Assessment of Motor Impairments in Early Untreated Parkinson's Disease Patients: The Wearable Electronics Impact

Abnormal arm swing movements in Parkinson's disease: onset, progression and response to L-Dopa

BACKGROUND

Reduced arm swing movements during gait are an early motor manifestation of Parkinson's disease (PD). The clinical evolution, response to L-Dopa and pathophysiological underpinning of abnormal arm swing movements in PD remain largely unclear. By using a network of wearable sensors, this study objectively assesses arm swing movements during gait in PD patients across different disease stages and therapeutic conditions.

METHODS

Twenty healthy subjects (HS) and 40 PD patients, including 20 early-stage and 20 mid-advanced subjects, underwent a 6-m Timed Up and Go test while monitored through a network of wearable inertial sensors. Arm swing movements were objectively evaluated in both hemibodies and different upper limb joints (shoulder and elbow), using specific time-domain (range of motion and velocity) and frequency-domain measures (harmonics and total harmonic distortion). To assess the effects of L-Dopa, patients under chronic dopaminergic therapy were randomly examined when OFF and ON therapy. Finally, clinical-behavioral correlations were investigated, primarily focusing on the relationship between arm swing movements and cardinal L-Dopa-responsive motor signs, including bradykinesia and rigidity.

RESULTS

Compared to HS, the whole group of PD patients showed reduced range of motion and velocity, alongside increased asymmetry of arm swing movements during gait. Additionally, a distinct increase in total harmonic distortion was found in patients. The kinematic changes were prominent in the early stage of the disease and progressively worsened owing to the involvement of the less affected hemibody. The time- and frequency-domain abnormalities were comparable in the two joints (i.e., shoulder and elbow). In the subgroup of patients under chronic dopaminergic treatment, L-Dopa restored patterns of arm swing movements. Finally, the kinematic alterations in arm swing movements during gait correlated with the clinical severity of bradykinesia and rigidity.

CONCLUSIONS

Arm swing movements during gait in PD are characterized by narrow, slow, and irregular patterns. As the disease progresses, arm swing movements deteriorate also in the less affected hemibody, without any joint specificity. The positive response to L-Dopa along with the significant correlation between kinematics and bradykinesia/rigidity scores points to the involvement of dopaminergic pathways in the pathophysiology of abnormal arm swing movements in PD.

The Use of Artificial Intelligence and Wearable Inertial Measurement Units in Medicine: Systematic Review

BACKGROUND

Artificial intelligence (AI) has already revolutionized the analysis of image, text, and tabular data, bringing significant advances across many medical sectors. Now, by combining with wearable inertial measurement units (IMUs), AI could transform health care again by opening new opportunities in patient care and medical research.

OBJECTIVE

This systematic review aims to evaluate the integration of AI models with wearable IMUs in health care, identifying current applications, challenges, and future opportunities. The focus will be on the types of models used, the characteristics of the datasets, and the potential for expanding and enhancing the use of this technology to improve patient care and advance medical research.

METHODS

This study examines this synergy of AI models and IMU data by using a systematic methodology, following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, to explore 3 core questions: (1) Which medical fields are most actively researching AI and IMU data? (2) Which models are being used in the analysis of IMU data within these medical fields? (3) What are the characteristics of the datasets used for in this fields?

RESULTS

The median dataset size is of 50 participants, which poses significant limitations for AI models given their dependency on large datasets for effective training and generalization. Furthermore, our analysis reveals the current dominance of machine learning models in 76% on the surveyed studies, suggesting a preference for traditional models like linear regression, support vector machine, and random forest, but also indicating significant growth potential for deep learning models in this area. Impressively, 93% of the studies used supervised learning, revealing an underuse of unsupervised learning, and indicating an important area for future exploration on discovering hidden patterns and insights without predefined labels or outcomes. In addition, there was a preference for conducting studies in clinical settings (77%), rather than in real-life scenarios, a choice that, along with the underapplication of the full potential of wearable IMUs, is recognized as a limitation in terms of practical applicability. Furthermore, the focus of 65% of the studies on neurological issues suggests an opportunity to broaden research scope to other clinical areas such as musculoskeletal applications, where AI could have significant impacts.

CONCLUSIONS

In conclusion, the review calls for a collaborative effort to address the highlighted challenges, including improvements in data collection, increasing dataset sizes, a move that inherently pushes the field toward the adoption of more complex deep learning models, and the expansion of the application of AI models on IMU data methodologies across various medical fields. This approach aims to enhance the reliability, generalizability, and clinical applicability of research findings, ultimately improving patient outcomes and advancing medical research.

Machine learning and wearable sensors for automated Parkinson's disease diagnosis aid: a systematic review

BACKGROUND

The diagnosis of Parkinson's disease is currently based on clinical evaluation. Despite clinical hallmarks, unfortunately, the error rate is still significant. Low in-vivo diagnostic accuracy of clinical evaluation mainly relies on the lack of quantitative biomarkers for an objective motor performance assessment. Non-invasive technologies, such as wearable sensors, coupled with machine learning algorithms, assess quantitatively and objectively the motor performances, with possible benefits either for in-clinic and at-home settings. We conducted a systematic review of the literature on machine learning algorithms embedded in smart devices in Parkinson's disease diagnosis.

