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

Generalizing Parkinson's disease detection using keystroke dynamics: a self-supervised approach

OBJECTIVE

Passive monitoring of touchscreen interactions generates keystroke dynamic signals that can be used to detect and track neurological conditions such as Parkinson's disease (PD) and psychomotor impairment with minimal burden on the user. However, this typically requires datasets with clinically confirmed labels collected in standardized environments, which is challenging, especially for a large subject pool. This study validates the efficacy of a self-supervised learning method in reducing the reliance on labels and evaluates its generalizability.

MATERIALS AND METHODS

We propose a new type of self-supervised loss combining Barlow Twins loss, which attempts to create similar feature representations with reduced feature redundancy for samples coming from the same subject, and a Dissimilarity loss, which promotes uncorrelated features for samples generated by different subjects. An encoder is first pre-trained using this loss on unlabeled data from an uncontrolled setting, then fine-tuned with clinically validated data. Our experiments test the model generalizability with controls and subjects with PD on 2 independent datasets.

RESULTS

Our approach showed better generalization compared to previous methods, including a feature engineering strategy, a deep learning model pre-trained on Parkinsonian signs, and a traditional supervised model.

DISCUSSION

The absence of standardized data acquisition protocols and the limited availability of annotated datasets compromise the generalizability of supervised models. In these contexts, self-supervised models offer the advantage of learning more robust patterns from the data, bypassing the need for ground truth labels.

CONCLUSION

This approach has the potential to accelerate the clinical validation of touchscreen typing software for neurodegenerative diseases.

Passive assessment of tapping speed through smartphone is useful for monitoring multiple sclerosis

INTRODUCTION

Continuously acquired smartphone keyboard interactions may be useful to monitor progression in multiple sclerosis (MS). We aimed to study the correlation between tapping speed (TS), measured as keys/s, and baseline disability scales in patients with MS.

METHODS

Single-center prospective study in patients with MS. We passively assessed TS during first week, measured by an "in house" smartphone application. Reliability was assessed by intraclass correlation coefficient (ICC). Correlations between median and maximum keys/s of first week of assessment and baseline disability measures were explored.

RESULTS

One-hundred three patients were included: 62.1 % women, with a median (IQR) age of 47 (40.4-54.8) years-old and an EDSS score of 3.0 (2.0-4.0). Distribution by MS subtypes was: 77.7 % relapsing-remitting MS (RRMS), 17.5 % secondary-progressive MS (SPMS) and 4.9 % primary-progressive MS (PPMS). ICC during first week was 0.714 (p < 0.00001). Both median and maximum keys/s showed a negative correlation with Expanded Disability Status Score, 9-hole peg test and timed 25-foot walk and a positive correlation with Processing Speed Test CogEval® raw and Z-score. Median and maximum keys/s were lower in patients diagnosed with SPMS than in RRMS. Both measures of tapping speed were associated with MS phenotype independently of age.

CONCLUSION

TS measured through our application is reliable and correlates with baseline disability scales.

Detection of Parkinson's disease with keystroke data

Parkinson's disease (PD) is one of the most widespread neurological disorders associated with nerve damage without definitive treatment. Impairments, such as trembling and slowing down in hand movements are among the first symptoms. For this purpose, in this study, machine learning (ML)-based models were developed by using keyboard keystroke dynamics. According to patients' drug use status, disease severity, and gender, we created 14 different sub-datasets and extracted 378 features using raw keystroke data. We developed alternative models with Support Vector Machines (SVM), k-Nearest Neighbors (kNN), and Random Forest (RF) algorithms. We further used Minimum Redundancy Maximum Relevance (mRmR), RELIEF, sequential forward selection (SFS), and RF feature selection methods to investigate prominent features in distinguishing PD. We developed ML models that jointly use the most popular features of selection algorithms (feature ensemble [FE]) and an ensemble classifier by combining multiple ML algorithms utilizing majority vote (model ensemble [ME]). With 14 different sets, FE and ME models provided accuracy (Acc.) in the range of 91.73 - 100% and 81.08 - 100%, respectively.

Exploring Asymmetric Fine Motor Impairment Trends in Early Parkinson's Disease via Keystroke Typing

Background

The nQiMechPD algorithm transforms natural typing data into a numerical index that characterizes motor impairment in people with Parkinson's Disease (PwPD).

Objectives

Use nQiMechPD to compare asymmetrical progression of PD-related impairment in dominant (D-PD) versus non-dominant side onset (ND-PD) de-novo patients.

Methods

Keystroke data were collected from 53 right-handed participants (15 D-PD, 13 ND-PD, 25 controls). We apply linear mixed effects modeling to evaluate participants' right, left, and both hands nQiMechPD relative change by group.

Results

The 6-month nQiMechPD trajectories of right (**P = 0.002) and both (*P = 0.043) hands showed a significant difference in nQiMechPD trends between D-PD and ND-PD participants. Left side trends were not significantly different between these two groups (P = 0.328).

Conclusions

Significant differences between D-PD and ND-PD groups were observed, likely driven by contrasting dominant hand trends. Our findings suggest disease onset side may influence motor impairment progression, medication response, and functional outcomes in PwPD.

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).

A scoping review of neurodegenerative manifestations in explainable digital phenotyping

Neurologists nowadays no longer view neurodegenerative diseases, like Parkinson's and Alzheimer's disease, as single entities, but rather as a spectrum of multifaceted symptoms with heterogeneous progression courses and treatment responses. The definition of the naturalistic behavioral repertoire of early neurodegenerative manifestations is still elusive, impeding early diagnosis and intervention. Central to this view is the role of artificial intelligence (AI) in reinforcing the depth of phenotypic information, thereby supporting the paradigm shift to precision medicine and personalized healthcare. This suggestion advocates the definition of disease subtypes in a new biomarker-supported nosology framework, yet without empirical consensus on standardization, reliability and interpretability. Although the well-defined neurodegenerative processes, linked to a triad of motor and non-motor preclinical symptoms, are detected by clinical intuition, we undertake an unbiased data-driven approach to identify different patterns of neuropathology distribution based on the naturalistic behavior data inherent to populations in-the-wild. We appraise the role of remote technologies in the definition of digital phenotyping specific to brain-, body- and social-level neurodegenerative subtle symptoms, emphasizing inter- and intra-patient variability powered by deep learning. As such, the present review endeavors to exploit digital technologies and AI to create disease-specific phenotypic explanations, facilitating the understanding of neurodegenerative diseases as "bio-psycho-social" conditions. Not only does this translational effort within explainable digital phenotyping foster the understanding of disease-induced traits, but it also enhances diagnostic and, eventually, treatment personalization.

