of 83.8%, an F1 score of 88.5%, and an AUC of 0.831, hence further enabling fully remote assessments. These computational methods demonstrate the feasibility of using sensor-based data to cluster patients based on their medication responses with further potential to assist with medication recommendations.

Three Days of Measurement Provide Reliable Estimates of Daily Tremor Characteristics: A Pilot Study in Organic and Functional Tremor Patients

Background

Long-term tremor recording is particularly useful for the assessment of overall severity and therapeutic interventions in tremor patients. The purpose of this paper is to investigate the optimal number of days needed to obtain reliable estimates of tremor percentage, tremor frequency variability and tremor intensity in tremor patients using long-term tremor recordings.

Methods

Participants were 18 years or older and were diagnosed with tremor by a movement disorders specialist. Participants wore an accelerometer on the wrist of the most affected arm during 30 consecutive days. Tremor presence, frequency variability and intensity were calculated per day. We used reliability analysis to determine the minimum number of days needed to obtain reliable estimates of these tremor characteristics.

Results

Data from 36 adult organic (OrgT) and functional tremor (FT) patients (24 males; mean age 63.9 ± 11.9 years; 15 FT) were analyzed. Using five hours per day, one day of measurement is enough, except for tremor frequency variability in the OrgT group, where three days are needed and for tremor intensity where two days are always needed.

Discussion

Visual analysis suggested that reliability can be increased considerably by using data from three days instead of one day even when using six hours of data per day. Three days with at least three hours of tremor data provide estimates of tremor percentage, frequency variability and intensity with good to excellent reliability, both for organic and functional tremor.

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.

Maximal Walking Distance in Persons with a Lower Limb Amputation

The distance one can walk at a time could be considered an important functional outcome in people with a lower limb amputation. In clinical practice, walking distance in daily life is based on self-report (SIGAM mobility grade (Special Interest Group in Amputee Medicine)), which is known to overestimate physical activity. The aim of this study was to assess the number of consecutive steps and walking bouts in persons with a lower limb amputation, using an accelerometer sensor. The number of consecutive steps was related to their SIGAM mobility grade and to the consecutive steps of age-matched controls in daily life. Twenty subjects with a lower limb amputation and ten age-matched controls participated in the experiment for two consecutive days, in their own environment. Maximal number of consecutive steps and walking bouts were obtained by two accelerometers in the left and right trouser pocket, and one accelerometer on the sternum. In addition, the SIGAM mobility grade was determined and the 10 m walking test (10 MWT) was performed. The maximal number of consecutive steps and walking bouts were significantly smaller in persons with a lower limb amputation, compared to the control group (p < 0.001). Only 4 of the 20 persons with a lower limb amputation had a maximal number of consecutive steps in the range of the control group. Although the maximal covered distance was moderately correlated with the SIGAM mobility grade in participants with an amputation (r = 0.61), for 6 of them, the SIGAM mobility grade did not match with the maximal covered distance. The current study indicated that mobility was highly affected in most persons with an amputation and that the SIGAM mobility grade did not reflect what persons with a lower limb amputation actually do in daily life. Therefore, objective assessment of the maximal number of consecutive steps of maximal covered distance is recommended for clinical treatment.

Parametric evaluation of deep brain stimulation parameter configurations for Parkinson's disease using a conformal wearable and wireless inertial sensor system and machine learning

Deep brain stimulation enables highly specified patient-unique therapeutic intervention ameliorating the symptoms of Parkinson's disease. Inherent to the efficacy of deep brain stimulation is the acquisition of an optimal parameter configuration. Using conventional methods, the optimization process for tuning the deep brain stimulation system parameters can intrinsically induce strain on clinical resources. An advanced means of quantifying Parkinson's hand tremor and distinguishing between parameter settings would be highly beneficial. The conformal wearable and wireless inertial sensor system, such as the BioStamp nPoint, has a volumetric profile on the order of a bandage that readily enables convenient quantification of Parkinson's disease hand tremor. Furthermore, the BioStamp nPoint has been certified by the FDA as a 510(k) medical device for acquisition of medical grade data. Parametric variation of the amplitude parameter for deep brain stimulation can be quantified through the BioStamp nPoint conformal wearable and wireless inertial sensor system mounted to the dorsum of the hand. The acquired inertial sensor signal data can be wirelessly transmitted to a secure Cloud computing environment for post-processing. The quantified inertial sensor data for the parametric study of the effects of varying amplitude can be distinguished through machine learning classification. Software automation through Python can consolidate the inertial sensor data into a suitable feature set format. Using the multilayer perceptron neural network considerable machine learning classification accuracy is attained to distinguish multiple parametric settings of amplitude for deep brain stimulation, such as 4.0 mA, 2.5 mA, 1.0 mA, and 'Off' status representing a baseline. These findings constitute an advance toward the pathway of attaining real-time closed loop automated parameter configuration tuning for treatment of Parkinson's disease using deep brain stimulation.

