Classification of Parkinson's disease and essential tremor based on balance and gait characteristics from wearable motion sensors via machine learning techniques: a data-driven approach

Intelligent devices for assessing essential tremor: a comprehensive review

Essential tremor (ET) stands as the most prevalent movement disorder, characterized by rhythmic and involuntary shaking of body parts. Achieving an accurate and comprehensive assessment of tremor severity is crucial for effectively diagnosing and managing ET. Traditional methods rely on clinical observation and rating scales, which may introduce subjective biases and hinder continuous evaluation of disease progression. Recent research has explored new approaches to quantifying ET. A promising method involves the use of intelligent devices to facilitate objective and quantitative measurements. These devices include inertial measurement units, electromyography, video equipment, and electronic handwriting boards, and more. Their deployment enables real-time monitoring of human activity data, featuring portability and efficiency. This capability allows for more extensive research in this field and supports the shift from in-lab/clinic to in-home monitoring of ET symptoms. Therefore, this review provides an in-depth analysis of the application, current development, potential characteristics, and roles of intelligent devices in assessing ET.

Machine Learning Models for Parkinson Disease: Systematic Review

Background

With the increasing availability of data, computing resources, and easier-to-use software libraries, machine learning (ML) is increasingly used in disease detection and prediction, including for Parkinson disease (PD). Despite the large number of studies published every year, very few ML systems have been adopted for real-world use. In particular, a lack of external validity may result in poor performance of these systems in clinical practice. Additional methodological issues in ML design and reporting can also hinder clinical adoption, even for applications that would benefit from such data-driven systems.

Objective

To sample the current ML practices in PD applications, we conducted a systematic review of studies published in 2020 and 2021 that used ML models to diagnose PD or track PD progression.

Methods

We conducted a systematic literature review in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines in PubMed between January 2020 and April 2021, using the following exact string: "Parkinson's" AND ("ML" OR "prediction" OR "classification" OR "detection" or "artificial intelligence" OR "AI"). The search resulted in 1085 publications. After a search query and review, we found 113 publications that used ML for the classification or regression-based prediction of PD or PD-related symptoms.

Results

Only 65.5% (74/113) of studies used a holdout test set to avoid potentially inflated accuracies, and approximately half (25/46, 54%) of the studies without a holdout test set did not state this as a potential concern. Surprisingly, 38.9% (44/113) of studies did not report on how or if models were tuned, and an additional 27.4% (31/113) used ad hoc model tuning, which is generally frowned upon in ML model optimization. Only 15% (17/113) of studies performed direct comparisons of results with other models, severely limiting the interpretation of results.

Conclusions

This review highlights the notable limitations of current ML systems and techniques that may contribute to a gap between reported performance in research and the real-life applicability of ML models aiming to detect and predict diseases such as PD.

Speech, voice, and language outcomes following deep brain stimulation: A systematic review

BACKGROUND

Deep brain stimulation (DBS) reliably ameliorates cardinal motor symptoms in Parkinson's disease (PD) and essential tremor (ET). However, the effects of DBS on speech, voice and language have been inconsistent and have not been examined comprehensively in a single study.

OBJECTIVE

We conducted a systematic analysis of literature by reviewing studies that examined the effects of DBS on speech, voice and language in PD and ET.

METHODS

A total of 675 publications were retrieved from PubMed, Embase, CINHAL, Web of Science, Cochrane Library and Scopus databases. Based on our selection criteria, 90 papers were included in our analysis. The selected publications were categorized into four subcategories: Fluency, Word production, Articulation and phonology and Voice quality.

RESULTS

The results suggested a long-term decline in verbal fluency, with more studies reporting deficits in phonemic fluency than semantic fluency following DBS. Additionally, high frequency stimulation, left-sided and bilateral DBS were associated with worse verbal fluency outcomes. Naming improved in the short-term following DBS-ON compared to DBS-OFF, with no long-term differences between the two conditions. Bilateral and low-frequency DBS demonstrated a relative improvement for phonation and articulation. Nonetheless, long-term DBS exacerbated phonation and articulation deficits. The effect of DBS on voice was highly variable, with both improvements and deterioration in different measures of voice.

