Accuracy of Smartphone Video for Contactless Measurement of Hand Tremor Frequency

Development of a smartphone screening test for preclinical Alzheimer's disease and validation across the dementia continuum

BACKGROUND

Dementia prevalence is predicted to triple to 152 million globally by 2050. Alzheimer's disease (AD) constitutes 70% of cases. There is an urgent need to identify individuals with preclinical AD, a 10-20-year period of progressive brain pathology without noticeable cognitive symptoms, for targeted risk reduction. Current tests of AD pathology are either too invasive, specialised or expensive for population-level assessments. Cognitive tests are normal in preclinical AD. Emerging evidence demonstrates that movement analysis is sensitive to AD across the disease continuum, including preclinical AD. Our new smartphone test, TapTalk, combines analysis of hand and speech-like movements to detect AD risk. This study aims to [1] determine which combinations of hand-speech movement data most accurately predict preclinical AD [2], determine usability, reliability, and validity of TapTalk in cognitively asymptomatic older adults and [3], prospectively validate TapTalk in older adults who have cognitive symptoms against cognitive tests and clinical diagnoses of Mild Cognitive Impairment and AD dementia.

METHODS

Aim 1 will be addressed in a cross-sectional study of at least 500 cognitively asymptomatic older adults who will complete computerised tests comprising measures of hand motor control (finger tapping) and oro-motor control (syllabic diadochokinesis). So far, 1382 adults, mean (SD) age 66.20 (7.65) years, range 50-92 (72.07% female) have been recruited. Motor measures will be compared to a blood-based AD biomarker, phosphorylated tau 181 to develop an algorithm that classifies preclinical AD risk. Aim 2 comprises three sub-studies in cognitively asymptomatic adults: (i) a cross-sectional study of 30-40 adults to determine the validity of data collection from different types of smartphones, (ii) a prospective cohort study of 50-100 adults ≥ 50 years old to determine usability and test-retest reliability, and (iii) a prospective cohort study of ~1,000 adults ≥ 50 years old to validate against cognitive measures. Aim 3 will be addressed in a cross-sectional study of ~200 participants with cognitive symptoms to validate TapTalk against Montreal Cognitive Assessment and interdisciplinary consensus diagnosis.

DISCUSSION

This study will establish the precision of TapTalk to identify preclinical AD and estimate risk of cognitive decline. If accurate, this innovative smartphone app will enable low-cost, accessible screening of individuals for AD risk. This will have wide applications in public health initiatives and clinical trials.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT06114914, 29 October 2023. Retrospectively registered.

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.

Brief webcam test of hand movements predicts episodic memory, executive function, and working memory in a community sample of cognitively asymptomatic older adults

INTRODUCTION

Low-cost simple tests for preclinical Alzheimer's disease are a research priority. We evaluated whether remote unsupervised webcam recordings of finger-tapping were associated with cognitive performance in older adults.

METHODS

A total of 404 cognitively-asymptomatic participants (64.6 [6.77] years; 70.8% female) completed 10-second finger-tapping tests (Tasmanian [TAS] Test) and cognitive tests (Cambridge Neuropsychological Test Automated Battery [CANTAB]) online at home. Regression models including hand movement features were compared with null models (comprising age, sex, and education level); change in Akaike Information Criterion greater than 2 (ΔAIC > 2) denoted statistical difference.

RESULTS

Hand movement features improved prediction of episodic memory, executive function, and working memory scores (ΔAIC > 2). Dominant hand features outperformed nondominant hand features for episodic memory (ΔAIC = 2.5), executive function (ΔAIC = 4.8), and working memory (ΔAIC = 2.2).

DISCUSSION

This brief webcam test improved prediction of cognitive performance compared to age, sex, and education. Finger-tapping holds potential as a remote language-agnostic screening tool to stratify community cohorts at risk for cognitive decline.