A Supervised Machine Learning Approach to Detect the On/Off State in Parkinson's Disease Using Wearable Based Gait Signals

Fluctuations in motor symptoms are mostly observed in Parkinson's disease (PD) patients. This characteristic is inevitable, and can affect the quality of life of the patients. However, it is difficult to collect precise data on the fluctuation characteristics using self-reported data from PD patients. Therefore, it is necessary to develop a suitable technology that can detect the medication state, also termed the "On"/"Off" state, automatically using wearable devices; at the same time, this could be used in the home environment. Recently, wearable devices, in combination with powerful machine learning techniques, have shown the potential to be effectively used in critical healthcare applications. In this study, an algorithm is proposed that can detect the medication state automatically using wearable gait signals. A combination of features that include statistical features and spatiotemporal gait features are used as inputs to four different classifiers such as random forest, support vector machine, K nearest neighbour, and Naïve Bayes. In total, 20 PD subjects with definite motor fluctuations have been evaluated by comparing the performance of the proposed algorithm in association with the four aforementioned classifiers. It was found that random forest outperformed the other classifiers with an accuracy of 96.72%, a recall of 97.35%, and a precision of 96.92%.

Using accelerometer as a diagnostic tool to detect drug-induced parkinsonism (DIP) secondary to first-generation anti-psychotic medications

OBJECTIVE

The objective of this study is to examine the effectiveness of an accelerometer-based compact system in detecting and quantifying drug-induced parkinsonism (DIP) in patients with schizophrenia.

METHOD

A pilot study controlled clinical trial comprising 6 people with schizophrenia and 11 control subjects was conducted at Alfred Health, Melbourne. Participants had their movements assessed using Barnes Akathisia Rating Scale (BARS), Simpson Angus Scale (SAS) and Movement Disorder Society Unified Parkinson's Disease Rating Scale Part III (MDS-UPDRS III) followed by an assessment of gait using three triaxial accelerometers.

RESULTS

Median BARS, SAS, MDS-UPDRS III and accelerometer scores were significantly higher for patients with schizophrenia than controls. Accelerometers detected three times more rest tremor than clinical rating scales. Patients with schizophrenia had 70% of their dynamic acceleration at frequencies between 4 and 10 Hz, which is almost twice that observed in the control population (38%). Accelerometer scores were significantly correlated with BARS scores.

CONCLUSION

Accelerometers were able to accurately detect patients with DIP better than some clinical rating scale including the SAS. Further larger-scale studies must be conducted to further demonstrate the accuracy of accelerometers in detecting DIP.

High-Resolution Motor State Detection in Parkinson's Disease Using Convolutional Neural Networks

Patients with advanced Parkinson's disease regularly experience unstable motor states. Objective and reliable monitoring of these fluctuations is an unmet need. We used deep learning to classify motion data from a single wrist-worn IMU sensor recording in unscripted environments. For validation purposes, patients were accompanied by a movement disorder expert, and their motor state was passively evaluated every minute. We acquired a dataset of 8,661 minutes of IMU data from 30 patients, with annotations about the motor state (OFF,ON, DYSKINETIC) based on MDS-UPDRS global bradykinesia item and the AIMS upper limb dyskinesia item. Using a 1-minute window size as an input for a convolutional neural network trained on data from a subset of patients, we achieved a three-class balanced accuracy of 0.654 on data from previously unseen subjects. This corresponds to detecting the OFF, ON, or DYSKINETIC motor state at a sensitivity/specificity of 0.64/0.89, 0.67/0.67 and 0.64/0.89, respectively. On average, the model outputs were highly correlated with the annotation on a per subject scale (r = 0.83/0.84; p < 0.0001), and sustained so for the highly resolved time windows of 1 minute (r = 0.64/0.70; p < 0.0001). Thus, we demonstrate the feasibility of long-term motor-state detection in a free-living setting with deep learning using motion data from a single IMU.

Development of digital biomarkers for resting tremor and bradykinesia using a wrist-worn wearable device

Objective assessment of Parkinson's disease symptoms during daily life can help improve disease management and accelerate the development of new therapies. However, many current approaches require the use of multiple devices, or performance of prescribed motor activities, which makes them ill-suited for free-living conditions. Furthermore, there is a lack of open methods that have demonstrated both criterion and discriminative validity for continuous objective assessment of motor symptoms in this population. Hence, there is a need for systems that can reduce patient burden by using a minimal sensor setup while continuously capturing clinically meaningful measures of motor symptom severity under free-living conditions. We propose a method that sequentially processes epochs of raw sensor data from a single wrist-worn accelerometer by using heuristic and machine learning models in a hierarchical framework to provide continuous monitoring of tremor and bradykinesia. Results show that sensor derived continuous measures of resting tremor and bradykinesia achieve good to strong agreement with clinical assessment of symptom severity and are able to discriminate between treatment-related changes in motor states.

