Smartphone-based evaluation of parkinsonian hand tremor: quantitative measurements vs clinical assessment scores

Smartphone-Based Hand Function Assessment: Systematic Review

BACKGROUND

Hand function assessment heavily relies on specific task scenarios, making it challenging to ensure validity and reliability. In addition, the wide range of assessment tools, limited and expensive data recording, and analysis systems further aggravate the issue. However, smartphones provide a promising opportunity to address these challenges. Thus, the built-in, high-efficiency sensors in smartphones can be used as effective tools for hand function assessment.

OBJECTIVE

This review aims to evaluate existing studies on hand function evaluation using smartphones.

METHODS

An information specialist searched 8 databases on June 8, 2023. The search criteria included two major concepts: (1) smartphone or mobile phone or mHealth and (2) hand function or function assessment. Searches were limited to human studies in the English language and excluded conference proceedings and trial register records. Two reviewers independently screened all studies, with a third reviewer involved in resolving discrepancies. The included studies were rated according to the Mixed Methods Appraisal Tool. One reviewer extracted data on publication, demographics, hand function types, sensors used for hand function assessment, and statistical or machine learning (ML) methods. Accuracy was checked by another reviewer. The data were synthesized and tabulated based on each of the research questions.

RESULTS

In total, 46 studies were included. Overall, 11 types of hand dysfunction-related problems were identified, such as Parkinson disease, wrist injury, stroke, and hand injury, and 6 types of hand dysfunctions were found, namely an abnormal range of motion, tremors, bradykinesia, the decline of fine motor skills, hypokinesia, and nonspecific dysfunction related to hand arthritis. Among all built-in smartphone sensors, the accelerometer was the most used, followed by the smartphone camera. Most studies used statistical methods for data processing, whereas ML algorithms were applied for disease detection, disease severity evaluation, disease prediction, and feature aggregation.

CONCLUSIONS

This systematic review highlights the potential of smartphone-based hand function assessment. The review suggests that a smartphone is a promising tool for hand function evaluation. ML is a conducive method to classify levels of hand dysfunction. Future research could (1) explore a gold standard for smartphone-based hand function assessment and (2) take advantage of smartphones' multiple built-in sensors to assess hand function comprehensively, focus on developing ML methods for processing collected smartphone data, and focus on real-time assessment during rehabilitation training. The limitations of the research are 2-fold. First, the nascent nature of smartphone-based hand function assessment led to limited relevant literature, affecting the evidence's completeness and comprehensiveness. This can hinder supporting viewpoints and drawing conclusions. Second, literature quality varies due to the exploratory nature of the topic, with potential inconsistencies and a lack of high-quality reference studies and meta-analyses.

NeuroDiag: Software for Automated Diagnosis of Parkinson's Disease Using Handwriting

OBJECTIVE

A change in handwriting is an early sign of Parkinson's disease (PD). However, significant inter-person differences in handwriting make it difficult to identify pathological handwriting, especially in the early stages. This paper reports the testing of NeuroDiag, a software-based medical device, for the automated detection of PD using handwriting patterns. NeuroDiag is designed to direct the user to perform six drawing and writing tasks, and the recordings are then uploaded onto a server for analysis. Kinematic information and pen pressure of handwriting are extracted and used as baseline parameters. NeuroDiag was trained based on 26 PD patients in the early stage of the disease and 26 matching controls.

METHODS

Twenty-three people with PD (PPD) in their early stage of the disease, 25 age-matched healthy controls (AMC), and 7 young healthy controls were recruited for this study. Under the supervision of a consultant neurologist or their nurse, the participants used NeuroDiag. The reports were generated in real-time and tabulated by an independent observer.

RESULTS

The participants were able to use NeuroDiag without assistance. The handwriting data was successfully uploaded to the server where the report was automatically generated in real-time. There were significant differences in the writing speed between PPD and AMC (P<0.001). NeuroDiag showed 86.96% sensitivity and 76.92% specificity in differentiating PPD from those without PD.

