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

Tremor assessment using smartphone sensor data and fuzzy reasoning

Background

Tremor severity assessment is an important step for the diagnosis and treatment decision-making of essential tremor (ET) patients. Traditionally, tremor severity is assessed by using questionnaires (e.g., ETRS and QUEST surveys). In this work we assume the possibility of assessing tremor severity using sensor data and computerized analyses. The goal of this work is to assess severity of tremor objectively, to be better able to asses improvement in ET patients due to deep brain stimulation or other treatments.

Methods

We collect tremor data by strapping smartphones to the wrists of ET patients. The resulting raw sensor data is then pre-processed to remove any artifact due to patient’s intentional movement. Finally, this data is exploited to automatically build a transparent, interpretable, and succinct fuzzy model for the severity assessment of ET. For this purpose, we exploit pyFUME, a tool for the data-driven estimation of fuzzy models. It leverages the FST-PSO swarm intelligence meta-heuristic to identify optimal clusters in data, reducing the possibility of a premature convergence in local minima which would result in a sub-optimal model. pyFUME was also combined with GRABS, a novel methodology for the automatic simplification of fuzzy rules.

Results

Our model is able to assess tremor severity of patients suffering from Essential Tremor, notably without the need for subjective questionnaires nor interviews. The fuzzy model improves the mean absolute error (MAE) metric by 78–81% compared to linear models and by 71–74% compared to a model based on decision trees.

Conclusion

This study confirms that tremor data gathered using the smartphones is useful for the constructing of machine learning models that can be used to support the diagnosis and monitoring of patients who suffer from Essential Tremor. The model produced by our methodology is easy to inspect and, notably, characterized by a lower error with respect to approaches based on linear models or decision trees.

Smartwatch inertial sensors continuously monitor real-world motor fluctuations in Parkinson's disease

Longitudinal, remote monitoring of motor symptoms in Parkinson's disease (PD) could enable more precise treatment decisions. We developed the Motor fluctuations Monitor for Parkinson's Disease (MM4PD), an ambulatory monitoring system that used smartwatch inertial sensors to continuously track fluctuations in resting tremor and dyskinesia. We designed and validated MM4PD in 343 participants with PD, including a longitudinal study of up to 6 months in a 225-subject cohort. MM4PD measurements correlated to clinical evaluations of tremor severity (ρ = 0.80) and mapped to expert ratings of dyskinesia presence (P < 0.001) during in-clinic tasks. MM4PD captured symptom changes in response to treatment that matched the clinician's expectations in 94% of evaluated subjects. In the remaining 6% of cases, symptom data from MM4PD identified opportunities to make improvements in pharmacologic strategy. These results demonstrate the promise of MM4PD as a tool to support patient-clinician communication, medication titration, and clinical trial design.

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.

IMPLEMENTATION OF A SMARTPHONE AS A WIRELESS ACCELEROMETER PLATFORM FOR QUANTIFYING HEMIPLEGIC GAIT DISPARITY IN A FUNCTIONALLY AUTONOMOUS CONTEXT

The utility of the smartphone, such as the iPhone, constitutes considerable potential for the advancement of the biomedical and healthcare industry. A notable feature of the iPhone is the capacity to combine the internal accelerometer sensor with a software application to enable the functionality of a wireless accelerometer platform. Preliminary research has demonstrated the iPhone’s ability to quantify features of healthy gait. The research applies a single iPhone mounted proximal to the lateral malleolus of the affected leg and subsequently the unaffected leg to ascertain quantified disparity of hemiplegic gait from an engineering proof of concept perspective. In order to maintain a consistent gait velocity, a constant velocity treadmill is incorporated into the research endeavor. Post-processing of the gait acceleration waveform is greatly facilitated through the use of a software automation program using Matlab that emphasizes on the rhythmicity of gait. Two gait parameters were obtained: stance-to-stance temporal disparity and stance-to-stance time-averaged acceleration, and demonstrated considerable accuracy, consistency, and reliability. As noted per the constant treadmill velocity, stance-to-stance temporal disparity for the affected and unaffected legs was established as not statistically significant. A statistical significance was determined for the stance-to-stance time-averaged acceleration regarding the affected and unaffected legs. The iPhone application represents a wireless accelerometer platform capable of identifying statistically significant and quantified disparity of hemiplegic gait features through automated post-processing in a functionally autonomous environment.