Long Short-Term Memory-Based Deep Learning Models for Screening Parkinson's Disease Using Sequential Diagnostic Codes

BACKGROUND AND PURPOSE

It is challenging to detect Parkinson's disease (PD) in its early stages, which has prompted researchers to develop techniques based on machine learning methods for detecting PD. However, previous studies did not fully incorporate the slow progression of PD over a long period of time nor consider that its symptoms occur in a time-sequential manner. Contributing to the literature on PD, which has relied heavily on cross-sectional data, this study aimed to develop a method for detecting PD early that can process time-series information using the long short-term memory (LSTM) algorithm.

METHODS

We sampled 926 patients with PD and 9,260 subjects without PD using medical-claims data. The LSTM algorithm was tested using diagnostic histories, which contained the diagnostic codes and their respective time information. We compared the prediction power of the 12-month diagnostic codes under two different settings over the 4 years prior to the first PD diagnosis.

RESULTS

The model that was trained using the most-recent 12-month diagnostic codes had the best performance, with an accuracy of 94.25%, a sensitivity of 82.91%, and a specificity of 95.26%. The other three models (12-month codes from 2, 3, and 4 years prior) were found to have comparable performances, with accuracies of 92.27%, 91.86%, and 91.81%, respectively. The areas under the curve from our data settings ranged from 0.839 to 0.923.

CONCLUSIONS

We explored the possibility that PD specialists could benefit from our proposed machine learning method as an early detection method for PD.

Keystroke-Dynamics for Parkinson's Disease Signs Detection in an At-Home Uncontrolled Population: A New Benchmark and Method

Parkinson's disease (PD) is the second most prevalent neurodegenerative disease disorder in the world. A prompt diagnosis would enable clinical trials for disease-modifying neuroprotective therapies. Recent research efforts have unveiled imaging and blood markers that have the potential to be used to identify PD patients promptly, however, the idiopathic nature of PD makes these tests very hard to scale to the general population. To this end, we need an easily deployable tool that would enable screening for PD signs in the general population. In this work, we propose a new set of features based on keystroke dynamics, i.e., the time required to press and release keyboard keys during typing, and used to detect PD in an ecologically valid data acquisition setup at the subject's homes, without requiring any pre-defined task. We compare and contrast existing models presented in the literature and present a new model that combines a new type of keystroke dynamics signal representation using hold time and flight time series as a function of key types and asymmetry in the time series using a convolutional neural network. We show how this model achieves an Area Under the Receiving Operating Characteristic curve ranging from 0.80 to 0.83 on a dataset of subjects who actively interacted with their computers for at least 5 months and positively compares against other state-of-the-art approaches previously tested on keystroke dynamics data acquired with mechanical keyboards.

An Extended Review Concerning the Relevance of Deep Learning and Privacy Techniques for Data-Driven Soft Sensors

The continuously increasing number of mobile devices actively being used in the world amounted to approximately 6.8 billion by 2022. Consequently, this implies a substantial increase in the amount of personal data collected, transported, processed, and stored. The authors of this paper designed and implemented an integrated personal health data management system, which considers data-driven software and hardware sensors, comprehensive data privacy techniques, and machine-learning-based algorithmic models. It was determined that there are very few relevant and complete surveys concerning this specific problem. Therefore, the current scientific research was considered, and this paper comprehensively analyzes the importance of deep learning techniques that are applied to the overall management of data collected by data-driven soft sensors. This survey considers aspects that are related to demographics, health and body parameters, and human activity and behaviour pattern detection. Additionally, the relatively complex problem of designing and implementing data privacy mechanisms, while ensuring efficient data access, is also discussed, and the relevant metrics are presented. The paper concludes by presenting the most important open research questions and challenges. The paper provides a comprehensive and thorough scientific literature survey, which is useful for any researcher or practitioner in the scope of data-driven soft sensors and privacy techniques, in relation to the relevant machine-learning-based models.

Digital Devices for Assessing Motor Functions in Mobility-Impaired and Healthy Populations: Systematic Literature Review

Background

With the advent of smart sensing technology, mobile and wearable devices can provide continuous and objective monitoring and assessment of motor function outcomes.

Objective

We aimed to describe the existing scientific literature on wearable and mobile technologies that are being used or tested for assessing motor functions in mobility-impaired and healthy adults and to evaluate the degree to which these devices provide clinically valid measures of motor function in these populations.

Methods

A systematic literature review was conducted by searching Embase, MEDLINE, CENTRAL (January 1, 2015, to June 24, 2020), the United States and European Union clinical trial registries, and the United States Food and Drug Administration website using predefined study selection criteria. Study selection, data extraction, and quality assessment were performed by 2 independent reviewers.

Results

A total of 91 publications representing 87 unique studies were included. The most represented clinical conditions were Parkinson disease (n=51 studies), followed by stroke (n=5), Huntington disease (n=5), and multiple sclerosis (n=2). A total of 42 motion-detecting devices were identified, and the majority (n=27, 64%) were created for the purpose of health care–related data collection, although approximately 25% were personal electronic devices (eg, smartphones and watches) and 11% were entertainment consoles (eg, Microsoft Kinect or Xbox and Nintendo Wii). The primary motion outcomes were related to gait (n=30), gross motor movements (n=25), and fine motor movements (n=23). As a group, sensor-derived motion data showed a mean sensitivity of 0.83 (SD 7.27), a mean specificity of 0.84 (SD 15.40), a mean accuracy of 0.90 (SD 5.87) in discriminating between diseased individuals and healthy controls, and a mean Pearson r validity coefficient of 0.52 (SD 0.22) relative to clinical measures. We did not find significant differences in the degree of validity between in-laboratory and at-home sensor-based assessments nor between device class (ie, health care–related device, personal electronic devices, and entertainment consoles).