CONCLUSION

In this work, we tested the reliability of NeuroDiag in differentiating between PPD and AMC for real-time applications. The results show that NeuroDiag has the potential to be used to assist neurologists and for telehealth applications. Clinical and Translational Impact Statement - This pre-clinical study shows the feasibility of developing a community-wide screening program for Parkinson's disease using automated handwriting analysis software, NeuroDiag.

Acute Effect of Transcutaneous Auricular Vagus Nerve Stimulation on Hand Tremor in Parkinson's Disease: A Pilot Study of Case Series

Objectives

The aim of this study is to investigate the effects of non-invasive vagus nerve stimulation (VNS) on tremor in Parkinson's disease (PD).

Methods

This single-center, prospective, and implementation study with before-after design included five participants diagnosed with PD. Auricular VNS was applied to each participant 3 times on different days. VNS was applied to the participants as the right ear, left ear, and bilateral ear. The cardiovascular parameters of the participants were evaluated with Kubios HRV Standard and tremor with UPDRS tremor subscale and smartphone application before and after the intervention.

Results

Significant decrease in diastolic blood pressure (p=0.043) was found in participants who underwent bilateral auricular VNS. Although there was no significant change in the UPDRS tremor subscale, decreases in the maximum tremor amplitude in the x (p=0.043) and y (0.014) planes were detected in the measurements made with the smartphone application.

Conclusion

In this study, a decrease in the tremor amplitude measured in the 3D plane with auricular VNS was found in patients with PD.

Diagnosis and Treatment of Tremor in Parkinson's Disease Using Mechanical Devices

BACKGROUND

Parkinsonian tremors are sometimes confused with essential tremors or other conditions. Recently, researchers conducted several studies on tremor evaluation using wearable sensors and devices, which may support accurate diagnosis. Mechanical devices are also commonly used to treat tremors and have been actively researched and developed. Here, we aimed to review recent progress and the efficacy of the devices related to Parkinsonian tremors.

METHODS

The PubMed and Scopus databases were searched for articles. We searched for "Parkinson disease" and "tremor" and "device".

RESULTS

Eighty-six articles were selected by our systematic approach. Many studies demonstrated that the diagnosis and evaluation of tremors in patients with PD can be done accurately by machine learning algorithms. Mechanical devices for tremor suppression include deep brain stimulation (DBS), electrical muscle stimulation, and orthosis. In recent years, adaptive DBS and optimization of stimulation parameters have been studied to further improve treatment efficacy.

CONCLUSIONS

Due to developments using state-of-the-art techniques, effectiveness in diagnosing and evaluating tremor and suppressing it using these devices is satisfactorily high in many studies. However, other than DBS, no devices are in practical use. To acquire high-level evidence, large-scale studies and randomized controlled trials are needed for these devices.

The hand tremor spectrum is modified by the inertial sensor mass during lightweight wearable and smartphone-based assessment in healthy young subjects

Tremors are common disorders characterized by an involuntary and relatively rhythmic oscillation that can occur in any part of the body and may be physiological or associated with some pathological condition. It is known that the mass loading can change the power spectral distribution of the tremor. Nowadays, many instruments have been used in the evaluation of tremors with bult-in inertial sensors, such as smartphones and wearables, which can significantly differ in the device mass. The aim of this study was to compare the quantification of hand tremor using Fourier spectral techniques obtained from readings of accelerometers built-in a lightweight handheld device and a commercial smartphone in healthy young subjects. We recruited 28 healthy right-handed subjects with ages ranging from 18 to 40 years. We tested hand tremors at rest and postural conditions using lightweight wearable device (5.7 g) and smartphone (169 g). Comparing both devices at resting tremor, we found with smartphone the power distribution of peak ranging 5 and 12 Hz in both hands. With wearable, the result was similar but less evident. When comparing both devices in postural tremor, there were significant differences in both frequency ranges in peak frequency and peak amplitude in both hands. Our main findings show that in resting condition the hand tremor spectrum had a higher peak amplitude in the 5–12 Hz range when the tremor was recorded with smartphones, and in postural condition there was a significantly (p < 0.05) higher peak power spectrum and peak frequency in the dominant hand tremors recorded with smartphones compared to those obtained with lightweight wearable device. Devices having different masses can alter the features of the hand tremor spectrum and their mutual comparisons can be prejudiced.