IMPLEMENTATION OF A SMARTPHONE WIRELESS GYROSCOPE PLATFORM WITH MACHINE LEARNING FOR CLASSIFYING DISPARITY OF A HEMIPLEGIC PATELLAR TENDON REFLEX PAIR

The patellar tendon reflex response provides fundamental means of assessing a subject’s neurological health. Dysfunction regarding the characteristics of the reflex response may warrant the escalation to more advanced diagnostic techniques. Current strategies involve the manual elicitation of the patellar tendon reflex by a highly skilled clinician with subsequent interpretation according to an ordinal scale. The reliability of the ordinal scale approach is a topic of contention. Highly skilled clinicians have been in disagreement regarding even the observation of asymmetric reflex pairs. An alternative strategy incorporated the ubiquitous smartphone with a software application to function as a wireless gyroscope platform for quantifying the reflex response. Each gyroscope signal recording of the reflex response can be conveyed wirelessly through Internet connectivity as an email attachment. The reflex response is evoked through a potential energy impact pendulum that enables prescribed targeting and potential energy level. The smartphone functioning as a wireless gyroscope platform reveals an observationally representative gyroscope signal of the reflex response. Three notably distinguishable attributes of the reflex response are incorporated into a feature set for machine learning: maximum angular rate of rotation, minimum angular rate of rotation, and time disparity between maximum and minimum angular rate of rotation. Four machine learning platforms such as the J48 decision tree, K-nearest neighbors, logistic regression, and support vector machine, were applied to the patellar tendon reflex response feature set incorporating a hemiplegic patellar tendon reflex pair. The J48 decision tree attained 98% classification accuracy, and the K-nearest neighbors, logistic regression, and support vector machine achieved perfect classification accuracy for distinguishing between a hemiplegic affected leg and unaffected leg patellar tendon reflex pair. The research findings reveal the potential of machine learning for enabling advanced diagnostic acuity respective of the gyroscope signal of the patellar tendon reflex response.

Wireless gyroscope platform enabled by a portable media device for quantifying wobble board therapy

The wobble board enables a therapy strategy for rehabilitation of the ankle foot complex. Quantification of therapy, such as through the use of a wobble board, can facilitate a therapist's acuity for advancing and optimizing the overall therapy strategy. The portable media device, such as an iPod, can be equipped with a software application to function as a wireless gyroscope platform. Integration of the wobble board with the portable media device functioning as a wireless gyroscope enables the potential for patient to therapist interaction through connectivity to the Internet. A patient can conduct wobble board therapy for the ankle foot complex from the convenient vantage point of a homebound setting with therapy data transmitted wirelessly as email attachments. The gyroscope signal of the wobble board therapy can be consolidated into a feature set for machine learning classification. Using a multilayer perceptron neural network considerable classification accuracy has been achieved for differentiating between a hemiplegic affected ankle and unaffected ankle while using a wobble board. The combination of machine learning, wireless systems, such as a portable media device functioning as a wireless gyroscope, and a conventional therapy device, such as a wobble board, are envisioned to advance the capability to optimally impact the rehabilitation experience.

Quantitative Measurement of Akinesia in Parkinson's Disease

BACKGROUND

There is great interest in developing simple, user-friendly, and inexpensive tools for the quantification and elucidation of motor deficits in patients with Parkinson's disease (PD). These systems could help to monitor the clinical status of patients with PD, to develop better treatments, and to identify individuals who have subtle motor signs that might pass unnoticed in the conventional neurological examination.

METHODS

Mememtum, a smartphone application that allows for the quantification of several parameters of movement, such as regularity, rhythm, and changes in the number of taps while taping with a single finger and with alternating fingers, was developed and then tested in a pilot study in Madrid and in an extensive study in Quito, Ecuador.