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.

Using wearables to assess bradykinesia and rigidity in patients with Parkinson's disease: a focused, narrative review of the literature

The potential of using wearable technologies for the objective assessment of motor symptoms in Parkinson's disease (PD) has gained prominence recently. Nonetheless, compared to tremor and gait impairment, less emphasis has been placed on the quantification of bradykinesia and rigidity. This review aimed to consolidate the existing research on objective measurement of bradykinesia and rigidity in PD through the use of wearables, focusing on the continuous monitoring of these two symptoms in free-living environments. A search of PubMed was conducted through a combination of keyword and MeSH searches. We also searched the IEEE, Google Scholar, Embase, and Scopus databases to ensure thorough results and to minimize the chances of missing relevant studies. Papers published after the year 2000 with sample sizes greater than five were included. Studies were assessed for quality and information was extracted regarding the devices used and their location on the body, the setting and duration of the study, the "gold standard" used as a reference for validation, the metrics used, and the results of each paper. Thirty-one and eight studies met the search criteria and evaluated bradykinesia and rigidity, respectively. Several studies reported strong associations between wearable-based measures and the gold-standard references for bradykinesia, and, to a lesser extent, rigidity. Only a few, pilot studies investigated the measurement of bradykinesia and rigidity in the home and free-living settings. While the current results are promising for the future of wearables, additional work is needed on their validation and adaptation in ecological, free-living settings. Doing so has the potential to improve the assessment and treatment of motor fluctuations and symptoms of PD more generally through real-time objective monitoring of bradykinesia and rigidity.

Assessment of response to medication in individuals with Parkinson's disease

BACKGROUND AND OBJECTIVE

Motor fluctuations between akinetic (medication OFF) and mobile phases (medication ON) states are one of the most prevalent complications of patients with Parkinson's disease (PD). There is a need for a technology-based system to provide reliable information about the duration in different medication phases that can be used by the treating physician to successfully adjust therapy.

METHODS

Two KinetiSense motion sensors were mounted on the most affected wrist and ankle of 19 PD subjects (age: 42-77, 14 males) and collected movement signals as the participants performed seven daily living activities in their medication OFF and ON phases. A feature selection and a classification algorithm based on support vector machine with fuzzy labeling was developed to detect medication ON/OFF states using gyroscope signals. The algorithm was trained using approximately 15% of the data from four activities and tested on the remaining data.

RESULTS

The algorithm was able to detect medication ON and OFF states with 90.5% accuracy, 94.2% sensitivity, and 85.4% specificity. It performed equally well for all the activities with an average accuracy of 91.3% for the activities that were used in the training phase and 88.4% for the new activities.

CONCLUSIONS

The developed sensor-based algorithm could provide objective and accurate assessment of medication states that can lead to successful adjustment of the therapy resulting in considerably improved care delivery and quality of life of PD patients.

Can the Latest Computerized Technologies Revolutionize Conventional Assessment Tools and Therapies for a Neurological Disease? The Example of Parkinson's Disease

Dramatic breakthroughs in the treatment and assessment of neurological diseases are lacking. We believe that conventional methods have several limitations. Computerized technologies, including virtual reality, augmented reality, and robot assistant systems, are advancing at a rapid pace. In this study, we used Parkinson's disease (PD) as an example to elucidate how the latest computerized technologies can improve the diagnosis and treatment of neurological diseases. Dopaminergic medication and deep brain stimulation remain the most effective interventions for treating PD. Subjective scales, such as the Unified Parkinson's Disease Rating Scale and the Hoehn and Yahr stage, are still the most widely used assessments. Wearable sensors, virtual reality, augmented reality, and robot assistant systems are increasingly being used for evaluation of patients with PD. The use of such computerized technologies can result in safe, objective, real-time behavioral assessments. Our experiences and understanding of PD have led us to believe that such technologies can provide real-time assessment, which will revolutionize the traditional assessment and treatment of PD. New technologies are desired that can revolutionize PD treatment and facilitate real-time adjustment of treatment based on motor fluctuations, such as telediagnosis systems and "smart treatment systems." The use of these technologies will substantially improve both the assessment and the treatment of neurological diseases before next-generation treatments, such as stem cell and genetic therapy, and next-generation assessments, can be clinically practiced, although the current level of artificial intelligence cannot replace the role of clinicians.