METHODS

Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we searched PubMed for articles published between December, 2007 and July, 2023, using a search string combining "Parkinson's disease" AND ("healthy" or "control") AND "diagnosis", within the Groups and Outcome domains. Additional search terms included "Algorithm", "Technology" and "Performance".

RESULTS

From 89 identified studies, 47 met the inclusion criteria based on the search string and four additional studies were included based on the Authors' expertise. Gait emerged as the most common parameter analysed by machine learning models, with Support Vector Machines as the prevalent algorithm. The results suggest promising accuracy with complex algorithms like Random Forest, Support Vector Machines, and K-Nearest Neighbours.

DISCUSSION

Despite the promise shown by machine learning algorithms, real-world applications may still face limitations. This review suggests that integrating machine learning with wearable sensors has the potential to improve Parkinson's disease diagnosis. These tools could provide clinicians with objective data, potentially aiding in earlier detection.

Short Step Length Estimation for Parkinson's Disease Patients by Using Fusion Data From Camera-IMU in Smart Glasses

Shortened step length is a prominent motor abnormality in Parkinson's disease (PD) patients. Current methods for estimating short step length have the limitation of relying on laboratory scenarios, wearing multiple sensors, and inaccurate estimation results from a single sensor. In this paper, we proposed a novel method for estimating short step length for PD patients by fusing data from camera and inertial measurement units in smart glasses. A simultaneous localization and mapping technique and acceleration thresholding-based step detection technique were combined to realize the step length estimation. Two sets of experiments were conducted to demonstrate the performance of our method. In the first set of experiments with 12 healthy subjects, the proposed method demonstrated an average error of 8.44% across all experiments including six fixed step lengths below 30 cm. The second set of straightly walking experiments were implemented with 12 PD patients, the proposed method exhibited an average error of 4.27% compared to a standard gait evaluation technique in total walking distance. Notably, among the results of step lengths below 40 cm, our method agreed with the standard technique (R 2=0.8659). This study offers a promising approach for estimating short step length for PD patients during smart glasses-based gait training.

3D Kinematics Quantifies Gait Response to Levodopa earlier and to a more Comprehensive Extent than the MDS-Unified Parkinson's Disease Rating Scale in Patients with Motor Complications

BACKGROUND

Quantitative 3D movement analysis using inertial measurement units (IMUs) allows for a more detailed characterization of motor patterns than clinical assessment alone. It is essential to discriminate between gait features that are responsive or unresponsive to current therapies to better understand the underlying pathophysiological basis and identify potential therapeutic strategies.

OBJECTIVES

This study aims to characterize the responsiveness and temporal evolution of different gait subcomponents in Parkinson's disease (PD) patients in their OFF and various ON states following levodopa administration, utilizing both wearable sensors and the gold-standard MDS-UPDRS motor part III.

METHODS

Seventeen PD patients were assessed while wearing a full-body set of 15 IMUs in their OFF state and at 20-minute intervals following the administration of a supra-threshold levodopa dose. Gait was reconstructed using a biomechanical model of the human body to quantify how each feature was modulated. Comparisons with non-PD control subjects were conducted in parallel.

RESULTS

Significant motor changes were observed in both the upper and lower limbs according to the MDS-UPDRS III, 40 minutes after levodopa intake. IMU-assisted 3D kinematics detected significant motor alterations as early as 20 minutes after levodopa administration, particularly in upper limbs metrics. Although all "pace-domain" gait features showed significant improvement in the Best-ON state, most rhythmicity, asymmetry, and variability features did not.

CONCLUSION

IMUs are capable of detecting motor alterations earlier and in a more comprehensive manner than the MDS-UPDRS III. The upper limbs respond more rapidly to levodopa, possibly reflecting distinct thresholds to levodopa across striatal regions.

Freezing of gait in Parkinson's disease: Classification using computational intelligence

Parkinson's disease (PD) is a neurodegenerative disease represented by the progressive loss of dopamine producing neurons, with motor and non-motor symptoms that may be hard to distinguish from other disorders. Affecting millions of people across the world, its symptoms include bradykinesia, tremors, depression, rigidity, postural instability, cognitive decline, and falls. Furthermore, changes in gait can be used as a primary diagnosis factor. A dataset is described that records data on healthy individuals and on PD patients, including those who experience freezing of gait, in both the ON and OFF-medication states. The dataset is comprised of data for four separate tasks: voluntary stop, timed up and go, simple motor task, and dual motor and cognitive task. Seven different classifiers are applied to two problems relating to this data. The first problem is to distinguish PD patients from healthy individuals, both overall and per task. The second problem is to determine the effectiveness of medication. A thorough analysis on the classifiers and their results is performed. Overall, multilayer perceptron and decision tree provide the most consistent results.

Wearable multisource quantitative gait analysis of Parkinson's diseases

As the motor symptoms of Parkinson's disease (PD) are complex and influenced by many factors, it is challenging to quantify gait abnormalities adequately using a single type of signal. Therefore, a wearable multisource gait monitoring system is developed to perform a quantitative analysis of gait abnormalities for improving the effectiveness of the clinical diagnosis. To detect multisource gait data for an accurate evaluation of gait abnormalities, force sensitive sensors, piezoelectric sensors, and inertial measurement units are integrated into the devised device. The modulation circuits and wireless framework are designed to simultaneously collect plantar pressure, dynamic deformation, and postural angle of the foot and then wirelessly transmit these collected data. With the designed system, multisource gait data from PD patients and healthy controls are collected. Multisource features for quantifying gait abnormalities are extracted and evaluated by a significance test of difference and correlation analysis. The results show that the features extracted from every single type of data are able to quantify the health status of the subjects (p < 0.001, ρ > 0.50). More importantly, the validity of multisource gait data is verified. The results demonstrate that the gait feature fusing multisource data achieves a maximum correlation coefficient of 0.831, a maximum Area Under Curve of 0.9206, and a maximum feature-based classification accuracy of 88.3%. The system proposed in this study can be applied to the gait analysis and objective evaluation of PD.