Conclusions

Sensor-derived motion data can be leveraged to classify and quantify disease status for a variety of neurological conditions. However, most of the recent research on digital clinical measures is derived from proof-of-concept studies with considerable variation in methodological approaches, and much of the reviewed literature has focused on clinical validation, with less than one-quarter of the studies performing analytical validation. Overall, future research is crucially needed to further consolidate that sensor-derived motion data may lead to the development of robust and transformative digital measurements intended to predict, diagnose, and quantify neurological disease state and its longitudinal change.

The Use of Smartphone Keystroke Dynamics to Passively Monitor Upper Limb and Cognitive Function in Multiple Sclerosis: Longitudinal Analysis

Background

Typing on smartphones, which has become a near daily activity, requires both upper limb and cognitive function. Analysis of keyboard interactions during regular typing, that is, keystroke dynamics, could therefore potentially be utilized for passive and continuous monitoring of function in patients with multiple sclerosis.

Objective

To determine whether passively acquired smartphone keystroke dynamics correspond to multiple sclerosis outcomes, we investigated the association between keystroke dynamics and clinical outcomes (upper limb and cognitive function). This association was investigated longitudinally in order to study within-patient changes independently of between-patient differences.

Methods

During a 1-year follow-up, arm function and information processing speed were assessed every 3 months in 102 patients with multiple sclerosis with the Nine-Hole Peg Test and Symbol Digit Modalities Test, respectively. Keystroke-dynamics data were continuously obtained from regular typing on the participants’ own smartphones. Press-and-release latency of the alphanumeric keys constituted the fine motor score cluster, while latency of the punctuation and backspace keys constituted the cognition score cluster. The association over time between keystroke clusters and the corresponding clinical outcomes was assessed with linear mixed models with subjects as random intercepts. By centering around the mean and calculating deviation scores within subjects, between-subject and within-subject effects were distinguished.

Results

Mean (SD) scores for the fine motor score cluster and cognition score cluster were 0.43 (0.16) and 0.94 (0.41) seconds, respectively. The fine motor score cluster was significantly associated with the Nine-Hole Peg Test: between-subject β was 15.9 (95% CI 12.2-19.6) and within-subject β was 6.9 (95% CI 2.0-11.9). The cognition score cluster was significantly associated with the Symbol Digit Modalities Test between subjects (between-subject β –11.2, 95% CI –17.3 to –5.2) but not within subjects (within-subject β –0.4, 95% CI –5.6 to 4.9).

Conclusions

Smartphone keystroke dynamics were longitudinally associated with multiple sclerosis outcomes. Worse arm function corresponded with longer latency in typing both across and within patients. Worse processing speed corresponded with higher latency in using punctuation and backspace keys across subjects. Hence, keystroke dynamics are a potential digital biomarker for remote monitoring and predicting clinical outcomes in patients with multiple sclerosis.

Trial Registration

Netherlands Trial Register NTR7268; https://trialsearch.who.int/Trial2.aspx?TrialID=NTR7268

A novel framework to estimate cognitive impairment via finger interaction with digital devices

Measuring cognitive function is essential for characterizing brain health and tracking cognitive decline in Alzheimer’s Disease and other neurodegenerative conditions. Current tools to accurately evaluate cognitive impairment typically rely on a battery of questionnaires administered during clinical visits which is essential for the acquisition of repeated measurements in longitudinal studies. Previous studies have shown that the remote data collection of passively monitored daily interaction with personal digital devices can measure motor signs in the early stages of synucleinopathies, as well as facilitate longitudinal patient assessment in the real-world scenario with high patient compliance. This was achieved by the automatic discovery of patterns in the time series of keystroke dynamics, i.e. the time required to press and release keys, by machine learning algorithms. In this work, our hypothesis is that the typing patterns generated from user-device interaction may reflect relevant features of the effects of cognitive impairment caused by neurodegeneration. We use machine learning algorithms to estimate cognitive performance through the analysis of keystroke dynamic patterns that were extracted from mechanical and touchscreen keyboard use in a dataset of cognitively normal (n = 39, 51% male) and cognitively impaired subjects (n = 38, 60% male). These algorithms are trained and evaluated using a novel framework that integrates items from multiple neuropsychological and clinical scales into cognitive subdomains to generate a more holistic representation of multifaceted clinical signs. In our results, we see that these models based on typing input achieve moderate correlations with verbal memory, non-verbal memory and executive function subdomains [Spearman’s ρ between 0.54 (P < 0.001) and 0.42 (P < 0.001)] and a weak correlation with language/verbal skills [Spearman’s ρ 0.30 (P < 0.05)]. In addition, we observe a moderate correlation between our typing-based approach and the Total Montreal Cognitive Assessment score [Spearman’s ρ 0.48 (P < 0.001)]. Finally, we show that these machine learning models can perform better by using our subdomain framework that integrates the information from multiple neuropsychological scales as opposed to using the individual items that make up these scales. Our results support our hypothesis that typing patterns are able to reflect the effects of neurodegeneration in mild cognitive impairment and Alzheimer’s disease and that this new subdomain framework both helps the development of machine learning models and improves their interpretability.

Self-management interventions for people with Parkinson’s Disease: A scoping review (Preprint)

Background

Objective

Methods

Results

Conclusions

Diagnostic accuracy of keystroke dynamics as digital biomarkers for fine motor decline in neuropsychiatric disorders: a systematic review and meta-analysis