Optimizing Clinical Assessments in Parkinson's Disease Through the Use of Wearable Sensors and Data Driven Modeling

The emergence of motion sensors as a tool that provides objective motor performance data on individuals afflicted with Parkinson's disease offers an opportunity to expand the horizon of clinical care for this neurodegenerative condition. Subjective clinical scales and patient based motor diaries have limited clinometric properties and produce a glimpse rather than continuous real time perspective into motor disability. Furthermore, the expansion of machine learn algorithms is yielding novel classification and probabilistic clinical models that stand to change existing treatment paradigms, refine the application of advance therapeutics, and may facilitate the development and testing of disease modifying agents for this disease. We review the use of inertial sensors and machine learning algorithms in Parkinson's disease.

A Kinematic Sensor and Algorithm to Detect Motor Fluctuations in Parkinson Disease: Validation Study Under Real Conditions of Use

BACKGROUND

A new algorithm has been developed, which combines information on gait bradykinesia and dyskinesia provided by a single kinematic sensor located on the waist of Parkinson disease (PD) patients to detect motor fluctuations (On- and Off-periods).

OBJECTIVE

The goal of this study was to analyze the accuracy of this algorithm under real conditions of use.

METHODS

This validation study of a motor-fluctuation detection algorithm was conducted on a sample of 23 patients with advanced PD. Patients were asked to wear the kinematic sensor for 1 to 3 days at home, while simultaneously keeping a diary of their On- and Off-periods. During this testing, researchers were not present, and patients continued to carry on their usual daily activities in their natural environment. The algorithm's outputs were compared with the patients' records, which were used as the gold standard.

RESULTS

The algorithm produced 37% more results than the patients' records (671 vs 489). The positive predictive value of the algorithm to detect Off-periods, as compared with the patients' records, was 92% (95% CI 87.33%-97.3%) and the negative predictive value was 94% (95% CI 90.71%-97.1%); the overall classification accuracy was 92.20%.

CONCLUSIONS

The kinematic sensor and the algorithm for detection of motor-fluctuations validated in this study are an accurate and useful tool for monitoring PD patients with difficult-to-control motor fluctuations in the outpatient setting.

A "HOLTER" for Parkinson's disease: Validation of the ability to detect on-off states using the REMPARK system

The treatment of Parkinson's disease (PD) with levodopa is very effective. However, over time, motor complications (MCs) appear, restricting the patient from leading a normal life. One of the most disabling MCs is ON-OFF fluctuations. Gathering accurate information about the clinical status of the patient is essential for planning treatment and assessing its effect. Systems such as the REMPARK system, capable of accurately and reliably monitoring ON-OFF fluctuations, are of great interest.

OBJECTIVE

To analyze the ability of the REMPARK System to detect ON-OFF fluctuations.

METHODS

Forty-one patients with moderate to severe idiopathic PD were recruited according to the UK Parkinson's Disease Society Brain Bank criteria. Patients with motor fluctuations, freezing of gait and/or dyskinesia and who were able to walk unassisted in the OFF phase, were included in the study. Patients wore the REMPARK System for 3days and completed a diary of their motor state once every hour.

RESULTS

The record obtained by the REMPARK System, compared with patient-completed diaries, demonstrated 97% sensitivity in detecting OFF states and 88% specificity (i.e., accuracy in detecting ON states).

CONCLUSION

The REMPARK System detects an accurate evaluation of ON-OFF fluctuations in PD; this technology paves the way for an optimisation of the symptomatic control of PD motor symptoms as well as an accurate assessment of medication efficacy.

A Possible Explanation of How High-Frequency Deep Brain Stimulation Suppresses Low-Frequency Tremors in Parkinson's Disease

Parkinson's disease (PD) is a neurodegenerative disorder of the central nervous system and one of its key symptoms is rest tremor. Deep brain stimulation (DBS) effectively suppresses rest tremor in Parkinson's disease. Despite being a successful treatment option, its underlying principle and the mechanism by which it attenuates tremors is not yet fully understood. Since existing methods for tuning DBS parameters are largely trial and error, understanding how DBS works can help to reduce time and costs, and could also ultimately lead to better treatment strategies for PD. In this paper, we set out to analyze how a high-frequency stimulation applied through DBS can help reduce the low-frequency rest tremors observed in PD patients. We identify key elements in the sensorimotor loop (the feedback loop consisting of sensory feedbacks and motor responses) that play a role in the interaction of high-frequency DBS signal and the low-frequency tremor. Based on the analysis of these elements, we draw insights about the working of DBS and the role of frequency and the nature of stimulation. We verify these observations with numerical examples and a bench top experimental example.

Analysis of Correlation between an Accelerometer-Based Algorithm for Detecting Parkinsonian Gait and UPDRS Subscales

Background

Our group earlier developed a small monitoring device, which uses accelerometer measurements to accurately detect motor fluctuations in patients with Parkinson’s (On and Off state) based on an algorithm that characterizes gait through the frequency content of strides. To further validate the algorithm, we studied the correlation of its outputs with the motor section of the Unified Parkinson’s Disease Rating Scale part-III (UPDRS-III).