Task-Oriented Intelligent Solution to Measure Parkinson's Disease Tremor Severity

Tremor is a common symptom of Parkinson's disease (PD). Currently, tremor is evaluated clinically based on MDS-UPDRS Rating Scale, which is inaccurate, subjective, and unreliable. Precise assessment of tremor severity is the key to effective treatment to alleviate the symptom. Therefore, several objective methods have been proposed for measuring and quantifying PD tremor from data collected while patients performing scripted and unscripted tasks. However, up to now, the literature appears to focus on suggesting tremor severity classification methods without discrimination tasks effect on classification and tremor severity measurement. In this study, a novel approach to identify a recommended system is used to measure tremor severity, including the influence of tasks performed during data collection on classification performance. The recommended system comprises recommended tasks, classifier, classifier hyperparameters, and resampling technique. The proposed approach is based on the above-average rule of five advanced metrics results of four subdatasets, six resampling techniques, six classifiers besides signal processing, and features extraction techniques. The results of this study indicate that tasks that do not involve direct wrist movements are better than tasks that involve direct wrist movements for tremor severity measurements. Furthermore, resampling techniques improve classification performance significantly. The findings of this study suggest that a recommended system consists of support vector machine (SVM) classifier combined with BorderlineSMOTE oversampling technique and data collection while performing set of recommended tasks, which are sitting, stairs up and down, walking straight, walking while counting, and standing.

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.

A-WEAR Bracelet for Detection of Hand Tremor and Bradykinesia in Parkinson's Patients

Parkinson's disease patients face numerous motor symptoms that eventually make their life different from those of normal healthy controls. Out of these motor symptoms, tremor and bradykinesia, are relatively prevalent in all stages of this disease. The assessment of these symptoms is usually performed by traditional methods where the accuracy of results is still an open question. This research proposed a solution for an objective assessment of tremor and bradykinesia in subjects with PD (10 older adults aged greater than 60 years with tremor and 10 older adults aged greater than 60 years with bradykinesia) and 20 healthy older adults aged greater than 60 years. Physical movements were recorded by means of an AWEAR bracelet developed using inertial sensors, i.e., 3D accelerometer and gyroscope. Participants performed upper extremities motor activities as adopted by neurologists during the clinical assessment based on Unified Parkinson's Disease Rating Scale (UPDRS). For discriminating the patients from healthy controls, temporal and spectral features were extracted, out of which non-linear temporal and spectral features show greater difference. Both supervised and unsupervised machine learning classifiers provide good results. Out of 40 individuals, neural net clustering discriminated 34 individuals in correct classes, while the KNN approach discriminated 91.7% accurately. In a clinical environment, the doctor can use the device to comprehend the tremor and bradykinesia of patients quickly and with higher accuracy.

The CloudUPDRS smartphone software in Parkinson's study: cross-validation against blinded human raters

Digital assessments of motor severity could improve the sensitivity of clinical trials and personalise treatment in Parkinson’s disease (PD) but have yet to be widely adopted. Their ability to capture individual change across the heterogeneous motor presentations typical of PD remains inadequately tested against current clinical reference standards. We conducted a prospective, dual-site, crossover-randomised study to determine the ability of a 16-item smartphone-based assessment (the index test) to predict subitems from the Movement Disorder Society-Unified Parkinson’s Disease Rating Scale part III (MDS-UPDRS III) as assessed by three blinded clinical raters (the reference-standard). We analysed data from 60 subjects (990 smartphone tests, 2628 blinded video MDS-UPDRS III subitem ratings). Subject-level predictive performance was quantified as the leave-one-subject-out cross-validation (LOSO-CV) accuracy. A pre-specified analysis classified 70.3% (SEM 5.9%) of subjects into a similar category to any of three blinded clinical raters and was better than random (36.7%; SEM 4.3%) classification. Post hoc optimisation of classifier and feature selection improved performance further (78.7%, SEM 5.1%), although individual subtests were variable (range 53.2–97.0%). Smartphone-based measures of motor severity have predictive value at the subject level. Future studies should similarly mitigate against subjective and feature selection biases and assess performance across a range of motor features as part of a broader strategy to avoid overly optimistic performance estimates.