CONCLUSION

This was the first study that aimed to combine the outcome of speech, voice, and language following DBS in a single systematic review. The findings revealed a heterogeneous pattern of results for speech, voice, and language across DBS studies, and provided directions for future studies.

Machine Learning in the Parkinson's disease smartwatch (PADS) dataset

The utilisation of smart devices, such as smartwatches and smartphones, in the field of movement disorders research has gained significant attention. However, the absence of a comprehensive dataset with movement data and clinical annotations, encompassing a wide range of movement disorders including Parkinson's disease (PD) and its differential diagnoses (DD), presents a significant gap. The availability of such a dataset is crucial for the development of reliable machine learning (ML) models on smart devices, enabling the detection of diseases and monitoring of treatment efficacy in a home-based setting. We conducted a three-year cross-sectional study at a large tertiary care hospital. A multi-modal smartphone app integrated electronic questionnaires and smartwatch measures during an interactive assessment designed by neurologists to provoke subtle changes in movement pathologies. We captured over 5000 clinical assessment steps from 504 participants, including PD, DD, and healthy controls (HC). After age-matching, an integrative ML approach combining classical signal processing and advanced deep learning techniques was implemented and cross-validated. The models achieved an average balanced accuracy of 91.16% in the classification PD vs. HC, while PD vs. DD scored 72.42%. The numbers suggest promising performance while distinguishing similar disorders remains challenging. The extensive annotations, including details on demographics, medical history, symptoms, and movement steps, provide a comprehensive database to ML techniques and encourage further investigations into phenotypical biomarkers related to movement disorders.

Machine learning to detect, stage and classify diseases and their symptoms based on inertial sensor data: a mapping review

This article presents a systematic review aimed at mapping the literature published in the last decade on the use of machine learning (ML) for clinical decision-making through wearable inertial sensors. The review aims to analyze the trends, perspectives, strengths, and limitations of current literature in integrating ML and inertial measurements for clinical applications. The review process involved defining four research questions and applying four relevance assessment indicators to filter the search results, providing insights into the pathologies studied, technologies and setups used, data processing schemes, ML techniques applied, and their clinical impact. When combined with ML techniques, inertial measurement units (IMUs) have primarily been utilized to detect and classify diseases and their associated motor symptoms. They have also been used to monitor changes in movement patterns associated with the presence, severity, and progression of pathology across a diverse range of clinical conditions. ML models trained with IMU data have shown potential in improving patient care by objectively classifying and predicting motor symptoms, often with a minimally encumbering setup. The findings contribute to understanding the current state of ML integration with wearable inertial sensors in clinical practice and identify future research directions. Despite the widespread adoption of these technologies and techniques in clinical applications, there is still a need to translate them into routine clinical practice. This underscores the importance of fostering a closer collaboration between technological experts and professionals in the medical field.

A review of emergent intelligent systems for the detection of Parkinson's disease

Parkinson's disease (PD) is a neurodegenerative disorder affecting people worldwide. The PD symptoms are divided into motor and non-motor symptoms. Detection of PD is very crucial and essential. Such challenges can be overcome by applying artificial intelligence to diagnose PD. Many studies have also proposed the implementation of computer-aided diagnosis for the detection of PD. This systematic review comprehensively analyzed all appropriate algorithms for detecting and assessing PD based on the literature from 2012 to 2023 which are conducted as per PRISMA model. This review focused on motor symptoms, namely handwriting dynamics, voice impairments and gait, multimodal features, and brain observation using single photon emission computed tomography, magnetic resonance and electroencephalogram signals. The significant challenges are critically analyzed, and appropriate recommendations are provided. The critical discussion of this review article can be helpful in today's PD community in such a way that it allows clinicians to provide proper treatment and timely medication.