Deep-learning detection of mild cognitive impairment from sleep electroencephalography for patients with Parkinson's disease

Parkinson's disease which is the second most prevalent neurodegenerative disorder in the United States is a serious and complex disease that may progress to mild cognitive impairment and dementia. The early detection of the mild cognitive impairment and the identification of its biomarkers is crucial to support neurologists in monitoring the progression of the disease and allow an early initiation of effective therapeutic treatments that will improve the quality of life for the patients. In this paper, we propose the first deep-learning based approaches to detect mild cognitive impairment in the sleep Electroencephalography for patients with Parkinson's disease and further identify the discriminative features of the disease. The proposed frameworks start by segmenting the sleep Electroencephalography time series into three sleep stages (i.e., two non-rapid eye movement sleep-stages and one rapid eye movement sleep stage), further transforming the segmented signals in the time-frequency domain using the continuous wavelet transform and the variational mode decomposition and finally applying novel convolutional neural networks on the time-frequency representations. The gradient-weighted class activation mapping was also used to visualize the features based on which the proposed deep-learning approaches reached an accurate prediction of mild cognitive impairment in Parkinson's disease. The proposed variational mode decomposition-based model offered a superior accuracy, sensitivity, specificity, area under curve, and quadratic weighted Kappa score, all above 99% as compared with the continuous wavelet transform-based model (that achieved a performance that is almost above 92%) in differentiating mild cognitive impairment from normal cognition in sleep Electroencephalography for patients with Parkinson's disease. In addition, the features attributed to the mild cognitive impairment in Parkinson's disease were demonstrated by changes in the middle and high frequency variational mode decomposition components across the three sleep-stages. The use of the proposed model on the time-frequency representation of the sleep Electroencephalography signals will provide a promising and precise computer-aided diagnostic tool for detecting mild cognitive impairment and hence, monitoring the progression of Parkinson's disease.

Clinical characteristics and reaction to dopaminergic treatment of drug-naïve patients with Parkinson's disease in central China: A cross sectional study

Background

The symptoms of early Parkinson's disease (PD) are complex and hidden. The aim of this study is to explore and summarize the characteristics of the symptoms of drug naïve patients with PD.

Objectives

and Methods Drug-naïve patients with PD and age-matched healthy controls were recruited from the outpatient clinic of Wuhan Union Hospital. The motor and non-motor symptoms were evaluated for further analysis using Unified Parkinson's Disease Rating Scale (UPDRS) I, II, and III; Sniffin' Sticks Screening 12 test; Mini-Mental State Exam (MMSE); Montreal Cognitive Assessment (MoCA); Hamilton Anxiety Scale (HAMA); and Hamilton Depression Scale (HAMD) scores. The acute levodopa challenge test (ALCT) was adopted to assess the reaction to dopaminergic treatment.

Results

We recruited 80 drug-naïve patients with PD and 40 age-matched healthy controls (HCs). Approximately 53.7% of the patients were females. The mean onset age was 59.96 ± 10.40 years. The mean UPDRS I, II, and III were 2.01 ± 1.90, 6.18 ± 3.68, and 26.13 ± 12.09, respectively. Compared with HCs, PD patients had lower scores in MMSE and MoCA; and higher scores in HAMA and HAMD (p < 0.05). In ALCT, 54 patients showed good responses to levodopa while 26 patients did not. The mean improvement rate of UPDRS III was 34.09% at 120 min.

Conclusion

The motor symptoms of patients with early PD were mild but virous. They also suffered from different non-motor symptoms. In ALCT, about two thirds of patients (54/80) with early PD showed good response to levodopa. Among four aspects of motor symptoms, bradykinesia reacted best to ALCT, while axial symptoms were the worst.

Robust and language-independent acoustic features in Parkinson's disease

Introduction

The analysis of vocal samples from patients with Parkinson's disease (PDP) can be relevant in supporting early diagnosis and disease monitoring. Intriguingly, speech analysis embeds several complexities influenced by speaker characteristics (e.g., gender and language) and recording conditions (e.g., professional microphones or smartphones, supervised, or non-supervised data collection). Moreover, the set of vocal tasks performed, such as sustained phonation, reading text, or monologue, strongly affects the speech dimension investigated, the feature extracted, and, as a consequence, the performance of the overall algorithm.

Methods

We employed six datasets, including a cohort of 176 Healthy Control (HC) participants and 178 PDP from different nationalities (i.e., Italian, Spanish, Czech), recorded in variable scenarios through various devices (i.e., professional microphones and smartphones), and performing several speech exercises (i.e., vowel phonation, sentence repetition). Aiming to identify the effectiveness of different vocal tasks and the trustworthiness of features independent of external co-factors such as language, gender, and data collection modality, we performed several intra- and inter-corpora statistical analyses. In addition, we compared the performance of different feature selection and classification models to evaluate the most robust and performing pipeline.