Quantitative assessment of Parkinsonian tremor by using biosensor device

Parkinson disease (PD) is the second most common neurodegenerative disease which affects population older than 65 years. Tremor represents one of the main symptomatic triads in PD, particularly in rest state.We enrolled 41 idiopathic PD patients, to validate the assessment of tremor symptoms.To be enrolled in the study, patients had to fulfill the movement disorder society clinical diagnostic criteria for PD.We used an innovative home-made, low-cost device, able to quantify the frequency and amplitude of rest tremor and stress conditionOur results confirmed the presence of tremor during muscular effort in a significant number of patients and the influence of emotional stress.We suppose that this new device should be validated in clinical practice as a support of differential diagnosis and therapeutic management of PD patients.

Metadata Concepts for Advancing the Use of Digital Health Technologies in Clinical Research

Digital health technologies (smartphones, smartwatches, and other body-worn sensors) can act as novel tools to aid in the diagnosis and remote objective monitoring of an individual's disease symptoms, both in clinical care and in research. Nonetheless, such digital health technologies have yet to widely demonstrate value in clinical research due to insufficient data interpretability and lack of regulatory acceptance. Metadata, i.e., data that accompany and describe the primary data, can be utilized to better understand the context of the sensor data and can assist in data management, data sharing, and subsequent data analysis. The need for data and metadata standards for digital health technologies has been raised in academic and industry research communities and has also been noted by regulatory authorities. Therefore, to address this unmet need, we here propose a metadata set that reflects regulatory guidelines and that can serve as a conceptual map to (1) inform researchers on the metadata they should collect in digital health studies, aiming to increase the interpretability and exchangeability of their data, and (2) direct standard development organizations on how to extend their existing standards to incorporate digital health technologies. The proposed metadata set is informed by existing standards pertaining to clinical trials and medical devices, in addition to existing schemas that have supported digital health technology studies. We illustrate this specifically in the context of Parkinson's disease, as a model for a wide range of other chronic conditions for which remote monitoring would be useful in both care and science. We invite the scientific and clinical research communities to apply the proposed metadata set to ongoing and planned research. Where the proposed metadata fall short, we ask users to contribute to its ongoing revision so that an adequate degree of consensus can be maintained in a rapidly evolving technology landscape.

A review of physiological and behavioral monitoring with digital sensors for neuropsychiatric illnesses

Physiological, behavioral, and psychological changes associated with neuropsychiatric illness are reflected in several related signals, including actigraphy, location, word sentiment, voice tone, social activity, heart rate, and responses to standardized questionnaires. These signals can be passively monitored using sensors in smartphones, wearable accelerometers, Holter monitors, and multimodal sensing approaches that fuse multiple data types. Connection of these devices to the internet has made large scale studies feasible and is enabling a revolution in neuropsychiatric monitoring. Currently, evaluation and diagnosis of neuropsychiatric disorders relies on clinical visits, which are infrequent and out of the context of a patient's home environment. Moreover, the demand for clinical care far exceeds the supply of providers. The growing prevalence of context-aware and physiologically relevant digital sensors in consumer technology could help address these challenges, enable objective indexing of patient severity, and inform rapid adjustment of treatment in real-time. Here we review recent studies utilizing such sensors in the context of neuropsychiatric illnesses including stress and depression, bipolar disorder, schizophrenia, post traumatic stress disorder, Alzheimer's disease, and Parkinson's disease.

Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab

The use of wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the accuracy achievable with such technology is highly reliant on separating the useful from irrelevant sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety of practical challenges, such as recording unexpected user behaviors. These behaviors often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab and affect the accuracy of the subsequent data analysis and scientific conclusions. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data that are sufficiently reliable for further analysis. Combining both parametric and nonparametric signal processing and machine learning techniques, we demonstrate that across 100 subjects and 300 clinimetric tests from three different types of behavioral clinimetric protocols, the system shows an average segmentation accuracy of around 90%. By extracting reliable sensor data, it is possible to strip the data of confounding factors in the environment that may threaten reproducibility and replicability.

Evidence assessing the diagnostic performance of medical smartphone apps: a systematic review and exploratory meta-analysis

OBJECTIVE

The number of mobile applications addressing health topics is increasing. Whether these apps underwent scientific evaluation is unclear. We comprehensively assessed papers investigating the diagnostic value of available diagnostic health applications using inbuilt smartphone sensors.

METHODS

Systematic Review-MEDLINE, Scopus, Web of Science inclusive Medical Informatics and Business Source Premier (by citation of reference) were searched from inception until 15 December 2016. Checking of reference lists of review articles and of included articles complemented electronic searches. We included all studies investigating a health application that used inbuilt sensors of a smartphone for diagnosis of disease. The methodological quality of 11 studies used in an exploratory meta-analysis was assessed with the Quality Assessment of Diagnostic Accuracy Studies 2 tool and the reporting quality with the 'STAndards for the Reporting of Diagnostic accuracy studies' (STARD) statement. Sensitivity and specificity of studies reporting two-by-two tables were calculated and summarised.

RESULTS

We screened 3296 references for eligibility. Eleven studies, most of them assessing melanoma screening apps, reported 17 two-by-two tables. Quality assessment revealed high risk of bias in all studies. Included papers studied 1048 subjects (758 with the target conditions and 290 healthy volunteers). Overall, the summary estimate for sensitivity was 0.82 (95 % CI 0.56 to 0.94) and 0.89 (95 %CI 0.70 to 0.97) for specificity.

CONCLUSIONS

The diagnostic evidence of available health apps on Apple's and Google's app stores is scarce. Consumers and healthcare professionals should be aware of this when using or recommending them.

PROSPERO REGISTRATION NUMBER

42016033049.

Automatic Classification of Tremor Severity in Parkinson's Disease Using a Wearable Device

Although there is clinical demand for new technology that can accurately measure Parkinsonian tremors, automatic scoring of Parkinsonian tremors using machine-learning approaches has not yet been employed. This study aims to fill this gap by proposing machine-learning algorithms as a way to predict the Unified Parkinson’s Disease Rating Scale (UPDRS), which are similar to how neurologists rate scores in actual clinical practice. In this study, the tremor signals of 85 patients with Parkinson’s disease (PD) were measured using a wrist-watch-type wearable device consisting of an accelerometer and a gyroscope. The displacement and angle signals were calculated from the measured acceleration and angular velocity, and the acceleration, angular velocity, displacement, and angle signals were used for analysis. Nineteen features were extracted from each signal, and the pairwise correlation strategy was used to reduce the number of feature dimensions. With the selected features, a decision tree (DT), support vector machine (SVM), discriminant analysis (DA), random forest (RF), and k-nearest-neighbor (kNN) algorithm were explored for automatic scoring of the Parkinsonian tremor severity. The performance of the employed classifiers was analyzed using accuracy, recall, and precision, and compared to other findings in similar studies. Finally, the limitations and plans for further study are discussed.

Differential diagnosis between Parkinson's disease and essential tremor using the smartphone's accelerometer

Background

The differential diagnosis between patients with essential tremor (ET) and those with Parkinson’s disease (PD) whose main manifestation is tremor may be difficult unless using complex neuroimaging techniques such as ¹²³I-FP-CIT SPECT. We considered that using smartphone’s accelerometer to stablish a diagnostic test based on time-frequency differences between PD an ET could support the clinical diagnosis.