The unmet timely diagnosis requirements, that take place years after substantial neural loss and neuroperturbations in neuropsychiatric disorders, affirm the dire need for biomarkers with proven efficacy. In Parkinson's disease (PD), Mild Cognitive impairment (MCI), Alzheimers disease (AD) and psychiatric disorders, it is difficult to detect early symptoms given their mild nature. We hypothesize that employing fine motor patterns, derived from natural interactions with keyboards, also knwon as keystroke dynamics, could translate classic finger dexterity tests from clinics to populations in-the-wild for timely diagnosis, yet, further evidence is required to prove this efficiency. We have searched PubMED, Medline, IEEEXplore, EBSCO and Web of Science for eligible diagnostic accuracy studies employing keystroke dynamics as an index test for the detection of neuropsychiatric disorders as the main target condition. We evaluated the diagnostic performance of keystroke dynamics across 41 studies published between 2014 and March 2022, comprising 3791 PD patients, 254 MCI patients, and 374 psychiatric disease patients. Of these, 25 studies were included in univariate random-effect meta-analysis models for diagnostic performance assessment. Pooled sensitivity and specificity are 0.86 (95% Confidence Interval (CI) 0.82-0.90, I2 = 79.49%) and 0.83 (CI 0.79-0.87, I2 = 83.45%) for PD, 0.83 (95% CI 0.65-1.00, I2 = 79.10%) and 0.87 (95% CI 0.80-0.93, I2 = 0%) for psychomotor impairment, and 0.85 (95% CI 0.74-0.96, I2 = 50.39%) and 0.82 (95% CI 0.70-0.94, I2 = 87.73%) for MCI and early AD, respectively. Our subgroup analyses conveyed the diagnosis efficiency of keystroke dynamics for naturalistic self-reported data, and the promising performance of multimodal analysis of naturalistic behavioral data and deep learning methods in detecting disease-induced phenotypes. The meta-regression models showed the increase in diagnostic accuracy and fine motor impairment severity index with age and disease duration for PD and MCI. The risk of bias, based on the QUADAS-2 tool, is deemed low to moderate and overall, we rated the quality of evidence to be moderate. We conveyed the feasibility of keystroke dynamics as digital biomarkers for fine motor decline in naturalistic environments. Future work to evaluate their performance for longitudinal disease monitoring and therapeutic implications is yet to be performed. We eventually propose a partnership strategy based on a "co-creation" approach that stems from mechanistic explanations of patients' characteristics derived from data obtained in-clinics and under ecologically valid settings. The protocol of this systematic review and meta-analysis is registered in PROSPERO; identifier CRD42021278707. The presented work is supported by the KU-KAIST joint research center.

Remote Assessments of Hand Function in Neurological Disorders: Systematic Review

BACKGROUND

Loss of fine motor skills is observed in many neurological diseases, and remote monitoring assessments can aid in early diagnosis and intervention. Hand function can be regularly assessed to monitor loss of fine motor skills in people with central nervous system disorders; however, there are challenges to in-clinic assessments. Remotely assessing hand function could facilitate monitoring and supporting of early diagnosis and intervention when warranted.

OBJECTIVE

Remote assessments can facilitate the tracking of limitations, aiding in early diagnosis and intervention. This study aims to systematically review existing evidence regarding the remote assessment of hand function in populations with chronic neurological dysfunction.

METHODS

PubMed and MEDLINE, CINAHL, Web of Science, and Embase were searched for studies that reported remote assessment of hand function (ie, outside of traditional in-person clinical settings) in adults with chronic central nervous system disorders. We excluded studies that included participants with orthopedic upper limb dysfunction or used tools for intervention and treatment. We extracted data on the evaluated hand function domains, validity and reliability, feasibility, and stage of development.

RESULTS

In total, 74 studies met the inclusion criteria for Parkinson disease (n=57, 77% studies), stroke (n=9, 12%), multiple sclerosis (n=6, 8%), spinal cord injury (n=1, 1%), and amyotrophic lateral sclerosis (n=1, 1%). Three assessment modalities were identified: external device (eg, wrist-worn accelerometer), smartphone or tablet, and telerehabilitation. The feasibility and overall participant acceptability were high. The most common hand function domains assessed included finger tapping speed (fine motor control and rigidity), hand tremor (pharmacological and rehabilitation efficacy), and finger dexterity (manipulation of small objects required for daily tasks) and handwriting (coordination). Although validity and reliability data were heterogeneous across studies, statistically significant correlations with traditional in-clinic metrics were most commonly reported for telerehabilitation and smartphone or tablet apps. The most readily implementable assessments were smartphone or tablet-based.

CONCLUSIONS

The findings show that remote assessment of hand function is feasible in neurological disorders. Although varied, the assessments allow clinicians to objectively record performance in multiple hand function domains, improving the reliability of traditional in-clinic assessments. Remote assessments, particularly via telerehabilitation and smartphone- or tablet-based apps that align with in-clinic metrics, facilitate clinic to home transitions, have few barriers to implementation, and prompt remote identification and treatment of hand function impairments.

Parkinson's disease severity clustering based on tapping activity on mobile device

In this study, we investigated the relationship between finger tapping tasks on the smartphone and the MDS-UPDRS I–II and PDQ-8 using the mPower dataset. mPower is a mobile application-based study for monitoring key indicators of PD progression and diagnosis. Currently, it is one of the largest, open access, mobile Parkinson’s Disease studies. Data from seven modules with a total of 8,320 participants who provided the data of at least one task were released to the public researcher. The modules comprise demographics, MDS-UPDRS I–II, PDQ-8, memory, tapping, voice, and walking. Finger-tapping is one of the tasks that easy to perform and has been analyzed for the quantitative measurement of PD. Therefore, participants who performed both the tapping activity and MDS-UPDRS I–II rating scale were selected for our analysis. Note that the MDS-UPDRS mPower Survey only contains parts of the original scale and has not been clinimetrically tested for validity and reliability. We obtained a total of 1851 samples that contained the tapping activity and MDS-UPDRS I–II for the analysis. Nine features were selected to represent tapping activity. K-mean was applied as an unsupervised clustering algorithm in our study. For determining the number of clusters, the elbow method, Sihouette score, and Davies–Bouldin index, were employed as supporting evaluation metrics. Based on these metrics and expert opinion, we decide that three clusters were appropriate for our study. The statistical analysis found that the tapping features could separate participants into three severity groups. Each group has different characteristics and could represent different PD severity based on the MDS-UPDRS I–II and PDQ-8 scores. Currently, the severity assessment of a movement disorder is based on clinical observation. Therefore, it is highly dependant on the skills and experiences of the trained movement disorder specialist who performs the procedure. We believe that any additional methods that could potentially assist with quantitative assessment of disease severity, without the need for a clinical visit would be beneficial to both the healthcare professionals and patients.

Digital Phenotyping in Clinical Neurology

Internet-connected devices, including personal computers, smartphones, smartwatches, and voice assistants, have evolved into powerful multisensor technologies that billions of people interact with daily to connect with friends and colleagues, access and share information, purchase goods, play games, and navigate their environment. Digital phenotyping taps into the data streams captured by these devices to characterize and understand health and disease. The purpose of this article is to summarize opportunities for digital phenotyping in neurology, review studies using everyday technologies to obtain motor and cognitive information, and provide a perspective on how neurologists can embrace and accelerate progress in this emerging field.