Method

Seventy-five patients suffering from Parkinson’s disease were asked to walk both in the Off and the On state while wearing the inertial sensor on the waist. Additionally, all patients were administered the motor section of the UPDRS in both motor phases. Tests were conducted at the patient’s home. Convergence between the algorithm and the scale was evaluated by using the Spearman’s correlation coefficient.

Results

Correlation with the UPDRS-III was moderate (rho −0.56; p < 0.001). Correlation between the algorithm outputs and the gait item in the UPDRS-III was good (rho −0.73; p < 0.001). The factorial analysis of the UPDRS-III has repeatedly shown that several of its items can be clustered under the so-called Factor 1: “axial function, balance, and gait.” The correlation between the algorithm outputs and this factor of the UPDRS-III was −0.67 (p < 0.01).

Conclusion

The correlation achieved by the algorithm with the UPDRS-III scale suggests that this algorithm might be a useful tool for monitoring patients with Parkinson’s disease and motor fluctuations.

Quantification of Hand Motor Symptoms in Parkinson's Disease: A Proof-of-Principle Study Using Inertial and Force Sensors

This proof-of-principle study describes the methodology and explores and demonstrates the applicability of a system, existing of miniature inertial sensors on the hand and a separate force sensor, to objectively quantify hand motor symptoms in patients with Parkinson’s disease (PD) in a clinical setting (off- and on-medication condition). Four PD patients were measured in off- and on- dopaminergic medication condition. Finger tapping, rapid hand opening/closing, hand pro/supination, tremor during rest, mental task and kinetic task, and wrist rigidity movements were measured with the system (called the PowerGlove). To demonstrate applicability, various outcome parameters of measured hand motor symptoms of the patients in off- vs. on-medication condition are presented. The methodology described and results presented show applicability of the PowerGlove in a clinical research setting, to objectively quantify hand bradykinesia, tremor and rigidity in PD patients, using a single system. The PowerGlove measured a difference in off- vs. on-medication condition in all tasks in the presented patients with most of its outcome parameters. Further study into the validity and reliability of the outcome parameters is required in a larger cohort of patients, to arrive at an optimal set of parameters that can assist in clinical evaluation and decision-making.

Telehealth Management of Parkinson's Disease Using Wearable Sensors: An Exploratory Study

Background

Parkinson's disease (PD) motor symptoms can fluctuate and may not be accurately reflected during a clinical evaluation. In addition, access to movement disorder specialists is limited for many with PD. The objective was to assess the impact of motion sensor-based telehealth diagnostics on PD clinical care and management.

Methods

Eighteen adults with PD were randomized to control or experimental groups. All participants were instructed to use a motion sensor-based monitoring system at home one day per week, for seven months. The system included a finger-worn motion sensor and tablet-based software interface that guided patients through tasks to quantify tremor, bradykinesia, and dyskinesia. Data were processed into motor symptom severity reports, which were reviewed by a movement disorders neurologist for experimental group participants. After three months and six months, control group participants visited the clinic for a routine appointment, while experimental group participants had a videoconference or phone call instead.

Results

Home based assessments were completed with median compliance of 95.7%. For a subset of participants, the neurologist successfully used information in the reports such as quantified response to treatment or progression over time to make therapy adjustments. Changes in clinical characteristics from study start to end were not significantly different between groups.

Discussion

Individuals with PD were able and willing to use remote monitoring technology. Patient management aided by telehealth diagnostics provided comparable outcomes to standard care. Telehealth technologies combined with wearable sensors have the potential to improve care for disparate PD populations or those unable to travel.

Continuous Assessment of Levodopa Response in Parkinson's Disease Using Wearable Motion Sensors

OBJECTIVE

Fluctuations in response to levodopa in Parkinson's disease (PD) are difficult to treat as tools to monitor temporal patterns of symptoms are hampered by several challenges. The objective was to use wearable sensors to quantify the dose response of tremor, bradykinesia, and dyskinesia in individuals with PD.

METHODS

Thirteen individuals with PD and fluctuating motor benefit were instrumented with wrist and ankle motion sensors and recorded by video. Kinematic data were recorded as subjects completed a series of activities in a simulated home environment through transition from off to on medication. Subjects were evaluated using the unified Parkinson disease rating scale motor exam (UPDRS-III) at the start and end of data collection. Algorithms were applied to the kinematic data to score tremor, bradykinesia, and dyskinesia. A blinded clinician rated severity observed on video. Accuracy of algorithms was evaluated by comparing scores with clinician ratings using a receiver operating characteristic (ROC) analysis.

RESULTS

Algorithm scores for tremor, bradykinesia, and dyskinesia agreed with clinician ratings of video recordings (ROC area > 0.8). Summary metrics extracted from time intervals before and after taking medication provided quantitative measures of therapeutic response (p < 0.01). Radar charts provided intuitive visualization, with graphical features correlated with UPDRS-III scores (R = 0.81).