Methods

The study was carried out in 17 patients with PD, 16 patients with ET, 12 healthy volunteers and 7 patients with tremor of undecided diagnosis (TUD), who were re-evaluated one year after the first visit to reach the definite diagnosis. The smartphone was placed over the hand dorsum to record epochs of 30 s at rest and 30 s during arm stretching. We generated frequency power spectra and calculated receiver operating characteristics curves (ROC) curves of total spectral power, to establish a threshold to separate subjects with and without tremor. In patients with PD and ET, we found that the ROC curve of relative energy was the feature discriminating better between the two groups. This threshold was then used to classify the TUD patients.

Results

We could correctly classify 49 out of 52 subjects in the category with/without tremor (97.96% sensitivity and 83.3% specificity) and 27 out of 32 patients in the category PD/ET (84.38% discrimination accuracy). Among TUD patients, 2 of 2 PD and 2 of 4 ET were correctly classified, and one patient having PD plus ET was classified as PD.

Conclusions

Based on the analysis of smartphone accelerometer recordings, we found several kinematic features in the analysis of tremor that distinguished first between healthy subjects and patients and, ultimately, between PD and ET patients. The proposed method can give immediate results for the clinician to gain valuable information for the diagnosis of tremor. This can be useful in environments where more sophisticated diagnostic techniques are unavailable.

Assessment of Head Tremor with Accelerometers Versus Gyroscopic Transducers

Background

Accelerometers and gyroscopes are used commonly in the assessment of hand tremor, but their validity in the assessment of head tremor has not been studied. We hypothesized that gyroscopy would be superior to accelerometry because head tremor is rotational motion, and gyroscopes record rotational motion, free of gravitational artifact. We also hypothesized a strong logarithmic relationship between 0 to 4-point tremor ratings and the transducer measures of tremor amplitude, similar to those previously reported for hand tremor.

Methods

Head tremor was recorded for 1 minute in each of the five head positions used in the Essential Tremor Rating Assessment Scale, using a triaxial accelerometer and triaxial gyroscope mounted at the vertex of the head. Mean and maximum 3-second burst displacement tremor and rotation tremor were computed by spectral analysis. The minimum detectable change for the transducers was estimated using the residual mean squared error from repeated-measures analysis of variance.

Results

Tremor displacement and rotation (T) were logarithmically related to tremor ratings (tremor rating score; TRS): log(T) = α TRS + β, where α ≈ 0.47 for displacement and ≈0.64 for rotation, and β ≈ -1.8 and -1.4. Tremor ratings correlated more strongly with gyroscopy (r = 0.83-0.87) than with accelerometry (r = 0.71-0.75). Minimum detectable change (percent reduction) was approximately 66% of the baseline geometric mean.

Conclusions

Gyroscopic transducers are superior to accelerometry for assessment of head tremor. Both measures of head tremor are logarithmically related to tremor ratings. The minimum detectable change of the transducer measures is comparable to those previously reported for hand tremor.

A Smartphone-Based Tool for Assessing Parkinsonian Hand Tremor

The aim of this study is to propose a practical smartphone-based tool to accurately assess upper limb tremor in Parkinson's disease (PD) patients. The tool uses signals from the phone's accelerometer and gyroscope (as the phone is held or mounted on a subject's hand) to compute a set of metrics which can be used to quantify a patient's tremor symptoms. In a small-scale clinical study with 25 PD patients and 20 age-matched healthy volunteers, we combined our metrics with machine learning techniques to correctly classify 82% of the patients and 90% of the healthy volunteers, which is high compared to similar studies. The proposed method could be effective in assisting physicians in the clinic, or to remotely evaluate the patient's condition and communicate the results to the physician. Our tool is low cost, platform independent, noninvasive, and requires no expertise to use. It is also well matched to the standard clinical examination for PD and can keep the patient "connected" to his physician on a daily basis. Finally, it can facilitate the creation of anonymous profiles for PD patients, aiding further research on the effectiveness of medication or other overlooked aspects of patients' lives.