RESULTS

Almost all patients could successfully perform single-finger tapping, but approximately 10% of patients with severe parkinsonism had problems taping with alternating fingers. The results revealed changes in the regularity of the pressure applied while tapping and a reduction in the number of taps on the device screen when alternating tapping among patients who had idiopathic PD and vascular parkinsonism compared with controls and individuals who had prediagnostic motor abnormalities of PD.

CONCLUSION

Applications available in smartphones could be used for investigation and treatment of patients with PD, but much research is needed to optimize the ideal parameters to be investigated and the potential usefulness of this technique for patients with PD in different stages of the disease.

Implementation of a smartphone as a wireless gyroscope platform for quantifying reduced arm swing in hemiplegie gait with machine learning classification by multilayer perceptron neural network

Natural gait consists of synchronous and rhythmic patterns for both the lower and upper limb. People with hemiplegia can experience reduced arm swing, which can negatively impact the quality of gait. Wearable and wireless sensors, such as through a smartphone, have demonstrated the ability to quantify various features of gait. With a software application the smartphone (iPhone) can function as a wireless gyroscope platform capable of conveying a gyroscope signal recording as an email attachment by wireless connectivity to the Internet. The gyroscope signal recordings of the affected hemiplegic arm with reduced arm swing arm and the unaffected arm are post-processed into a feature set for machine learning. Using a multilayer perceptron neural network a considerable degree of classification accuracy is attained to distinguish between the affected hemiplegic arm with reduced arm swing arm and the unaffected arm.

Clinical Assessments in Parkinson's Disease: Scales and Monitoring

Measurement of disease state is essential in both clinical practice and research in order to assess the severity and progression of a patient's disease status, effect of treatment, and alterations in other relevant factors. Parkinson's disease (PD) is a complex disorder expressed through many motor and nonmotor manifestations, which cause disabilities that can vary both gradually over time or come on suddenly. In addition, there is a wide interpatient variability making the appraisal of the many facets of this disease difficult. Two kinds of measure are used for the evaluation of PD. The first is subjective, inferential, based on rater-based interview and examination or patient self-assessment, and consist of rating scales and questionnaires. These evaluations provide estimations of conceptual, nonobservable factors (e.g., symptoms), usually scored on an ordinal scale. The second type of measure is objective, factual, based on technology-based devices capturing physical characteristics of the pathological phenomena (e.g., sensors to measure the frequency and amplitude of tremor). These instrumental evaluations furnish appraisals with real numbers on an interval scale for which a unit exists. In both categories of measures, a broad variety of tools exist. This chapter aims to present an up-to-date summary of the most relevant characteristics of the most widely used scales, questionnaires, and technological resources currently applied to the assessment of PD. The review concludes that, in our opinion: (1) no assessment methods can substitute the clinical judgment and (2) subjective and objective measures in PD complement each other, each method having strengths and weaknesses.

GAIT ANALYSIS: SYSTEMS, TECHNOLOGIES, AND IMPORTANCE

Human gait is the identity of a person's style and quality of life. Reliable cognition of gait properties over time, continuous monitoring, accuracy of evaluation, and proper analysis of human gait characteristics have demonstrated their importance not only in clinical and medical studies, but also in the field of sports, rehabilitation, training, and robotics research. Focusing on walking gait, this study presents an overview on gait mechanisms, common technologies used in gait analysis, and importance of this particular field of research. Firstly, available technologies that involved in gait analysis are briefly introduced in this paper by concentrating on the usability and limitations of the systems. Secondly, key gait parameters and motion characteristics are elucidated from four angles of views; one: gait phases and gait properties; two: center of mass and center of pressure (CoM-CoP) tracking profile; three: Ground Reaction Force (GRF) and impact, and four: muscle activation. Thirdly, the study focuses on the clinical observations of gait patterns in diagnosing gait abnormalities of impaired patients. The presentation also shows the importance of gait analysis in sports to improve performance as well as to avoid risk of injuries of sports personnel. Significance of gait analysis in robotic research is also illustrated in this part where the study focuses on robot assisted systems and its possible applicability in clinical rehabilitation and sports training.