Contactless hand tremor amplitude measurement using smartphones: development and pilot evaluation

Background - Physiological tremor is defined as an involuntary and rhythmic shaking. Tremor of the hand is a key symptom of multiple neurological diseases, and its frequency and amplitude differs according to both disease type and disease progression. In routine clinical practice, tremor frequency and amplitude are assessed by expert rating using a 0 to 4 integer scale. Such ratings are subjective and have poor inter-rater reliability. There is thus a clinical need for a practical and accurate method for objectively assessing hand tremor.Objective - to develop a proof-of-principle method to measure hand tremor amplitude from smartphone videos.Methods - We created a computer vision pipeline that automatically extracts salient points on the hand and produces a 1-D time series of movement due to tremor, in pixels. Using the smartphones' depth measurement, we convert this measure into real distance units. We assessed the accuracy of the method using 60 videos of simulated tremor of different amplitudes from two healthy adults. Videos were taken at distances of 50, 75 and 100 cm between hand and camera. The participants had skin tone II and VI on the Fitzpatrick scale. We compared our method to a gold-standard measurement from a slide rule. Bland-Altman methods agreement analysis indicated a bias of 0.04 cm and 95% limits of agreement from -1.27 to 1.20 cm. Furthermore, we qualitatively observed that the method was robust to limited occlusion.Clinical relevance - We have demonstrated how tremor amplitude can be measured from smartphone videos. In conjunction with tremor frequency, this approach could be used to help diagnose and monitor neurological diseases.

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

INTRODUCTION

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

AREAS COVERED

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

EXPERT OPINION

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

A systematic review of the applications of markerless motion capture (MMC) technology for clinical measurement in rehabilitation

BACKGROUND

Markerless motion capture (MMC) technology has been developed to avoid the need for body marker placement during motion tracking and analysis of human movement. Although researchers have long proposed the use of MMC technology in clinical measurement-identification and measurement of movement kinematics in a clinical population, its actual application is still in its preliminary stages. The benefits of MMC technology are also inconclusive with regard to its use in assessing patients' conditions. In this review we put a minor focus on the method's engineering components and sought primarily to determine the current application of MMC as a clinical measurement tool in rehabilitation.

METHODS

A systematic computerized literature search was conducted in PubMed, Medline, CINAHL, CENTRAL, EMBASE, and IEEE. The search keywords used in each database were "Markerless Motion Capture OR Motion Capture OR Motion Capture Technology OR Markerless Motion Capture Technology OR Computer Vision OR Video-based OR Pose Estimation AND Assessment OR Clinical Assessment OR Clinical Measurement OR Assess." Only peer-reviewed articles that applied MMC technology for clinical measurement were included. The last search took place on March 6, 2023. Details regarding the application of MMC technology for different types of patients and body parts, as well as the assessment results, were summarized.

RESULTS

A total of 65 studies were included. The MMC systems used for measurement were most frequently used to identify symptoms or to detect differences in movement patterns between disease populations and their healthy counterparts. Patients with Parkinson's disease (PD) who demonstrated obvious and well-defined physical signs were the largest patient group to which MMC assessment had been applied. Microsoft Kinect was the most frequently used MMC system, although there was a recent trend of motion analysis using video captured with a smartphone camera.

CONCLUSIONS

This review explored the current uses of MMC technology for clinical measurement. MMC technology has the potential to be used as an assessment tool as well as to assist in the detection and identification of symptoms, which might further contribute to the use of an artificial intelligence method for early screening for diseases. Further studies are warranted to develop and integrate MMC system in a platform that can be user-friendly and accurately analyzed by clinicians to extend the use of MMC technology in the disease populations.