Results

According to our results, the combined use of sustained phonation and sentence repetition should be preferred over a single exercise. As for the set of features, the Mel Frequency Cepstral Coefficients demonstrated to be among the most effective parameters in discriminating between HC and PDP, also in the presence of heterogeneous languages and acquisition techniques.

Conclusion

Even though preliminary, the results of this work can be exploited to define a speech protocol that can effectively capture vocal alterations while minimizing the effort required to the patient. Moreover, the statistical analysis identified a set of features minimally dependent on gender, language, and recording modalities. This discloses the feasibility of extensive cross-corpora tests to develop robust and reliable tools for disease monitoring and staging and PDP follow-up.

Antiparkinsonian medication masks motor signal progression in de novo patients

Patients not yet receiving medication provide insight to drug-naïve early physiology of Parkinson's Disease (PD). Wearable sensors can measure changes in motor features before and after introduction of antiparkinsonian medication. We aimed to identify features of upper limb bradykinesia, postural stability, and gait that measurably progress in de novo PD patients prior to the start of medication, and determine whether these features remain sensitive to progression in the period after commencement of antiparkinsonian medication. Upper limb motion was measured using an inertial sensor worn on a finger, while postural stability and gait were recorded using an array of six wearable sensors. Patients were tested over nine visits at three monthly intervals. The timepoint of start of medication was noted. Three upper limb bradykinetic features (finger tapping speed, pronation supination speed, and pronation supination amplitude) and three gait features (gait speed, arm range of motion, duration of stance phase) were found to progress in unmedicated early-stage PD patients. In all features, progression was masked after the start of medication. Commencing antiparkinsonian medication is known to lead to masking of progression signals in clinical measures in de novo PD patients. In this study, we show that this effect is also observed with digital measures of bradykinetic and gait motor features.

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson's Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

Parkinson's Disease (PD) is one of the most common non-curable neurodegenerative diseases. Diagnosis is achieved clinically on the basis of different symptoms with considerable delays from the onset of neurodegenerative processes in the central nervous system. In this study, we investigated early and full-blown PD patients based on the analysis of their voice characteristics with the aid of the most commonly employed machine learning (ML) techniques. A custom dataset was made with hi-fi quality recordings of vocal tasks gathered from Italian healthy control subjects and PD patients, divided into early diagnosed, off-medication patients on the one hand, and mid-advanced patients treated with L-Dopa on the other. Following the current state-of-the-art, several ML pipelines were compared usingdifferent feature selection and classification algorithms, and deep learning was also explored with a custom CNN architecture. Results show how feature-based ML and deep learning achieve comparable results in terms of classification, with KNN, SVM and naïve Bayes classifiers performing similarly, with a slight edge for KNN. Much more evident is the predominance of CFS as the best feature selector. The selected features act as relevant vocal biomarkers capable of differentiating healthy subjects, early untreated PD patients and mid-advanced L-Dopa treated patients.

Evaluation of Arm Swing Features and Asymmetry during Gait in Parkinson's Disease Using the Azure Kinect Sensor

Arm swinging is a typical feature of human walking: Continuous and rhythmic movement of the upper limbs is important to ensure postural stability and walking efficiency. However, several factors can interfere with arm swings, making walking more risky and unstable: These include aging, neurological diseases, hemiplegia, and other comorbidities that affect motor control and coordination. Objective assessment of arm swings during walking could play a role in preventing adverse consequences, allowing appropriate treatments and rehabilitation protocols to be activated for recovery and improvement. This paper presents a system for gait analysis based on Microsoft Azure Kinect DK sensor and its body-tracking algorithm: It allows noninvasive full-body tracking, thus enabling simultaneous analysis of different aspects of walking, including arm swing characteristics. Sixteen subjects with Parkinson's disease and 13 healthy controls were recruited with the aim of evaluating differences in arm swing features and correlating them with traditional gait parameters. Preliminary results show significant differences between the two groups and a strong correlation between the parameters. The study thus highlights the ability of the proposed system to quantify arm swing features, thus offering a simple tool to provide a more comprehensive gait assessment.

fNIRS-based brain state transition features to signify functional degeneration after Parkinson's disease

OBJECTIVE

Parkinson's disease (PD) is a common neurodegenerative brain disorder, and early diagnosis is of vital importance for treatment. Existing methods are mainly focused on behavior examination, while the functional neurodegeneration after PD has not been well explored. This paper aims to investigate the brain functional variation of PD patients in comparison with healthy controls.

APPROACH

In this work, we propose brain hemodynamic states and state transition features to signify functional degeneration after PD. Firstly, a functional near-infrared spectroscopy (fNIRS)-based experimental paradigm was designed to capture brain activation during dual-task walking from PD patients and healthy controls. Then, three brain states, named expansion, contraction, and intermediate states, were defined with respect to the oxyhemoglobin and deoxyhemoglobin responses. After that, two features were designed from a constructed transition factor and concurrent variations of oxy- and deoxy-hemoglobin over time, to quantify the transitions of brain states. Further, a support vector machine classifier was trained with the proposed features to distinguish PD patients and healthy controls.

RESULTS

Experimental results showed that our method with the proposed brain state transition features achieved classification accuracy of 0:8200 and F score of 0:9091, and outperformed existing fNIRS-based methods. Compared with healthy controls, PD patients had significantly smaller transition acceleration and transition angle.