Treatment Detection and Movement Disorder Society-Unified Parkinson's Disease Rating Scale, Part III Estimation Using Finger Tapping Tasks

The validation of objective and easy-to-implement biomarkers that can monitor the effects of fast-acting drugs among Parkinson's disease (PD) patients would benefit antiparkinsonian drug development. We developed composite biomarkers to detect levodopa/carbidopa effects and to estimate PD symptom severity. For this development, we trained machine learning algorithms to select the optimal combination of finger tapping task features to predict treatment effects and disease severity. Data were collected during a placebo-controlled, crossover study with 20 PD patients. The alternate index and middle finger tapping (IMFT), alternative index finger tapping (IFT), and thumb-index finger tapping (TIFT) tasks and the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) III were performed during treatment. We trained classification algorithms to select features consisting of the MDS-UPDRS III item scores; the individual IMFT, IFT, and TIFT; and all three tapping tasks collectively to classify treatment effects. Furthermore, we trained regression algorithms to estimate the MDS-UPDRS III total score using the tapping task features individually and collectively. The IFT composite biomarker had the best classification performance (83.50% accuracy, 93.95% precision) and outperformed the MDS-UPDRS III composite biomarker (75.75% accuracy, 73.93% precision). It also achieved the best performance when the MDS-UPDRS III total score was estimated (mean absolute error: 7.87, Pearson's correlation: 0.69). We demonstrated that the IFT composite biomarker outperformed the combined tapping tasks and the MDS-UPDRS III composite biomarkers in detecting treatment effects. This provides evidence for adopting the IFT composite biomarker for detecting antiparkinsonian treatment effect in clinical trials. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

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.

Using histogram analysis of the intrinsic brain activity mapping to identify essential tremor

Background

Essential tremor (ET) is one of the most common movement disorders. Histogram analysis based on brain intrinsic activity imaging is a promising way to identify ET patients from healthy controls (HCs) and further explore the spontaneous brain activity change mechanisms and build the potential diagnostic biomarker in ET patients.

Methods

The histogram features based on the Resting-state functional magnetic resonance imaging (Rs-fMRI) data were extracted from 133 ET patients and 135 well-matched HCs as the input features. Then, a two-sample t-test, the mutual information, and the least absolute shrinkage and selection operator methods were applied to reduce the feature dimensionality. Support vector machine (SVM), logistic regression (LR), random forest (RF), and k-nearest neighbor (KNN) were used to differentiate ET and HCs, and classification performance of the established models was evaluated by the mean area under the curve (AUC). Moreover, correlation analysis was carried out between the selected histogram features and clinical tremor characteristics.

Results

Each classifier achieved a good classification performance in training and testing sets. The mean accuracy and area under the curve (AUC) of SVM, LR, RF, and KNN in the testing set were 92.62%, 0.948; 92.01%, 0.942; 93.88%, 0.941; and 92.27%, 0.939, respectively. The most power-discriminative features were mainly located in the cerebello-thalamo-motor and non-motor cortical pathways. Correlation analysis showed that there were two histogram features negatively and one positively correlated with tremor severity.

Conclusion

Our findings demonstrated that the histogram analysis of the amplitude of low-frequency fluctuation (ALFF) images with multiple machine learning algorithms could identify ET patients from HCs and help to understand the spontaneous brain activity pathogenesis mechanisms in ET patients.

Wearable sensor-based gait analysis to discriminate early Parkinson's disease from essential tremor

BACKGROUND

Differentiating early-stage Parkinson's disease (PD) from essential tremor (ET) is challenging since they have some overlapping clinical features. Since early-stage PD may present with slight gait impairment and ET generally does not, gait analysis could be used to differentiate PD from ET using machine learning.

OBJECTIVE

To differentiate early-stage PD from ET via machine learning using gait and postural transition parameters calculated using the raw kinematic signal captured from inertial measurement unit (IMU) sensors.

METHODS

Gait and postural transition parameters were collected from 84 early-stage PD and 80 ET subjects during the Time Up and Go (TUG) test. We randomly split our data into training and test data. Within the training data, we separated the TUG test into four components: standing, straight walk, turning, and sitting to build weighted average ensemble classification models. The four components' weight indices were trained using logistic regression. Several ensemble models' leave-one-out cross-validation (LOOCV) performances were compared. Independent test data were used to evaluate the model with the best LOOCV performance.