Bias Investigation in Artificial Intelligence Systems for Early Detection of Parkinson's Disease: A Narrative Review

Background and Motivation: Diagnosis of Parkinson's disease (PD) is often based on medical attention and clinical signs. It is subjective and does not have a good prognosis. Artificial Intelligence (AI) has played a promising role in the diagnosis of PD. However, it introduces bias due to lack of sample size, poor validation, clinical evaluation, and lack of big data configuration. The purpose of this study is to compute the risk of bias (RoB) automatically.

METHOD

The PRISMA search strategy was adopted to select the best 39 AI studies out of 85 PD studies closely associated with early diagnosis PD. The studies were used to compute 30 AI attributes (based on 6 AI clusters), using AP(ai)Bias 1.0 (AtheroPointTM, Roseville, CA, USA), and the mean aggregate score was computed. The studies were ranked and two cutoffs (Moderate-Low (ML) and High-Moderate (MH)) were determined to segregate the studies into three bins: low-, moderate-, and high-bias.

RESULT

The ML and HM cutoffs were 3.50 and 2.33, respectively, which constituted 7, 13, and 6 for low-, moderate-, and high-bias studies. The best and worst architectures were "deep learning with sketches as outcomes" and "machine learning with Electroencephalography," respectively. We recommend (i) the usage of power analysis in big data framework, (ii) that it must undergo scientific validation using unseen AI models, and (iii) that it should be taken towards clinical evaluation for reliability and stability tests.

CONCLUSION

The AI is a vital component for the diagnosis of early PD and the recommendations must be followed to lower the RoB.

Breaking the Data Value-Privacy Paradox in Mobile Mental Health Systems Through User-Centered Privacy Protection: A Web-Based Survey Study

BACKGROUND

Mobile mental health systems (MMHS) have been increasingly developed and deployed in support of monitoring, management, and intervention with regard to patients with mental disorders. However, many of these systems rely on patient data collected by smartphones or other wearable devices to infer patients' mental status, which raises privacy concerns. Such a value-privacy paradox poses significant challenges to patients' adoption and use of MMHS; yet, there has been limited understanding of it.

OBJECTIVE

To address the significant literature gap, this research aims to investigate both the antecedents of patients' privacy concerns and the effects of privacy concerns on their continuous usage intention with regard to MMHS.

METHODS

Using a web-based survey, this research collected data from 170 participants with MMHS experience recruited from online mental health communities and a university community. The data analyses used both repeated analysis of variance and partial least squares regression.

RESULTS

The results showed that data type (P=.003), data stage (P<.001), privacy victimization experience (P=.01), and privacy awareness (P=.08) have positive effects on privacy concerns. Specifically, users report higher privacy concerns for social interaction data (P=.007) and self-reported data (P=.001) than for biometrics data; privacy concerns are higher for data transmission (P=.01) and data sharing (P<.001) than for data collection. Our results also reveal that privacy concerns have an effect on attitude toward privacy protection (P=.001), which in turn affects continuous usage intention with regard to MMHS.

CONCLUSIONS

This study contributes to the literature by deepening our understanding of the data value-privacy paradox in MMHS research. The findings offer practical guidelines for breaking the paradox through the design of user-centered and privacy-preserving MMHS.

Touchscreen-based finger tapping: Repeatability and configuration effects on tapping performance

Parkinson’s disease (PD) is a progressive neurodegenerative disease that affects almost 2% of the population above the age of 65. To better quantify the effects of new medications, fast and objective methods are needed. Touchscreen-based tapping tasks are simple yet effective tools for quantifying drug effects on PD-related motor symptoms, especially bradykinesia. However, there is no consensus on the optimal task set-up. The present study compares four tapping tasks in 14 healthy participants. In alternate finger tapping (AFT), tapping occurred with the index and middle finger with 2.5 cm between targets, whereas in alternate side tapping (AST) the index finger with 20 cm between targets was used. Both configurations were tested with or without the presence of a visual cue. Moreover, for each tapping task, within- and between-day repeatability and (potential) sensitivity of the calculated parameters were assessed. Visual cueing reduced tapping speed and rhythm, and improved accuracy. This effect was most pronounced for AST. On average, AST had a lower tapping speed with impaired accuracy and improved rhythm compared to AFT. Of all parameters, the total number of taps and mean spatial error had the highest repeatability and sensitivity. The findings suggest against the use of visual cueing because it is crucial that parameters can vary freely to accurately capture medication effects. The choice for AFT or AST depends on the research question, as these tasks assess different aspects of movement. These results encourage further validation of non-cued AFT and AST in PD patients.

Effectiveness of Telerehabilitation on Motor Impairments, Non-motor Symptoms and Compliance in Patients With Parkinson's Disease: A Systematic Review

Introduction: Parkinson's disease (PD) is a chronic neurodegenerative disease involving a progressive alteration of the motor and non-motor function. PD influences the patient's daily living and reduces participation and quality of life in all phases of the disease. Early physical exercise can mitigate the effects of symptoms but access to specialist care is difficult. With current technological progress, telemedicine, and telerehabilitation is now a viable option for managing patients, although few studies have investigated the use of telerehabilitation in PD. In this systematic review, was investigated whether telerehabilitation leads to improvements in global or specific motor tasks (gait and balance, hand function) and non-motor dysfunction (motor speech disorder, dysphagia). The impact of TR on quality of life and patient satisfaction, were also assessed. The usage of telerehabilitation technologies in the management of cognitive impairment was not addressed.

Method: An electronic database search was performed using the following databases: PubMed/MEDLINE, COCHRANE Library, PEDro, and SCOPUS for data published between January 2005 and December 2019 on the effects of telerehabilitation systems in managing motor and non-motor symptoms. This systematic review was conducted in accordance with the PRISMA guideline and was registered in the PROSPERO database (CRD42020141300).

Results: A total of 15 articles involving 421 patients affected by PD were analyzed. The articles were divided into two categories based on their topic of interest or outcome. The first category consisted of the effects of telerehabilitation on gait and balance (3), dexterity of the upper limbs (3), and bradykinesia (0); the second category regarded non-motor symptoms such as speech disorders (8) and dysphagia (0). Quality of life (7) and patient satisfaction (8) following telerehabilitation programs were also analyzed, as well as feasibility and costs.