A Validation Study of a Smartphone-Based Finger Tapping Application for Quantitative Assessment of Bradykinesia in Parkinson's Disease

Background

Most studies of smartphone-based assessments of motor symptoms in Parkinson’s disease (PD) focused on gait, tremor or speech. Studies evaluating bradykinesia using wearable sensors are limited by a small cohort size and study design. We developed an application named smartphone tapper (SmT) to determine its applicability for clinical purposes and compared SmT parameters to current standard methods in a larger cohort.

Methods

A total of 57 PD patients and 87 controls examined with motor UPDRS underwent timed tapping tests (TT) using SmT and mechanical tappers (MeT) according to CAPSIT-PD. Subjects were asked to alternately tap each side of two rectangles with an index finger at maximum speed for ten seconds. Kinematic measurements were compared between the two groups.

Results

The mean number of correct tapping (MCoT), mean total distance of finger movement (T-Dist), mean inter-tap distance, and mean inter-tap dwelling time (IT-DwT) were significantly different between PD patients and controls. MCoT, as assessed using SmT, significantly correlated with motor UPDRS scores, bradykinesia subscores and MCoT using MeT. Multivariate analysis using the SmT parameters, such as T-Dist or IT-DwT, as predictive variables and age and gender as covariates demonstrated that PD patients were discriminated from controls. ROC curve analysis of a regression model demonstrated that the AUC for T-Dist was 0.92 (95% CI 0.88–0.96).

Conclusion

Our results suggest that a smartphone tapping application is comparable to conventional methods for the assessment of motor dysfunction in PD and may be useful in clinical practice.

Validation of a smartphone-based measurement tool for the quantification of level walking

INTRODUCTION

It is important to assess and quantify gait in order to determine the severity of impairments during gait and to evaluate therapeutic interventions. However, laboratory gait assessment is expensive and time consuming and there is a lack of an easily applicable tool for the quantification of gait in clinical practice. The aim of this study was to validate a smartphone-based measurement tool for the quantification of level walking.

METHODS

Vertical center of mass displacement and step duration of 22 healthy young adults were assessed by a smartphone application and a motion capture system. Intra-session reliability was evaluated by repeated-measures ANOVA, intraclass correlation coefficient (ICC), and standard error of measurement. In order to evaluate the concurrent validity of the smartphone application, smartphone- and motion capture-derived values were compared by Pearson correlation coefficient and Bland-Altman limits of agreement.

RESULTS

Six out of eight variables derived by the smartphone application showed an excellent reliability (ICC≥0.75) and all variables correlated significantly with measurements of the motion capture system with moderate to strong correlations ranging from 0.61 to 0.92.

CONCLUSION

The results showed a great potential of the smartphone application to be a user-friendly and valid tool for the assessment of gait in clinical practice. Further research needs to investigate whether the smartphone application is able to detect differences in gait patterns following therapeutic or orthopedic interventions and whether it is valid for the quantification of gait in people with movement disorders.

Implementation of a smartphone wireless accelerometer platform for establishing deep brain stimulation treatment efficacy of essential tremor with machine learning

Essential tremor (ET) is a highly prevalent movement disorder. Patients with ET exhibit a complex progressive and disabling tremor, and medical management often fails. Deep brain stimulation (DBS) has been successfully applied to this disorder, however there has been no quantifiable way to measure tremor severity or treatment efficacy in this patient population. The quantified amelioration of kinetic tremor via DBS is herein demonstrated through the application of a smartphone (iPhone) as a wireless accelerometer platform. The recorded acceleration signal can be obtained at a setting of the subject's convenience and conveyed by wireless transmission through the Internet for post-processing anywhere in the world. Further post-processing of the acceleration signal can be classified through a machine learning application, such as the support vector machine. Preliminary application of deep brain stimulation with a smartphone for acquisition of a feature set and machine learning for classification has been successfully applied. The support vector machine achieved 100% classification between deep brain stimulation in `on' and `off' mode based on the recording of an accelerometer signal through a smartphone as a wireless accelerometer platform.