SIGNIFICANCE

The proposed brain state transition features well signify functional degeneration of PD patients and may serve as promising functional biomarkers for PD diagnosis.

Performance Index for in Home Assessment of Motion Abilities in Ataxia Telangiectasia: A Pilot Study

Background. It has been shown in the very recent literature that human walking generates rhythmic motor patterns with hidden time harmonic structures that are represented (at the subject’s comfortable speed) by the occurrence of the golden ratio as the the ratio of the durations of specific walking gait subphases. Such harmonic proportions may be affected—partially or even totally destroyed—by several neurological and/or systemic disorders, thus drastically reducing the smooth, graceful, and melodic flow of movements and altering gait self-similarities. Aim. In this paper we aim at, preliminarily, showing the reliability of a technologically assisted methodology—performed with an easy to use wearable motion capture system—for the evaluation of motion abilities in Ataxia-Telangiectasia (AT), a rare infantile onset neurodegenerative disorder, whose typical neurological manifestations include progressive gait unbalance and the disturbance of motor coordination. Methods. Such an experimental methodology relies, for the first time, on the most recent accurate and objective outcome measures of gait recursivity and harmonicity and symmetry and double support subphase consistency, applied to three AT patients with different ranges of AT severity. Results. The quantification of the level of the distortions of harmonic temporal proportions is shown to include the qualitative evaluations of the three AT patients provided by clinicians. Conclusions. Easy to use wearable motion capture systems might be used to evaluate AT motion abilities through recursivity and harmonicity and symmetry (quantitative) outcome measures.

The impact of wearable electronics in assessing the effectiveness of levodopa treatment in Parkinsons disease

OBJECTIVE

In order to evaluate Parkinson disease patients response to therapeutic interventions, sources of information are mainly patient reports and clinicians assessment of motor functions. However, these sources can suffer from patients subjectivity and from inter/intra raters score variability. Our work aimed at determining the impact of wearable electronics and data analysis in objectifying the effectiveness of levodopa treatment.

METHODS

Seven motor tasks performed by thirty-six patients were measured by wearable electronics and related data were analyzed. This was at the time of therapy initiation (T0), and repeated after six (T1) and 12 months (T2). Wearable electronics consisted of inertial measurement units each equipped with 3-axis accelerometer and 3-axis gyroscope, while data analysis of ANOVA and Pearson correlation algorithms, in addition to a support vector machine (SVM) classification.

RESULTS

According to our findings, levodopa-based therapy alters the patients conditions in general, ameliorating something (e.g. bradykinesia), leaving unchanged others (e.g. tremor), but with poor correlation to the levodopa dose.

CONCLUSION

A technology-based approach can objectively assess levodopa-based therapy effectiveness.

SIGNIFICANCE

Novel devices can improve the accuracy of the assessment of motor function, by integrating the clinical evaluation and patient reports.

Resting-state electroencephalography based deep-learning for the detection of Parkinson's disease

Parkinson's disease (PD) is one of the most serious and challenging neurodegenerative disorders to diagnose. Clinical diagnosis on observing motor symptoms is the gold standard, yet by this point nerve cells are degenerated resulting in a lower efficacy of therapeutic treatments. In this study, we introduce a deep-learning approach based on a recently-proposed 20-Layer Convolutional Neural Network (CNN) applied on the visual realization of the Wavelet domain of a resting-state EEG. The proposed approach was able to efficiently and accurately detect PD as well as distinguish subjects with PD on medications from subjects who are off medication. The gradient-weighted class activation mapping (Grad-CAM) was used to visualize the features based on which the approach provided the predictions. A significantly high accuracy, sensitivity, specificity, AUC, and Weighted Kappa Score up to 99.9% were achieved and the visualization of the regions in the Wavelet images that contributed to the deep-learning approach decisions was provided. The proposed framework can then serve as an effective computer-aided diagnostic tool that will support physicians and scientists in further understanding the nature of PD and providing an objective and confident opinion regarding the clinical diagnosis of the disease.

Internet of Things Technologies and Machine Learning Methods for Parkinson's Disease Diagnosis, Monitoring and Management: A Systematic Review

Parkinson's disease is a chronic neurodegenerative disease that affects a large portion of the population, especially the elderly. It manifests with motor, cognitive and other types of symptoms, decreasing significantly the patients' quality of life. The recent advances in the Internet of Things and Artificial Intelligence fields, including the subdomains of machine learning and deep learning, can support Parkinson's disease patients, their caregivers and clinicians at every stage of the disease, maximizing the treatment effectiveness and minimizing the respective healthcare costs at the same time. In this review, the considered studies propose machine learning models, trained on data acquired via smart devices, wearable or non-wearable sensors and other Internet of Things technologies, to provide predictions or estimations regarding Parkinson's disease aspects. Seven hundred and seventy studies have been retrieved from three dominant academic literature databases. Finally, one hundred and twelve of them have been selected in a systematic way and have been considered in the state-of-the-art systematic review presented in this paper. These studies propose various methods, applied on various sensory data to address different Parkinson's disease-related problems. The most widely deployed sensors, the most commonly addressed problems and the best performing algorithms are highlighted. Finally, some challenges are summarized along with some future considerations and opportunities that arise.