CONCLUSION

A system with wrist and ankle motion sensors can provide accurate measures of tremor, bradykinesia, and dyskinesia as patients complete routine activities.

SIGNIFICANCE

This technology could provide insight on motor fluctuations in the context of daily life to guide clinical management and aid in development of new therapies.

Detection of Motor Impairment in Parkinson's Disease Via Mobile Touchscreen Typing

Mobile technology is opening a wide range of opportunities for transforming the standard of care for chronic disorders. Using smartphones as tools for longitudinally tracking symptoms could enable personalization of drug regimens and improve patient monitoring. Parkinson's disease (PD) is an ideal candidate for these tools. At present, evaluation of PD signs requires trained experts to quantify motor impairment in the clinic, limiting the frequency and quality of the information available for understanding the status and progression of the disease. Mobile technology can help clinical decision making by completing the information of motor status between hospital visits. This paper presents an algorithm to detect PD by analyzing the typing activity on smartphones independently of the content of the typed text. We propose a set of touchscreen typing features based on a covariance, skewness, and kurtosis analysis of the timing information of the data to capture PD motor signs. We tested these features, both independently and in a multivariate framework, in a population of 21 PD and 23 control subjects, achieving a sensitivity/specificity of 0.81/0.81 for the best performing feature and 0.73/0.84 for the best multivariate method. The results of the alternating finger-tapping, an established motor test, measured in our cohort are 0.75/0.78. This paper contributes to the development of a home-based, high-compliance, and high-frequency PD motor test by analysis of routine typing on touchscreens.

Improved kinect-based spatiotemporal and kinematic treadmill gait assessment

A cost-effective, clinician friendly gait assessment tool that can automatically track patients' anatomical landmarks can provide practitioners with important information that is useful in prescribing rehabilitative and preventive therapies. This study investigated the validity and reliability of the Microsoft Kinect v2 as a potential inexpensive gait analysis tool. Ten healthy subjects walked on a treadmill at 1.3 and 1.6m·s^-1, as spatiotemporal parameters and kinematics were extracted concurrently using the Kinect and three-dimensional motion analysis. Spatiotemporal measures included step length and width, step and stride times, vertical and mediolateral pelvis motion, and foot swing velocity. Kinematic outcomes included hip, knee, and ankle joint angles in the sagittal plane. The absolute agreement and relative consistency between the two systems were assessed using interclass correlations coefficients (ICC2,1), while reproducibility between systems was established using Lin's Concordance Correlation Coefficient (rc). Comparison of ensemble curves and associated 90% confidence intervals (CI90) of the hip, knee, and ankle joint angles were performed to investigate if the Kinect sensor could consistently and accurately assess lower extremity joint motion throughout the gait cycle. Results showed that the Kinect v2 sensor has the potential to be an effective clinical assessment tool for sagittal plane knee and hip joint kinematics, as well as some spatiotemporal temporal variables including pelvis displacement and step characteristics during the gait cycle.

Assessing Motor Fluctuations in Parkinson's Disease Patients Based on a Single Inertial Sensor

Altered movement control is typically the first noticeable symptom manifested by Parkinson's disease (PD) patients. Once under treatment, the effect of the medication is very patent and patients often recover correct movement control over several hours. Nonetheless, as the disease advances, patients present motor complications. Obtaining precise information on the long-term evolution of these motor complications and their short-term fluctuations is crucial to provide optimal therapy to PD patients and to properly measure the outcome of clinical trials. This paper presents an algorithm based on the accelerometer signals provided by a waist sensor that has been validated in the automatic assessment of patient's motor fluctuations (ON and OFF motor states) during their activities of daily living. A total of 15 patients have participated in the experiments in ambulatory conditions during 1 to 3 days. The state recognised by the algorithm and the motor state annotated by patients in standard diaries are contrasted. Results show that the average specificity and sensitivity are higher than 90%, while their values are higher than 80% of all patients, thereby showing that PD motor status is able to be monitored through a single sensor during daily life of patients in a precise and objective way.

Unsupervised home monitoring of Parkinson's disease motor symptoms using body-worn accelerometers

INTRODUCTION

Current PD assessment methods have inherent limitations. There is need for an objective method to assist clinical decisions and to facilitate evaluation of treatments. Accelerometers, and analysis using artificial neural networks (ANN), have shown potential as a method of motor symptom evaluation. This work describes the development of a novel PD disease state detection system informed by algorithms based on data collected in an unsupervised, home environment. We evaluated whether this approach can reproduce patient-completed symptom diaries and clinical assessment of disease state.

METHODS

34 participants with PD wore bilateral wrist-worn accelerometers for 4 h in a research facility (phase 1) and for 7 days at home whilst completing symptom diaries (phase 2). An ANN to predict disease state was developed based on home-derived accelerometer data. Using a leave-one-out approach, ANN performance was evaluated against patient-completed symptom diaries and against clinician rating of disease state.