Conclusion: Telerehabilitation is feasible in people affected by PD. Our analysis of the available data highlighted that telerehabilitation systems are effective in maintaining and/or improving some clinical and non-clinical aspects of PD (balance and gait, speech and voice, quality of life, patient satisfaction).

Systematic Review Registration:https://www.crd.york.ac.uk/prospero/, identifier: CRD42020141300.

Digital Technology in Movement Disorders: Updates, Applications, and Challenges

Purpose of Review

Digital technology affords the opportunity to provide objective, frequent, and sensitive assessment of disease outside of the clinic environment. This article reviews recent literature on the application of digital technology in movement disorders, with a focus on Parkinson’s disease (PD) and Huntington’s disease.

Recent Findings

Recent research has demonstrated the ability for digital technology to discriminate between individuals with and without PD, identify those at high risk for PD, quantify specific motor features, predict clinical events in PD, inform clinical management, and generate novel insights.

Summary

Digital technology has enormous potential to transform clinical research and care in movement disorders. However, more work is needed to better validate existing digital measures, including in new populations, and to develop new more holistic digital measures that move beyond motor features.

Building a Machine-Learning Framework to Remotely Assess Parkinson's Disease Using Smartphones

OBJECTIVE

Parkinson's disease (PD) is a neurodegenerative disorder that affects multiple neurological systems. Traditional PD assessment is conducted by a physician during infrequent clinic visits. Using smartphones, remote patient monitoring has the potential to obtain objective behavioral data semi-continuously, track disease fluctuations, and avoid rater dependency.

METHODS

Smartphones collect sensor data during various active tests and passive monitoring, including balance (postural instability), dexterity (skill in performing tasks using hands), gait (the pattern of walking), tremor (involuntary muscle contraction and relaxation), and voice. Some of the features extracted from smartphone data are potentially associated with specific PD symptoms identified by physicians. To leverage large-scale cross-modality smartphone features, we propose a machine-learning framework for performing automated disease assessment. The framework consists of a two-step feature selection procedure and a generic model based on the elastic-net regularization.

RESULTS

Using this framework, we map the PD-specific architecture of behaviors using data obtained from both PD participants and healthy controls (HCs). Utilizing these atlases of features, the framework shows promises to (a) discriminate PD participants from HCs, and (b) estimate the disease severity of individuals with PD.

SIGNIFICANCE

Data analysis results from 437 behavioral features obtained from 72 subjects (37 PD and 35 HC) sampled from 17 separate days during a period of up to six months suggest that this framework is potentially useful for the analysis of remotely collected smartphone sensor data in individuals with PD.

Multi-Dimensional, Short-Timescale Quantification of Parkinson's Disease and Essential Tremor Motor Dysfunction

Introduction: Parkinson's disease (PD) is a progressive movement disorder characterized by heterogenous motor dysfunction with fluctuations in severity. Objective, short-timescale characterization of this dysfunction is necessary as therapies become increasingly adaptive.

Objectives: This study aims to characterize a novel, naturalistic, and goal-directed tablet-based task and complementary analysis protocol designed to characterize the motor features of PD.

Methods: A total of 26 patients with PD and without deep brain stimulation (DBS), 20 control subjects, and eight patients with PD and with DBS completed the task. Eight metrics, each designed to capture an aspect of motor dysfunction in PD, were calculated from 1-second, non-overlapping epochs of the raw positional and pressure data captured during task completion. These metrics were used to generate a classifier using a support vector machine (SVM) model to produce a unifying, scalar “motor error score” (MES). The data generated from these patients with PD were compared to same-day standard clinical assessments. Additionally, these data were compared to analogous data generated from a separate group of 12 patients with essential tremor (ET) to assess the task's specificity for different movement disorders. Finally, an SVM model was generated for each of the eight patients with PD and with DBS to differentiate between their motor dysfunction in the “DBS On” and “DBS Off” stimulation states.

Results: The eight metrics calculated from the raw positional and force data captured during task completion were non-redundant. MES generated by the SVM analysis protocol showed a strong correlation with MDS-UPDRS-III scores assigned by movement disorder specialists. Analysis of the relative contributions of each of the eight metrics showed a significant difference between the motor dysfunction of PD and ET. Much of this difference was attributable to the homogenous, tremor-dominant phenotype of ET motor dysfunction. Finally, in individual patients with PD with DBS, task performance and subsequent SVM classification effectively differentiated between the “DBS On” and “DBS Off” stimulation states.

Conclusion: This tablet-based task and analysis protocol correlated strongly with expert clinical assessments of PD motor dysfunction. Additionally, the task showed specificity for PD when compared to ET, another common movement disorder. This specificity was driven by the relative heterogeneity of motor dysfunction of PD compared to ET. Finally, the task was able to distinguish between the “DBS On” and “DBS Off” states within single patients with PD. This task provides temporally-precise and specific information about motor dysfunction in at least two movement disorders that could feasibly correlate to neural activity.

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

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

Parkinson's Disease Exhibits Amplified Intermuscular Coherence During Dynamic Voluntary Action

Parkinson's disease (PD) is typically diagnosed and evaluated on the basis of overt motor dysfunction, however, subtle changes in the frequency spectrum of neural drive to muscles have been reported as well. During dynamic actions, coactive muscles of healthy adults often share a common source of 6-15 Hz (alpha-band) neural drive, creating synchronous alpha-band activity in their EMG signals. Individuals with PD commonly exhibit kinetic action tremor at similar frequencies, but the potential relationship between the intermuscular alpha-band neural drive seen in healthy adults and the action tremor associated with PD is not well-understood. A close relationship is most tenable during voluntary dynamic tasks where alpha-band neural drive is strongest in healthy adults, and where neural circuits affected by PD are most engaged. In this study, we characterized the frequency spectrum of EMG synchronization (intermuscular coherence) in 16 participants with PD and 15 age-matched controls during two dynamic motor tasks: (1) rotation of a dial between the thumb and index finger, and (2) dynamic scaling of isometric precision pinch force. These tasks produce different profiles of coherence between the first dorsal interosseous and abductor pollicis brevis muscles. We sought to determine if alpha-band intermuscular coherence would be amplified in participants with PD relative to controls, if such differences would be task-specific, and if they would correlate with symptom severity. We found that relative to controls, the PD group displayed amplified, but similarly task-dependent, coherence in the alpha-band. The magnitude of coherence during the rotation task correlated with overall symptom severity as per the UPDRS rating scale. Finally, we explored the potential for our coherence measures, with no additional information, to discriminate individuals with PD from controls. The area under the Receiver Operating Characteristic curve (AUC) indicated a clear separation between groups (AUC = 0.96), even though participants with PD were on their typical medication and displayed only mild-moderate symptoms. We conclude that a task-dependent, intermuscular neural drive within the alpha-band is amplified in PD. Its quantification via intermuscular coherence analysis may provide a useful tool for detecting the presence of PD, or assessing its progression.