Complex motion series performance differs between previously untreated patients with Parkinson's disease and controls

Motor behaviour in patients with Parkinson's disease is determined with instrumental tests and rating procedures. Results mirror impairment of an individual patient. Objectives were to determine the associations between two kinds of motion series and rating scores in previously untreated 64 patients and to compare outcomes to controls. The line tracing task asks to follow a given path. It measures the needed interval, the number and duration of contacts to the path. The aiming procedure asks to hit contact plates with a pencil and determines the needed time period and the number of accurate, respectively, missed key strokes. Both tests differed between patients and controls. The line tracing task was more sensitive. The line tracing task asks for a complex motion series performance with more cognitive load. The aiming task prompts for a conduction of preponderant simple, repetitive movement series. Only initially, a complex process of aiming is necessary. Performance of complex motion sequences better differs between patients with Parkinson's disease and controls than conduction of simple, repetitive movement series.

Technology-based therapy-response and prognostic biomarkers in a prospective study of a de novo Parkinson's disease cohort

Early noninvasive reliable biomarkers are among the major unmet needs in Parkinson's disease (PD) to monitor therapy response and disease progression. Objective measures of motor performances could allow phenotyping of subtle, undetectable, early stage motor impairments of PD patients. This work aims at identifying prognostic biomarkers in newly diagnosed PD patients and quantifying therapy-response. Forty de novo PD patients underwent clinical and technology-based kinematic assessments performing motor tasks (MDS-UPDRS part III) to assess tremor, bradykinesia, gait, and postural stability (T0). A visit after 6 months (T1) and a clinical and kinematic assessment after 12 months (T2) where scheduled. A clinical follow-up was provided between 30 and 36 months after the diagnosis (T3). We performed an ANOVA for repeated measures to compare patients' kinematic features at baseline and at T2 to assess therapy response. Pearson correlation test was run between baseline kinematic features and UPDRS III score variation between T0 and T3, to select candidate kinematic prognostic biomarkers. A multiple linear regression model was created to predict the long-term motor outcome using T0 kinematic measures. All motor tasks significantly improved after the dopamine replacement therapy. A significant correlation was found between UPDRS scores variation and some baseline bradykinesia (toe tapping amplitude decrement, p = 0.009) and gait features (velocity of arms and legs, sit-to-stand time, p = 0.007; p = 0.009; p = 0.01, respectively). A linear regression model including four baseline kinematic features could significantly predict the motor outcome (p = 0.000214). Technology-based objective measures represent possible early and reproducible therapy-response and prognostic biomarkers.

Generalized Finite-Length Fibonacci Sequences in Healthy and Pathological Human Walking: Comprehensively Assessing Recursivity, Asymmetry, Consistency, Self-Similarity, and Variability of Gaits

Healthy and pathological human walking are here interpreted, from a temporal point of view, by means of dynamics-on-graph concepts and generalized finite-length Fibonacci sequences. Such sequences, in their most general definition, concern two sets of eight specific time intervals for the newly defined composite gait cycle, which involves two specific couples of overlapping (left and right) gait cycles. The role of the golden ratio, whose occurrence has been experimentally found in the recent literature, is accordingly characterized, without resorting to complex tools from linear algebra. Gait recursivity, self-similarity, and asymmetry (including double support sub-phase consistency) are comprehensively captured. A new gait index, named Φ-bonacci gait number, and a new related experimental conjecture—concerning the position of the foot relative to the tibia—are concurrently proposed. Experimental results on healthy or pathological gaits support the theoretical derivations.

Atypical Gait Cycles in Parkinson's Disease

It is important to find objective biomarkers for evaluating gait in Parkinson's Disease (PD), especially related to the foot and lower leg segments. Foot-switch signals, analyzed through Statistical Gait Analysis (SGA), allow the foot-floor contact sequence to be characterized during a walking session lasting five-minutes, which includes turnings. Gait parameters were compared between 20 PD patients and 20 age-matched controls. PDs showed similar straight-line speed, cadence, and double-support compared to controls, as well as typical gait-phase durations, except for a small decrease in the flat-foot contact duration (-4% of the gait cycle, p = 0.04). However, they showed a significant increase in atypical gait cycles (+42%, p = 0.006), during both walking straight and turning. A forefoot strike, instead of a "normal" heel strike, characterized the large majority of PD's atypical cycles, whose total percentage was 25.4% on the most-affected and 15.5% on the least-affected side. Moreover, we found a strong correlation between the atypical cycles and the motor clinical score UPDRS-III (r = 0.91, p = 0.002), in the subset of PD patients showing an abnormal number of atypical cycles, while we found a moderate correlation (r = 0.60, p = 0.005), considering the whole PD population. Atypical cycles have proved to be a valid biomarker to quantify subtle gait dysfunctions in PD patients.

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.