Artificial intelligence-assisted smartphone-based sensing for bioanalytical applications: A review

Artificial intelligence (AI) has received great attention since the concept was proposed, and it has developed rapidly in recent years with applications in many fields. Meanwhile, newer iterations of smartphone hardware technologies which have excellent data processing capabilities have leveraged on AI capabilities. Based on the desirability for portable detection, researchers have been investigating intelligent analysis by combining smartphones with AI algorithms. Various examples of the application of AI algorithm-based smartphone detection and analysis have been developed. In this review, we give an overview of this field, with a particular focus on bioanalytical detection applications. The applications are presented in terms of hardware design, software algorithms, and specific application areas. We also discuss the existing limitations of AI-based smartphone detection and analytical approaches, and their future prospects. The take-home message of our review is that the application of AI in the field of detection analysis is restricted by the limitations of the smartphone's hardware as well as the model building of AI for detection targets with insufficient data. Nevertheless, at this juncture, while bioanalytical diagnostics and health monitoring have set the pace for AI-based smartphone applicability, the future should see the technology making greater inroads into other fields. In relation to the latter, it is likely that the ordinary or average person will play a greater participatory role.

Assessing the Usability of an Instagram Filter in Monitoring Essential Tremor: A Proof-of-Concept Study

Background

Spiral drawing is an important test in monitoring essential tremor (ET). With the rise of telemedicine amid the coronavirus disease 2019 pandemic, a contactless tool for monitoring tremors was required. We aimed to assess the validity of a novel smartphone technology using a video-based social media platform for rapid and objective monitoring of ET.

Methods

A prospective pilot study evaluated patients with ET in 2 clinic visits. Videos of tremors were recorded using a publicly available Instagram filter and were visually compared with spirals drawn by the patients. The level of agreement among the raters was evaluated.

Results

A total of 12 patients with ET were recruited. A consensus between both raters was achieved for 11 patients (91.6%) for both spirals and videos with good interrater agreement (κ value, 0.755 ± 0.332).

Conclusion

This novel method was found to be valid and easy to use in measuring ET in real-world settings. Further research in a larger cohort is needed to suggest its use as a home-based or clinic-based monitoring tool.

Smartphone video nystagmography using convolutional neural networks: ConVNG

Background

Eye movement abnormalities are commonplace in neurological disorders. However, unaided eye movement assessments lack granularity. Although videooculography (VOG) improves diagnostic accuracy, resource intensiveness precludes its broad use. To bridge this care gap, we here validate a framework for smartphone video-based nystagmography capitalizing on recent computer vision advances.

Methods

A convolutional neural network was fine-tuned for pupil tracking using > 550 annotated frames: ConVNG. In a cross-sectional approach, slow-phase velocity of optokinetic nystagmus was calculated in 10 subjects using ConVNG and VOG. Equivalence of accuracy and precision was assessed using the “two one-sample t-test” (TOST) and Bayesian interval-null approaches. ConVNG was systematically compared to OpenFace and MediaPipe as computer vision (CV) benchmarks for gaze estimation.

Results

ConVNG tracking accuracy reached 9–15% of an average pupil diameter. In a fully independent clinical video dataset, ConVNG robustly detected pupil keypoints (median prediction confidence 0.85). SPV measurement accuracy was equivalent to VOG (TOST p < 0.017; Bayes factors (BF) > 24). ConVNG, but not MediaPipe, achieved equivalence to VOG in all SPV calculations. Median precision was 0.30°/s for ConVNG, 0.7°/s for MediaPipe and 0.12°/s for VOG. ConVNG precision was significantly higher than MediaPipe in vertical planes, but both algorithms’ precision was inferior to VOG.

Conclusions

ConVNG enables offline smartphone video nystagmography with an accuracy comparable to VOG and significantly higher precision than MediaPipe, a benchmark computer vision application for gaze estimation. This serves as a blueprint for highly accessible tools with potential to accelerate progress toward precise and personalized Medicine.