A machine learning algorithm successfully screens for Parkinson's in web users

Objective

To develop, apply, and evaluate, a novel web‐based classifier for screening for Parkinson disease among a large cohort of search engine users.

Methods

A supervised machine learning classifier learned to distinguish web users with self‐reported Parkinson's disease from controls based on their interactions with a search engine (Bing, Microsoft). It was then applied to groups of web users with low or high risk for actual Parkinson's disease. Textual content of web queries was used to sort surfers into the different risk groups, but not for classifying users as negative or positive for Parkinson's disease. Disease detection was unsolicited. Researchers did not have access to any identifying data on users.

Results

Applying the classifier (with an estimated positive predictive value of 25%) resulted in 17,843/1,490,987 (1.2%) web users over the age of 40 years screened positive for Parkinson's disease. This percentile was higher in at‐risk groups (Fisher exact P < 0.00001), including users who searched for information regarding the disease (518/804, 64.4%), and users with non‐motor Parkinson's symptom or with an affected relative (57/1064, 5.3%). Longitudinal follow‐up revealed that in all studied groups individuals classified as having the disease showed a higher mean rate of progression in disease‐related features (t‐test P < 0.05).

Interpretation

An automatic classifier, based on mouse and keyboard interactions with a search engine, is able to reliably trace individuals at high risk for actual Parkinson's disease as well as to demonstrate more rapid progression of disease‐related signs in those who screened positive. This ability raises novel ethical issues.

Touchscreen typing pattern analysis for remote detection of the depressive tendency

Depressive disorder (DD) is a mental illness affecting more than 300 million people worldwide, whereas social stigma and subtle, variant symptoms impede diagnosis. Psychomotor retardation is a common component of DD with a negative impact on motor function, usually reflected on patients’ routine activities, including, nowadays, their interaction with mobile devices. Therefore, such interactions constitute an enticing source of information towards unsupervised screening for DD symptoms in daily life. In this vein, this paper proposes a machine learning-based method for discriminating between subjects with depressive tendency and healthy controls, as denoted by self-reported Patient Health Questionnaire-9 (PHQ-9) compound scores, based on typing patterns captured in-the-wild. The latter consisted of keystroke timing sequences and typing metadata, passively collected during natural typing on touchscreen smartphones by 11/14 subjects with/without depressive tendency. Statistical features were extracted and tested in univariate and multivariate classification pipelines to reach a decision on subjects’ status. The best-performing pipeline achieved an AUC = 0.89 (0.72–1.00; 95% Confidence Interval) and 0.82/0.86 sensitivity/specificity, with the outputted probabilities significantly correlating (>0.60) with the respective PHQ-9 scores. This work adds to the findings of previous research associating typing patterns with psycho-motor impairment and contributes to the development of an unobtrusive, high-frequency monitoring of depressive tendency in everyday living.

Remote Monitoring of Treatment Response in Parkinson's Disease: The Habit of Typing on a Computer

OBJECTIVE

The recent advances in technology are opening a new opportunity to remotely evaluate motor features in people with Parkinson's disease (PD). We hypothesized that typing on an electronic device, a habitual behavior facilitated by the nigrostriatal dopaminergic pathway, could allow for objectively and nonobtrusively monitoring parkinsonian features and response to medication in an at-home setting.

METHODS

We enrolled 31 participants recently diagnosed with PD who were due to start dopaminergic treatment and 30 age-matched controls. We remotely monitored their typing pattern during a 6-month (24 weeks) follow-up period before and while dopaminergic medications were being titrated. The typing data were used to develop a novel algorithm based on recursive neural networks and detect participants' responses to medication. The latter were defined by the Unified Parkinson's Disease Rating Scale-III (UPDRS-III) minimal clinically important difference. Furthermore, we tested the accuracy of the algorithm to predict the final response to medication as early as 21 weeks prior to the final 6-month clinical outcome.

RESULTS

The score on the novel algorithm based on recursive neural networks had an overall moderate kappa agreement and fair area under the receiver operating characteristic (ROC) curve with the time-coincident UPDRS-III minimal clinically important difference. The participants classified as responders at the final visit (based on the UPDRS-III minimal clinically important difference) had higher scores on the novel algorithm based on recursive neural networks when compared with the participants with stable UPDRS-III, from the third week of the study onward.

CONCLUSIONS

This preliminary study suggests that remotely gathered unsupervised typing data allows for the accurate detection and prediction of drug response in PD. © 2019 International Parkinson and Movement Disorder Society.

Reduced habit-driven errors in Parkinson's Disease

Parkinson’s Disease can be understood as a disorder of motor habits. A prediction of this theory is that early stage Parkinson’s patients will display fewer errors caused by interference from previously over-learned behaviours. We test this prediction in the domain of skilled typing, where actions are easy to record and errors easy to identify. We describe a method for categorizing errors as simple motor errors or habit-driven errors. We test Spanish and English participants with and without Parkinson’s, and show that indeed patients make fewer habit errors than healthy controls, and, further, that classification of error type increases the accuracy of discriminating between patients and healthy controls. As well as being a validation of a theory-led prediction, these results offer promise for automated, enhanced and early diagnosis of Parkinson’s Disease.