Evaluation for Parkinsonian Bradykinesia by deep learning modeling of kinematic parameters

A wearable sensor system is available for monitoring of bradykinesia in patients with Parkinson's disease (PD), however, it remains unclear whether kinematic parameters would reflect clinical severity of PD, or would help clinical diagnosis of physicians. The present study investigated whether the classification model using kinematic parameters from the wearable sensor may show accordance with clinical rating and diagnosis in PD patients. Using the Inertial Measurement Units (IMU) sensor, we measured the movement of finger tapping (FT), hand movements (HM), and rapid alternating movements (RA) in 25 PD patients and 21 healthy controls. Through the analysis of the measured signal, 11 objective features were derived. In addition, a clinician who specializes in movement disorders viewed the test video and evaluated each of the Unified Parkinson's Disease Rating Scale (UPDRS) scores. In all items of FT, HM, RA, the correlation between the linear regression score obtained through objective features (angle, period, coefficient variances for angle and period, change rates of angle and period, angular velocity, total angle, frequency, magnitude, and frequency × magnitude) and the clinician's UPDRS score was analyzed, and there was a significant correlation (rho > 0.7, p < 0.001). PD patients and controls were classified by deep learning using objective features. As a result, it showed a high performance with an area under the curve (AUC) about as high as 0.9 (FT Total = 0.950, HM Total = 0.889, RA Total = 0.888, ALL Total = 0.926. This showed similar performance to the classification result of binary logistic regression and neurologist, and significantly higher than that of family medicine specialists. Our results suggest that the deep learning model using objective features from the IMU sensor can be usefully used to identify and evaluate bradykinesia, especially for general physicians not specializing in neurology.

Wearable Health Devices in Health Care: Narrative Systematic Review

BACKGROUND

With the rise of mobile medicine, the development of new technologies such as smart sensing, and the popularization of personalized health concepts, the field of smart wearable devices has developed rapidly in recent years. Among them, medical wearable devices have become one of the most promising fields. These intelligent devices not only assist people in pursuing a healthier lifestyle but also provide a constant stream of health care data for disease diagnosis and treatment by actively recording physiological parameters and tracking metabolic status. Therefore, wearable medical devices have the potential to become a mainstay of the future mobile medical market.

OBJECTIVE

Although previous reviews have discussed consumer trends in wearable electronics and the application of wearable technology in recreational and sporting activities, data on broad clinical usefulness are lacking. We aimed to review the current application of wearable devices in health care while highlighting shortcomings for further research. In addition to daily health and safety monitoring, the focus of our work was mainly on the use of wearable devices in clinical practice.

METHODS

We conducted a narrative review of the use of wearable devices in health care settings by searching papers in PubMed, EMBASE, Scopus, and the Cochrane Library published since October 2015. Potentially relevant papers were then compared to determine their relevance and reviewed independently for inclusion.

RESULTS

A total of 82 relevant papers drawn from 960 papers on the subject of wearable devices in health care settings were qualitatively analyzed, and the information was synthesized. Our review shows that the wearable medical devices developed so far have been designed for use on all parts of the human body, including the head, limbs, and torso. These devices can be classified into 4 application areas: (1) health and safety monitoring, (2) chronic disease management, (3) disease diagnosis and treatment, and (4) rehabilitation. However, the wearable medical device industry currently faces several important limitations that prevent further use of wearable technology in medical practice, such as difficulties in achieving user-friendly solutions, security and privacy concerns, the lack of industry standards, and various technical bottlenecks.

CONCLUSIONS

We predict that with the development of science and technology and the popularization of personalized health concepts, wearable devices will play a greater role in the field of health care and become better integrated into people's daily lives. However, more research is needed to explore further applications of wearable devices in the medical field. We hope that this review can provide a useful reference for the development of wearable medical devices.

More Sensitive Identification for Bradykinesia Compared to Tremors in Parkinson's Disease Based on Parkinson's KinetiGraph (PKG)

The effective management and therapies for Parkinson's disease (PD) require appropriate clinical evaluation. The Parkinson's KinetiGraph (PKG) is a wearable sensor system that can monitor the motion characteristics of PD objectively and continuously. This study was aimed to assess the correlations between PKG data and clinical scores of bradykinesia, rigidity, tremor, and fluctuation. It also aims to explore the application value of identifying early motor symptoms. An observational study of 100 PD patients wearing the PKG for ≥ 6 days was performed. It provides a series of data, such as the bradykinesia score (BKS), percent time tremor (PTT), dyskinesia score (DKS), and fluctuation and dyskinesia score (FDS). PKG data and UPDRS scores were analyzed, including UPDRS III total scores, UPDRS III-bradykinesia scores (UPDRS III-B: items 23-26, 31), UPDRS III-rigidity scores (UPDRS III-R: item 22), and scores from the Wearing-off Questionnaire (WOQ-9). This study shows that there was significant correlation between BKS and UPDRS III scores, including UPDRS III total scores, UPDRS III-B, and UPDRS III-R scores (r = 0.479-0.588, p ≤ 0.001), especially in the early-stage group (r = 0.682, p < 0.001). Furthermore, we found that BKS in patients with left-sided onset (33.57 ± 5.14, n = 37) is more serious than in patients with right-sided onset (29.87 ± 6.86, n = 26). Our findings support the feasibility of using the PKG to detect abnormal movements, especially bradykinesia in PD. It is suitable for the early detection, remote monitoring, and timely treatment of PD symptoms.

Evaluation of Wearable Sensor Devices in Parkinson's Disease: A Review of Current Status and Future Prospects

Parkinson's disease (PD) decreases the quality of life of the affected individuals. The incidence of PD is expected to increase given the growing aging population. Motor symptoms associated with PD render the patients unable to self-care and function properly. Given that several drugs have been developed to control motor symptoms, highly sensitive scales for clinical evaluation of drug efficacy are needed. Among such scales, the objective and continuous evaluation of wearable devices is increasingly utilized by clinicians and patients. Several electronic technologies have revolutionized the clinical monitoring of PD development, especially its motor symptoms. Here, we review and discuss the recent advances in the development of wearable devices for bradykinesia, tremor, gait, and myotonia. Our aim is to capture the experiences of patients and clinicians, as well as expand our understanding on the application of wearable technology. In so-doing, we lay the foundation for further research into the use of wearable technology in the management of PD.