Exploring the relationship between brain white matter change and higher degree of invisible hand tremor with computer technology

BACKGROUND: At present, the clinical diagnosis of white matter change (WMC) patients depends on cranial magnetic resonance imaging (MRI) technology. This diagnostic method is costly and does not allow for large-scale screening, leading to delays in the patient’s condition due to inability to receive timely diagnosis. OBJECTIVE: To evaluate whether the burden of WMC is associated with the degree of invisible hand tremor in humans. METHODS: Previous studies have shown that tremor is associated with WMC, however, tremor does not always have imaging of WMC. Therefore, to confirm that the appearance of WMC causes tremor, which are sometimes invisible to the naked eye, we achieved an optical-based computer-aided diagnostic device by detecting the invisible hand tremor, and we proposed a calculation method of WMC volume by using the characteristics of MRI images. RESULTS: Statistical analysis results further clarified the relationship between WMC and tremor, and our devices are validated for the detection of tremors with WMC. CONCLUSIONS: The burden of WMC volume is positive factor for degree of invisible hand tremor in the participants without visible hand tremor. Detection technology provides a more convenient and low-cost evaluating method before MRI for tremor diseases.

Video-Based Hand Movement Analysis of Parkinson Patients before and after Medication Using High-Frame-Rate Videos and MediaPipe

Tremor is one of the common symptoms of Parkinson's disease (PD). Thanks to the recent evolution of digital technologies, monitoring of PD patients' hand movements employing contactless methods gained momentum. Objective: We aimed to quantitatively assess hand movements in patients suffering from PD using the artificial intelligence (AI)-based hand-tracking technologies of MediaPipe. Method: High-frame-rate videos and accelerometer data were recorded from 11 PD patients, two of whom showed classical Parkinsonian-type tremor. In the OFF-state and 30 Minutes after taking their standard oral medication (ON-state), video recordings were obtained. First, we investigated the frequency and amplitude relationship between the video and accelerometer data. Then, we focused on quantifying the effect of taking standard oral treatments. Results: The data extracted from the video correlated well with the accelerometer-based measurement system. Our video-based approach identified the tremor frequency with a small error rate (mean absolute error 0.229 (±0.174) Hz) and an amplitude with a high correlation. The frequency and amplitude of the hand movement before and after medication in PD patients undergoing medication differ. PD Patients experienced a decrease in the mean value for frequency from 2.012 (±1.385) Hz to 1.526 (±1.007) Hz and in the mean value for amplitude from 8.167 (±15.687) a.u. to 4.033 (±5.671) a.u. Conclusions: Our work achieved an automatic estimation of the movement frequency, including the tremor frequency with a low error rate, and to the best of our knowledge, this is the first paper that presents automated tremor analysis before/after medication in PD, in particular using high-frame-rate video data.

The TAS Test project: a prospective longitudinal validation of new online motor-cognitive tests to detect preclinical Alzheimer's disease and estimate 5-year risks of cognitive decline and dementia

BACKGROUND

The worldwide prevalence of dementia is rapidly rising. Alzheimer's disease (AD), accounts for 70% of cases and has a 10-20-year preclinical period, when brain pathology covertly progresses before cognitive symptoms appear. The 2020 Lancet Commission estimates that 40% of dementia cases could be prevented by modifying lifestyle/medical risk factors. To optimise dementia prevention effectiveness, there is urgent need to identify individuals with preclinical AD for targeted risk reduction. Current preclinical AD tests are too invasive, specialist or costly for population-level assessments. We have developed a new online test, TAS Test, that assesses a range of motor-cognitive functions and has capacity to be delivered at significant scale. TAS Test combines two innovations: using hand movement analysis to detect preclinical AD, and computer-human interface technologies to enable robust 'self-testing' data collection. The aims are to validate TAS Test to [1] identify preclinical AD, and [2] predict risk of cognitive decline and AD dementia.