RESULTS

In the clinical setting, specificity for dyskinesia detection was extremely high (0.99); high specificity was also demonstrated for home-derived data (0.93), but with low sensitivity (0.38). In both settings, sensitivity for on/off detection was sub-optimal. ANN-derived values of the proportions of time in each disease state showed strong, significant correlations with patient-completed symptom diaries.

CONCLUSION

Accurate, real-time evaluation of symptoms in an unsupervised, home environment, with this sensor system, is not yet achievable. In terms of the amounts of time spent in each disease state, ANN-derived results were comparable to those of symptom diaries, suggesting this method may provide a valuable outcome measure for medication trials.

Automatic assessment of medication states of patients with Parkinson's disease using wearable sensors

Motor fluctuations are a major focus of clinical managements in patients with mid-stage and advance Parkinson's disease (PD). In this paper, we develop a new patient-specific algorithm that can classify those fluctuations during a variety of activities. We extract a set of temporal and spectral features from the ambulatory signals and then introduce a semi-supervised classification algorithm based on K-means and self-organizing tree map clustering methods. Two different types of cluster labeling are introduced: hard and fuzzy labeling. The developed algorithm is evaluated on a dataset from triaxial gyroscope sensors for 12 PD patients. The average result of using K-means and fuzzy labeling on the trunk and the more affected leg sensors' readings was 75.96%, 70.57%, and 86.93% for accuracy, sensitivity, and specificity, respectively. The accuracy for individual patients varied from 99.95% to 42.53%, which was correlated with dyskinesia severity and the improvement of the PD symptoms with medication.

Technologies for Assessment of Motor Disorders in Parkinson's Disease: A Review

Parkinson’s Disease (PD) is characterized as the commonest neurodegenerative illness that gradually degenerates the central nervous system. The goal of this review is to come out with a summary of the recent progress of numerous forms of sensors and systems that are related to diagnosis of PD in the past decades. The paper reviews the substantial researches on the application of technological tools (objective techniques) in the PD field applying different types of sensors proposed by previous researchers. In addition, this also includes the use of clinical tools (subjective techniques) for PD assessments, for instance, patient self-reports, patient diaries and the international gold standard reference scale, Unified Parkinson Disease Rating Scale (UPDRS). Comparative studies and critical descriptions of these approaches have been highlighted in this paper, giving an insight on the current state of the art. It is followed by explaining the merits of the multiple sensor fusion platform compared to single sensor platform for better monitoring progression of PD, and ends with thoughts about the future direction towards the need of multimodal sensor integration platform for the assessment of PD.

A mobile cloud-based Parkinson's disease assessment system for home-based monitoring

BACKGROUND

Parkinson's disease (PD) is the most prevalent movement disorder of the central nervous system, and affects more than 6.3 million people in the world. The characteristic motor features include tremor, bradykinesia, rigidity, and impaired postural stability. Current therapy based on augmentation or replacement of dopamine is designed to improve patients' motor performance but often leads to levodopa-induced adverse effects, such as dyskinesia and motor fluctuation. Clinicians must regularly monitor patients in order to identify these effects and other declines in motor function as soon as possible. Current clinical assessment for Parkinson's is subjective and mostly conducted by brief observations made during patient visits. Changes in patients' motor function between visits are hard to track and clinicians are not able to make the most informed decisions about the course of therapy without frequent visits. Frequent clinic visits increase the physical and economic burden on patients and their families.

OBJECTIVE

In this project, we sought to design, develop, and evaluate a prototype mobile cloud-based mHealth app, "PD Dr", which collects quantitative and objective information about PD and would enable home-based assessment and monitoring of major PD symptoms.

METHODS

We designed and developed a mobile app on the Android platform to collect PD-related motion data using the smartphone 3D accelerometer and to send the data to a cloud service for storage, data processing, and PD symptoms severity estimation. To evaluate this system, data from the system were collected from 40 patients with PD and compared with experts' rating on standardized rating scales.

RESULTS

The evaluation showed that PD Dr could effectively capture important motion features that differentiate PD severity and identify critical symptoms. For hand resting tremor detection, the sensitivity was .77 and accuracy was .82. For gait difficulty detection, the sensitivity was .89 and accuracy was .81. In PD severity estimation, the captured motion features also demonstrated strong correlation with PD severity stage, hand resting tremor severity, and gait difficulty. The system is simple to use, user friendly, and economically affordable.

CONCLUSIONS

The key contribution of this study was building a mobile PD assessment and monitoring system to extend current PD assessment based in the clinic setting to the home-based environment. The results of this study proved feasibility and a promising future for utilizing mobile technology in PD management.