RESULTS

The best weighted average ensemble classification model LOOCV results included an accuracy of 84%, Kappa of 0.68, sensitivity of 85.9%, specificity of 82.1%, and AUC of 0.912. Thirty-three gait and postural transition parameters, such as Arm-Symbolic Symmetry Index and 180° Turn-Max Angular Velocity, were included in Feature Group III. The independent test data achieved a 75.8% accuracy.

CONCLUSIONS

Our findings suggest that gait and postural transition parameters obtained from wearable sensors combined with machine learning had the potential to distinguish between early-stage PD and ET.

Classification of Kinematic and Electromyographic Signals Associated with Pathological Tremor Using Machine and Deep Learning

Peripheral Electrical Stimulation (PES) of afferent pathways has received increased interest as a solution to reduce pathological tremors with minimal side effects. Closed-loop PES systems might present some advantages in reducing tremors, but further developments are required in order to reliably detect pathological tremors to accurately enable the stimulation only if a tremor is present. This study explores different machine learning (K-Nearest Neighbors, Random Forest and Support Vector Machines) and deep learning (Long Short-Term Memory neural networks) models in order to provide a binary (Tremor; No Tremor) classification of kinematic (angle displacement) and electromyography (EMG) signals recorded from patients diagnosed with essential tremors and healthy subjects. Three types of signal sequences without any feature extraction were used as inputs for the classifiers: kinematics (wrist flexion-extension angle), raw EMG and EMG envelopes from wrist flexor and extensor muscles. All the models showed high classification scores (Tremor vs. No Tremor) for the different input data modalities, ranging from 0.8 to 0.99 for the f₁ score. The LSTM models achieved 0.98 f₁ scores for the classification of raw EMG signals, showing high potential to detect tremors without any processed features or preliminary information. These models may be explored in real-time closed-loop PES strategies to detect tremors and enable stimulation with minimal signal processing steps.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Identifying and distinguishing of essential tremor and Parkinson's disease with grouped stability analysis based on searchlight-based MVPA

BACKGROUND

Since both essential tremor (ET) and Parkinson's disease (PD) are movement disorders and share similar clinical symptoms, it is very difficult to recognize the differences in the presentation, course, and treatment of ET and PD, which leads to misdiagnosed commonly.

PURPOSE

Although neuroimaging biomarker of ET and PD has been investigated based on statistical analysis, it is unable to assist the clinical diagnosis of ET and PD and ensure the efficiency of these biomarkers. The aim of the study was to identify the neuroimaging biomarkers of ET and PD based on structural magnetic resonance imaging (MRI). Moreover, the study also distinguished ET from PD via these biomarkers to validate their classification performance.

METHODS

This study has developed and implemented a three-level machine learning framework to identify and distinguish ET and PD. First of all, at the model-level assessment, the searchlight-based machine learning method has been used to identify the group differences of patients (ET/PD) with normal controls (NCs). And then, at the feature-level assessment, the stability of group differences has been tested based on structural brain atlas separately using the permutation test to identify the robust neuroimaging biomarkers. Furthermore, the identified biomarkers of ET and PD have been applied to classify ET from PD based on machine learning techniques. Finally, the identified biomarkers have been compared with the previous findings of the biology-level assessment.

RESULTS

According to the biomarkers identified by machine learning, this study has found widespread alterations of gray matter (GM) for ET and large overlap between ET and PD and achieved superior classification performance (PCA + SVM, accuracy = 100%).

CONCLUSIONS

This study has demonstrated the significance of a machine learning framework to identify and distinguish ET and PD. Future studies using a large data set are needed to confirm the potential clinical application of machine learning techniques to discern between PD and ET.