METHODS

Aim 1 will be addressed through a cross-sectional study of 500 cognitively healthy older adults, who will complete TAS Test items comprising measures of motor control, processing speed, attention, visuospatial ability, memory and language. TAS Test measures will be compared to a blood-based AD biomarker, phosphorylated tau 181 (p-tau181). Aim 2 will be addressed through a 5-year prospective cohort study of 10,000 older adults. Participants will complete TAS Test annually and subtests of the Cambridge Neuropsychological Test Battery (CANTAB) biennially. 300 participants will undergo in-person clinical assessments. We will use machine learning of motor-cognitive performance on TAS Test to develop an algorithm that classifies preclinical AD risk (p-tau181-defined) and determine the precision to prospectively estimate 5-year risks of cognitive decline and AD.

DISCUSSION

This study will establish the precision of TAS Test to identify preclinical AD and estimate risk of cognitive decline and AD. If accurate, TAS Test will provide a low-cost, accessible enrichment strategy to pre-screen individuals for their likelihood of AD pathology prior to more expensive tests such as blood or imaging biomarkers. This would have wide applications in public health initiatives and clinical trials.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT05194787 , 18 January 2022. Retrospectively registered.

New horizons in late-onset essential tremor: a pre-cognitive biomarker of dementia?

Essential tremor (ET) is the most common cause of tremor in older adults. However, it is increasingly recognised that 30–50% of ET cases are misdiagnosed. Late-onset ET, when tremor begins after the age of 60, is particularly likely to be misdiagnosed and there is mounting evidence that it may be a distinct clinical entity, perhaps better termed ‘ageing-related tremor’. Compared with older adults with early-onset ET, late-onset ET is associated with weak grip strength, cognitive decline, dementia and mortality. This raises questions around whether late-onset ET is a pre-cognitive biomarker of dementia and whether modification of dementia risk factors may be particularly important in this group. On the other hand, it is possible that the clinical manifestations of late-onset ET simply reflect markers of healthy ageing, or frailty, superimposed on typical ET. These issues are important to clarify, especially in the era of specialist neurosurgical treatments for ET being increasingly offered to older adults, and these may not be suitable in people at high risk of cognitive decline. There is a pressing need for clinicians to understand late-onset ET, but this is challenging when there are so few publications specifically focussed on this subject and no specific features to guide prognosis. More rigorous clinical follow-up and precise phenotyping of the clinical manifestations of late-onset ET using accessible computer technologies may help us delineate whether late-onset ET is a separate clinical entity and aid prognostication.

Moving towards intelligent telemedicine: Computer vision measurement of human movement

Background:

Telemedicine video consultations are rapidly increasing globally, accelerated by the COVID-19 pandemic. This presents opportunities to use computer vision technologies to augment clinician visual judgement because video cameras are so ubiquitous in personal devices and new techniques, such as DeepLabCut (DLC) can precisely measure human movement from smartphone videos. However, the accuracy of DLC to track human movements in videos obtained from laptop cameras, which have a much lower FPS, has never been investigated; this is a critical gap because patients use laptops for most telemedicine consultations.

Objectives:

To determine the validity and reliability of DLC applied to laptop videos to measure finger tapping, a validated test of human movement.

Method:

Sixteen adults completed finger-tapping tests at 0.5 Hz, 1 Hz, 2 Hz, 3 Hz and at maximal speed. Hand movements were recorded simultaneously by a laptop camera at 30 frames per second (FPS) and by Optotrak, a 3D motion analysis system at 250 FPS. Eight DLC neural network architectures (ResNet50, ResNet101, ResNet152, MobileNetV1, MobileNetV2, EfficientNetB0, EfficientNetB3, EfficientNetB6) were applied to the laptop video and extracted movement features were compared to the ground truth Optotrak motion tracking.

Results:

Over 96% (529/552) of DLC measures were within +/−0.5 Hz of the Optotrak measures. At tapping frequencies >4 Hz, there was progressive decline in accuracy, attributed to motion blur associated with the laptop camera’s low FPS. Computer vision methods hold potential for moving us towards intelligent telemedicine by providing human movement analysis during consultations. However, further developments are required to accurately measure the fastest movements.