Validation of a portable device for mapping motor and gait disturbances in Parkinson's disease

BACKGROUND

Patients with severe idiopathic Parkinson's disease experience motor fluctuations, which are often difficult to control. Accurate mapping of such motor fluctuations could help improve patients' treatment.

OBJECTIVE

The objective of the study was to focus on developing and validating an automatic detector of motor fluctuations. The device is small, wearable, and detects the motor phase while the patients walk in their daily activities.

METHODS

Algorithms for detection of motor fluctuations were developed on the basis of experimental data from 20 patients who were asked to wear the detector while performing different daily life activities, both in controlled (laboratory) and noncontrolled environments. Patients with motor fluctuations completed the experimental protocol twice: (1) once in the ON, and (2) once in the OFF phase. The validity of the algorithms was tested on 15 different patients who were asked to wear the detector for several hours while performing daily activities in their habitual environments. In order to assess the validity of detector measurements, the results of the algorithms were compared with data collected by trained observers who were accompanying the patients all the time.

RESULTS

The motor fluctuation detector showed a mean sensitivity of 0.96 (median 1; interquartile range, IQR, 0.93-1) and specificity of 0.94 (median 0.96; IQR, 0.90-1).

CONCLUSIONS

ON/OFF motor fluctuations in Parkinson's patients can be detected with a single sensor, which can be worn in everyday life.

Task independent identification of sensor location on upper limb from orientation data

In this paper we describe a novel method for sensor placement identification, and demonstrate the effectiveness of this method on an upper limb neuroprothesis for tremor suppression under a variety of tasks. Our objective is to facilitate long-term tremor monitoring; tremor is the most prevalent movement disorder. Two assumptions are made: 1) movement and tremor demonstrate an additive effect further down the kinematic chain; 2) most applications have chained or fixed sensor locations. These assumptions justify obtaining absolute location through identifying relative location and thus to allow us to simplify the classification algorithm. Seventeen tasks were performed by patients suffering from essential tremor or Parkinson's disease. Ten features were found that resulted in 98.30% average accuracy (min: 92.31%; max: 100%) for the best configuration, irrespective of the task being performed. The method presented here is an important step towards more user-friendly and context-aware neuroprostheses for tremor suppression and monitoring, and facilitates the use of wearable sensors by non-trained personnel.

Use of smartphones and portable media devices for quantifying human movement characteristics of gait, tendon reflex response, and Parkinson's disease hand tremor

Smartphones and portable media devices are both equipped with sensor components, such as accelerometers. A software application enables these devices to function as a robust wireless accelerometer platform. The recorded accelerometer waveform can be transmitted wireless as an e-mail attachment through connectivity to the Internet. The implication of such devices as a wireless accelerometer platform is the experimental and post-processing locations can be placed anywhere in the world. Gait was quantified by mounting a smartphone or portable media device proximal to the lateral malleolus of the ankle joint. Attributes of the gait cycle were quantified with a considerable accuracy and reliability. The patellar tendon reflex response was quantified by using the device in tandem with a potential energy impact pendulum to evoke the patellar tendon reflex. The acceleration waveform maximum acceleration feature of the reflex response displayed considerable accuracy and reliability. By mounting the smartphone or portable media device to the dorsum of the hand through a glove, Parkinson's disease hand tremor was quantified and contrasted with significance to a non-Parkinson's disease steady hand control. With the methods advocated in this chapter, any aspect of human movement may be quantified through smartphones or portable media devices and post-processed anywhere in the world. These wearable devices are anticipated to substantially impact the biomedical and healthcare industry.

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.

Detecting Parkinsons' symptoms in uncontrolled home environments: a multiple instance learning approach

In this paper, we propose to use a weakly supervised machine learning framework for automatic detection of Parkinson's Disease motor symptoms in daily living environments. Our primary goal is to develop a monitoring system capable of being used outside of controlled laboratory settings. Such a system would enable us to track medication cycles at home and provide valuable clinical feedback. Most of the relevant prior works involve supervised learning frameworks (e.g., Support Vector Machines). However, in-home monitoring provides only coarse ground truth information about symptom occurrences, making it very hard to adapt and train supervised learning classifiers for symptom detection. We address this challenge by formulating symptom detection under incomplete ground truth information as a multiple instance learning (MIL) problem. MIL is a weakly supervised learning framework that does not require exact instances of symptom occurrences for training; rather, it learns from approximate time intervals within which a symptom might or might not have occurred on a given day. Once trained, the MIL detector was able to spot symptom-prone time windows on other days and approximately localize the symptom instances. We monitored two Parkinson's disease (PD) patients, each for four days with a set of five triaxial accelerometers and utilized a MIL algorithm based on axis parallel rectangle (APR) fitting in the feature space. We were able to detect subject specific symptoms (e.g. dyskinesia) that conformed with a daily log maintained by the patients.