Effect of Parkinsonism on Proximal Unstructured Movement Captured by Inertial Sensors

In this study, we endeavour to measure characteristic movements of patients with Parkinson's disease (PD). Our eventual aim is to obtain the severity of these exhibited movements entirely based on measurements conducted in un-clinical environments. Indeed, we investigate the feasibility of capturing such un-structured movements using wearable sensors. In particular, as Bradykinesia and axial Bradykinesia are vital characteristics yet challenging to measure, we design a test system of Inertial Measurement (IM) based wearable sensors in order to capture the affected movements of the back. The study evaluated the characteristics of PD patients during the unstructured activities. Our analysis captured back flexibility based on frequency information of the sensors attached to the human back. Satisfactory classification in each test confirms that this testing system can identify as well as evaluate PD patients using a minimal number of sensors during these unstructured movements. Our objective is to enhance the uptake and promote the use of wearable sensors in longer term monitoring scenarios relevant to non-clinical environments. Thus, we envisage clinicians monitoring the progress due to the treatment of patients residing in their homes assisted by sensors with enhanced wearability.

Evaluation of smartphone-based testing to generate exploratory outcome measures in a phase 1 Parkinson's disease clinical trial

BACKGROUND

Ubiquitous digital technologies such as smartphone sensors promise to fundamentally change biomedical research and treatment monitoring in neurological diseases such as PD, creating a new domain of digital biomarkers.

OBJECTIVES

The present study assessed the feasibility, reliability, and validity of smartphone-based digital biomarkers of PD in a clinical trial setting.

METHODS

During a 6-month, phase 1b clinical trial with 44 Parkinson participants, and an independent, 45-day study in 35 age-matched healthy controls, participants completed six daily motor active tests (sustained phonation, rest tremor, postural tremor, finger-tapping, balance, and gait), then carried the smartphone during the day (passive monitoring), enabling assessment of, for example, time spent walking and sit-to-stand transitions by gyroscopic and accelerometer data.

RESULTS

Adherence was acceptable: Patients completed active testing on average 3.5 of 7 times/week. Sensor-based features showed moderate-to-excellent test-retest reliability (average intraclass correlation coefficient = 0.84). All active and passive features significantly differentiated PD from controls with P < 0.005. All active test features except sustained phonation were significantly related to corresponding International Parkinson and Movement Disorder Society-Sponsored UPRDS clinical severity ratings. On passive monitoring, time spent walking had a significant (P = 0.005) relationship with average postural instability and gait disturbance scores. Of note, for all smartphone active and passive features except postural tremor, the monitoring procedure detected abnormalities even in those Parkinson participants scored as having no signs in the corresponding International Parkinson and Movement Disorder Society-Sponsored UPRDS items at the site visit.

CONCLUSIONS

These findings demonstrate the feasibility of smartphone-based digital biomarkers and indicate that smartphone-sensor technologies provide reliable, valid, clinically meaningful, and highly sensitive phenotypic data in Parkinson's disease. © 2018 The Authors. Movement Disorders published by Wiley Periodicals, Inc. on behalf of International Parkinson and Movement Disorder Society.

Touchscreen typing-pattern analysis for detecting fine motor skills decline in early-stage Parkinson's disease

Parkinson’s disease (PD) is a degenerative movement disorder causing progressive disability that severely affects patients’ quality of life. While early treatment can produce significant benefits for patients, the mildness of many early signs combined with the lack of accessible high-frequency monitoring tools may delay clinical diagnosis. To meet this need, user interaction data from consumer technologies have recently been exploited towards unsupervised screening for PD symptoms in daily life. Similarly, this work proposes a method for detecting fine motor skills decline in early PD patients via analysis of patterns emerging from finger interaction with touchscreen smartphones during natural typing. Our approach relies on low-/higher-order statistical features of keystrokes timing and pressure variables, computed from short typing sessions. Features are fed into a two-stage multi-model classification pipeline that reaches a decision on the subject’s status (PD patient/control) by gradually fusing prediction probabilities obtained for individual typing sessions and keystroke variables. This method achieved an AUC = 0.92 and 0.82/0.81 sensitivity/specificity (matched groups of 18 early PD patients/15 controls) with discriminant features plausibly correlating with clinical scores of relevant PD motor symptoms. These findings suggest an improvement over similar approaches, thereby constituting a further step towards unobtrusive early PD detection from routine activities.

Detecting Motor Impairment in Early Parkinson's Disease via Natural Typing Interaction With Keyboards: Validation of the neuroQWERTY Approach in an Uncontrolled At-Home Setting

Background

Parkinson’s disease (PD) is the second most prevalent neurodegenerative disease and one of the most common forms of movement disorder. Although there is no known cure for PD, existing therapies can provide effective symptomatic relief. However, optimal titration is crucial to avoid adverse effects. Today, decision making for PD management is challenging because it relies on subjective clinical evaluations that require a visit to the clinic. This challenge has motivated recent research initiatives to develop tools that can be used by nonspecialists to assess psychomotor impairment. Among these emerging solutions, we recently reported the neuroQWERTY index, a new digital marker able to detect motor impairment in an early PD cohort through the analysis of the key press and release timing data collected during a controlled in-clinic typing task.

Objective

The aim of this study was to extend the in-clinic implementation to an at-home implementation by validating the applicability of the neuroQWERTY approach in an uncontrolled at-home setting, using the typing data from subjects’ natural interaction with their laptop to enable remote and unobtrusive assessment of PD signs.

Methods

We implemented the data-collection platform and software to enable access and storage of the typing data generated by users while using their computer at home. We recruited a total of 60 participants; of these participants 52 (25 people with Parkinson’s and 27 healthy controls) provided enough data to complete the analysis. Finally, to evaluate whether our in-clinic-built algorithm could be used in an uncontrolled at-home setting, we compared its performance on the data collected during the controlled typing task in the clinic and the results of our method using the data passively collected at home.

Results

Despite the randomness and sparsity introduced by the uncontrolled setting, our algorithm performed nearly as well in the at-home data (area under the receiver operating characteristic curve [AUC] of 0.76 and sensitivity/specificity of 0.73/0.69) as it did when used to evaluate the in-clinic data (AUC 0.83 and sensitivity/specificity of 0.77/0.72). Moreover, the keystroke metrics presented a strong correlation between the 2 typing settings, which suggests a minimal influence of the in-clinic typing task in users’ normal typing.

Conclusions

The finding that an algorithm trained on data from an in-clinic setting has comparable performance with that tested on data collected through naturalistic at-home computer use reinforces the hypothesis that subtle differences in motor function can be detected from typing behavior. This work represents another step toward an objective, user-convenient, and quasi-continuous monitoring tool for PD.