A Portable Non-Contact Tremor Vibration Measurement and Classification Apparatus

Tremors are the most common type of movement disorder and affect the lives of those experiencing them. The efficacy of tremor therapies varies according to the aetiology of the tremor and its correct diagnosis. This study develops a portable measurement device capable of non-contact measurement of the tremor, which could assist in tremor diagnosis and classification. The performance of this device was assessed through a validation process using a shaker at a controlled frequency to measure human tremors, and the device was able to measure vibrations of 50 Hz accurately, which is more than twice the frequency of tremors produced by humans. Then, the device is tested to measure the tremors for two different activation conditions: rest and postural, for both hand and leg. The measured non-contact tremor vibration data successfully led to tremor classification in the subjects already diagnosed using a contact accelerometer.

Next move in movement disorders (NEMO): developing a computer-aided classification tool for hyperkinetic movement disorders

INTRODUCTION

Our aim is to develop a novel approach to hyperkinetic movement disorder classification, that combines clinical information, electromyography, accelerometry and video in a computer-aided classification tool. We see this as the next step towards rapid and accurate phenotype classification, the cornerstone of both the diagnostic and treatment process.

METHODS AND ANALYSIS

The Next Move in Movement Disorders (NEMO) study is a cross-sectional study at Expertise Centre Movement Disorders Groningen, University Medical Centre Groningen. It comprises patients with single and mixed phenotype movement disorders. Single phenotype groups will first include dystonia, myoclonus and tremor, and then chorea, tics, ataxia and spasticity. Mixed phenotypes are myoclonus-dystonia, dystonic tremor, myoclonus ataxia and jerky/tremulous functional movement disorders. Groups will contain 20 patients, or 40 healthy participants. The gold standard for inclusion consists of interobserver agreement on the phenotype among three independent clinical experts. Electromyography, accelerometry and three-dimensional video data will be recorded during performance of a set of movement tasks, chosen by a team of specialists to elicit movement disorders. These data will serve as input for the machine learning algorithm. Labels for supervised learning are provided by the expert-based classification, allowing the algorithm to learn to predict what the output label should be when given new input data. Methods using manually engineered features based on existing clinical knowledge will be used, as well as deep learning methods which can detect relevant and possibly new features. Finally, we will employ visual analytics to visualise how the classification algorithm arrives at its decision.

ETHICS AND DISSEMINATION

Ethical approval has been obtained from the relevant local ethics committee. The NEMO study is designed to pioneer the application of machine learning of movement disorders. We expect to publish articles in multiple related fields of research and patients will be informed of important results via patient associations and press releases.

Hand tremor detection in videos with cluttered background using neural network based approaches

With the increasing prevalence of neurodegenerative diseases, including Parkinson’s disease, hand tremor detection has become a popular research topic because it helps with the diagnosis and tracking of disease progression. Conventional hand tremor detection algorithms involved wearable sensors. A non-invasive hand tremor detection algorithm using videos as input is desirable but the existing video-based algorithms are sensitive to environmental conditions. An algorithm, with the capability of detecting hand tremor from videos with a cluttered background, would allow the videos recorded in a non-research environment to be used. Clinicians and researchers could use videos collected from patients and participants in their own home environment or standard clinical settings. Neural network based machine learning architectures provide high accuracy classification results in related fields including hand gesture recognition and body movement detection systems. We thus investigated the accuracy of advanced neural network architectures to automatically detect hand tremor in videos with a cluttered background. We examined configurations with different sets of features and neural network based classification models. We compared the performance of different combinations of features and classification models and then selected the combination which provided the highest accuracy of hand tremor detection. We used cross validation to test the accuracy of the trained model predictions. The highest classification accuracy for automatically detecting tremor (vs non tremor) was 80.6% and this was obtained using Convolutional Neural Network-Long Short-Term Memory and features based on measures of frequency and amplitude change.