A Computerized Analysis with Machine Learning Techniques for the Diagnosis of Parkinson's Disease: Past Studies and Future Perspectives

According to the World Health Organization (WHO), Parkinson's disease (PD) is a neurodegenerative disease of the brain that causes motor symptoms including slower movement, rigidity, tremor, and imbalance in addition to other problems like Alzheimer's disease (AD), psychiatric problems, insomnia, anxiety, and sensory abnormalities. Techniques including artificial intelligence (AI), machine learning (ML), and deep learning (DL) have been established for the classification of PD and normal controls (NC) with similar therapeutic appearances in order to address these problems and improve the diagnostic procedure for PD. In this article, we examine a literature survey of research articles published up to September 2022 in order to present an in-depth analysis of the use of datasets, various modalities, experimental setups, and architectures that have been applied in the diagnosis of subjective disease. This analysis includes a total of 217 research publications with a list of the various datasets, methodologies, and features. These findings suggest that ML/DL methods and novel biomarkers hold promising results for application in medical decision-making, leading to a more methodical and thorough detection of PD. Finally, we highlight the challenges and provide appropriate recommendations on selecting approaches that might be used for subgrouping and connection analysis with structural magnetic resonance imaging (sMRI), DaTSCAN, and single-photon emission computerized tomography (SPECT) data for future Parkinson's research.

Machine learning predicting mortality in sarcoidosis patients admitted for acute heart failure

Background

Sarcoidosis with cardiac involvement, although rare, has a worse prognosis than sarcoidosis involving other organ systems.

Objective

We used a large dataset to train machine learning models to predict in-hospital mortality among sarcoidosis patients admitted with heart failure (HF).

Method

Utilizing the National Inpatient Sample, we identified 4659 patients hospitalized with a primary diagnosis of HF. In this cohort, we identified patients with a secondary diagnosis of sarcoidosis using International Statistical Classification of Disease, Tenth Revision (ICD-10) codes. Patients were separated into a training group and a testing group in a 7:3 ratio. Least absolute shrinkage and selection operator regression was used to select variables to prevent model overfitting or underfitting. For machine learning models, logistic regression, random forest, and XGBoosting were applied in the training group. Parameters in each of the models were tuned using the GridSearchCV function. After training, all models were further validated in the testing group. Models were then evaluated using the area under curve (AUC) score, sensitivity, and specificity.

Results

A total of 2.3% of sarcoidosis patients died in HF admission. Our machine learning model analysis found the RF model to have the highest AUC score and sensitivity. Feature analysis found that comorbid arrhythmias and fluid electrolyte disorders were the strongest factors in predicting in-hospital mortality.

Conclusion

Machine learning methods can be useful in identifying predictors of in-hospital mortality in a given dataset.

Development and Assessment of a Movement Disorder Simulator Based on Inertial Data

The detection analysis of neurodegenerative diseases by means of low-cost sensors and suitable classification algorithms is a key part of the widely spreading telemedicine techniques. The choice of suitable sensors and the tuning of analysis algorithms require a large amount of data, which could be derived from a large experimental measurement campaign involving voluntary patients. This process requires a prior approval phase for the processing and the use of sensitive data in order to respect patient privacy and ethical aspects. To obtain clearance from an ethics committee, it is necessary to submit a protocol describing tests and wait for approval, which can take place after a typical period of six months. An alternative consists of structuring, implementing, validating, and adopting a software simulator at most for the initial stage of the research. To this end, the paper proposes the development, validation, and usage of a software simulator able to generate movement disorders-related data, for both healthy and pathological conditions, based on raw inertial measurement data, and give tri-axial acceleration and angular velocity as output. To present a possible operating scenario of the developed software, this work focuses on a specific case study, i.e., the Parkinson's disease-related tremor, one of the main disorders of the homonym pathology. The full framework is reported, from raw data availability to pathological data generation, along with a common machine learning method implementation to evaluate data suitability to be distinguished and classified. Due to the development of a flexible and easy-to-use simulator, the paper also analyses and discusses the data quality, described with typical measurement features, as a metric to allow accurate classification under a low-performance sensing device. The simulator's validation results show a correlation coefficient greater than 0.94 for angular velocity and 0.93 regarding acceleration data. Classification performance on Parkinson's disease tremor was greater than 98% in the best test conditions.