Sign Language Recognition Using Wearable Electronics: Implementing k-Nearest Neighbors with Dynamic Time Warping and Convolutional Neural Network Algorithms

We propose a sign language recognition system based on wearable electronics and two different classification algorithms. The wearable electronics were made of a sensory glove and inertial measurement units to gather fingers, wrist, and arm/forearm movements. The classifiers were k-Nearest Neighbors with Dynamic Time Warping (that is a non-parametric method) and Convolutional Neural Networks (that is a parametric method). Ten sign-words were considered from the Italian Sign Language: cose, grazie, maestra, together with words with international meaning such as google, internet, jogging, pizza, television, twitter, and ciao. The signs were repeated one-hundred times each by seven people, five male and two females, aged 29–54 y ± 10.34 (SD). The adopted classifiers performed with an accuracy of 96.6% ± 3.4 (SD) for the k-Nearest Neighbors plus the Dynamic Time Warping and of 98.0% ± 2.0 (SD) for the Convolutional Neural Networks. Our system was made of wearable electronics among the most complete ones, and the classifiers top performed in comparison with other relevant works reported in the literature.

Prediction of Individual Progression Rate in Parkinson's Disease Using Clinical Measures and Biomechanical Measures of Gait and Postural Stability

Parkinson's disease (PD) is a common neurological disorder characterized by gait impairment. PD has no cure, and an impediment to developing a treatment is the lack of any accepted method to predict disease progression rate. The primary aim of this study was to develop a model using clinical measures and biomechanical measures of gait and postural stability to predict an individual's PD progression over two years. Data from 160 PD subjects were utilized. Machine learning models, including XGBoost and Feed Forward Neural Networks, were developed using extensive model optimization and cross-validation. The highest performing model was a neural network that used a group of clinical measures, achieved a PPV of 71% in identifying fast progressors, and explained a large portion (37%) of the variance in an individual's progression rate on held-out test data. This demonstrates the potential to predict individual PD progression rate and enrich trials by analyzing clinical and biomechanical measures with machine learning.

Technology-Based Objective Measures Detect Subclinical Axial Signs in Untreated, de novo Parkinson's Disease

BACKGROUND

Technology-based objective measures (TOMs) recently gained relevance to support clinicians in the assessment of motor function in Parkinson's disease (PD), although limited data are available in the early phases.

OBJECTIVE

To assess motor performances of a population of newly diagnosed, drug free PD patients using wearable inertial sensors and to compare them to healthy controls (HC) and differentiate different PD subtypes [tremor dominant (TD), postural instability gait disability (PIGD), and mixed phenotype (MP)].

METHODS

We enrolled 65 subjects, 36 newly diagnosed, drug-free PD patients and 29 HCs. PD patients were clinically defined as tremor dominant, postural instability-gait difficulties or mixed phenotype. All 65 subjects performed seven MDS-UPDRS III motor tasks wearing inertial sensors: rest tremor, postural tremor, rapid alternating hand movement, foot tapping, heel-to-toe tapping, Timed-Up-and-Go test (TUG) and pull test. The most relevant motor tasks were found combining ReliefF ranking and Kruskal- Wallis feature-selection methods. We used these features, linked to the relevant motor tasks, to highlight differences between PD from HC, by means of Support Vector Machine (SVM) classifier. Furthermore, we adopted SVM to support the relevance of each motor task on the classification accuracy, excluding one task at time.

RESULTS

Motion analysis distinguished PD from HC with an accuracy as high as 97%, based on SVM performed with measured features from tremor and bradykinesia items, pull test and TUG. Heel-to-toe test was the most relevant, followed by TUG and Pull Test.

CONCLUSIONS

In this pilot study, we demonstrate that the SVM algorithm successfully distinguishes de novo drug-free PD patients from HC. Surprisingly, pull test and TUG tests provided relevant features for obtaining high SVM classification accuracy, differing from the report of the experienced examiner. The use of TOMs may improve diagnostic accuracy for these patients.

Wearable Electronics Assess the Effectiveness of Transcranial Direct Current Stimulation on Balance and Gait in Parkinson's Disease Patients

Currently, clinical evaluation represents the primary outcome measure in Parkinson's disease (PD). However, clinical evaluation may underscore some subtle motor impairments, hidden from the visual inspection of examiners. Technology-based objective measures are more frequently utilized to assess motor performance and objectively measure motor dysfunction. Gait and balance impairments, frequent complications in later disease stages, are poorly responsive to classic dopamine-replacement therapy. Although recent findings suggest that transcranial direct current stimulation (tDCS) can have a role in improving motor skills, there is scarce evidence for this, especially considering the difficulty to objectively assess motor function. Therefore, we used wearable electronics to measure motor abilities, and further evaluated the gait and balance features of 10 PD patients, before and (three days and one month) after the tDCS. To assess patients' abilities, we adopted six motor tasks, obtaining 72 meaningful motor features. According to the obtained results, wearable electronics demonstrated to be a valuable tool to measure the treatment response. Meanwhile the improvements from tDCS on gait and balance abilities of PD patients demonstrated to be generally partial and selective.