End-to-end design of wearable sensors

Wearable devices provide an alternative pathway to clinical diagnostics by exploiting various physical, chemical and biological sensors to mine physiological (biophysical and/or biochemical) information in real time (preferably, continuously) and in a non-invasive or minimally invasive manner. These sensors can be worn in the form of glasses, jewellery, face masks, wristwatches, fitness bands, tattoo-like devices, bandages or other patches, and textiles. Wearables such as smartwatches have already proved their capability for the early detection and monitoring of the progression and treatment of various diseases, such as COVID-19 and Parkinson disease, through biophysical signals. Next-generation wearable sensors that enable the multimodal and/or multiplexed measurement of physical parameters and biochemical markers in real time and continuously could be a transformative technology for diagnostics, allowing for high-resolution and time-resolved historical recording of the health status of an individual. In this Review, we examine the building blocks of such wearable sensors, including the substrate materials, sensing mechanisms, power modules and decision-making units, by reflecting on the recent developments in the materials, engineering and data science of these components. Finally, we synthesize current trends in the field to provide predictions for the future trajectory of wearable sensors.

A Vision-Based System for Stage Classification of Parkinsonian Gait Using Machine Learning and Synthetic Data

Parkinson's disease is characterized by abnormal gait, which worsens as the condition progresses. Although several methods have been able to classify this feature through pose-estimation algorithms and machine-learning classifiers, few studies have been able to analyze its progression to perform stage classification of the disease. Moreover, despite the increasing popularity of these systems for gait analysis, the amount of available gait-related data can often be limited, thereby, hindering the progress of the implementation of this technology in the medical field. As such, creating a quantitative prognosis method that can identify the severity levels of a Parkinsonian gait with little data could help facilitate the study of the Parkinsonian gait for rehabilitation. In this contribution, we propose a vision-based system to analyze the Parkinsonian gait at various stages using linear interpolation of Parkinsonian gait models. We present a comparison between the performance of a k-nearest neighbors algorithm (KNN), support-vector machine (SVM) and gradient boosting (GB) algorithms in classifying well-established gait features. Our results show that the proposed system achieved 96-99% accuracy in evaluating the prognosis of Parkinsonian gaits.

Objective quantification of the severity of postural tremor based on kinematic parameters: A multi-sensory fusion study

BACKGROUND

Current clinical assessments of essential tremor (ET) are primarily based on expert consultation combined with reviewing patient complaints, physician expertise, and diagnostic experience. Thus, traditional evaluation methods often lead to biased diagnostic results. There is a clinical demand for a method that can objectively quantify the severity of the patient's disease.

METHODS

This study aims to develop an artificial intelligence-aided diagnosis method based on multi-sensory fusion wearables. The experiment relies on a rigorous clinical trial paradigm to collect multi-modal fusion of signals from 98 ET patients. At the same time, three clinicians scored independently, and the consensus score obtained was used as the ground truth for the machine learning models.

RESULTS

Sixty kinematic parameters were extracted from the signals recorded by the nine-axis inertial measurement unit (IMU). The results showed that most of the features obtained by IMU could effectively characterize the severity of the tremors. The accuracy of the optimal model for three tasks classifying five severity levels was 97.71%, 97.54%, and 97.72%, respectively.

CONCLUSIONS

This paper reports the first attempt to combine multiple feature selection and machine learning algorithms for fine-grained automatic quantification of postural tremor in ET patients. The promising results showed the potential of the proposed approach to quantify the severity of ET objectively.

Generalizability of deep learning models for predicting outdoor irregular walking surfaces

Observations from laboratory-based gait analysis are difficult to extrapolate to real-world environments where gait behavior is modulated in response to complex environmental conditions and surface profiles. Inertial measurement units (IMUs) permit real-world gait analysis; however, automatic detection of surfaces encountered remains largely unexplored. The aims of this study are to quantify for machine learning models the effect of (1) random and subject-wise data splitting and (2) sensor location and count on surface classification performance. Thirty participants walked on nine surface conditions (flat-even, slope-up, slope-down, stairs-up, stairs-down, cobblestone, grass, banked-left, banked-right) wearing IMUs (wrist, trunk, bilateral thighs, bilateral shanks). Data were separated into gait cycles, normalized to 101 samples, and spilt into train and test sets (85 and 15%, respectively). For random splitting, trials were randomly assigned to the train or test set. In subject-wise splitting, all trials from 4 random participants were selected for testing. Linear discriminant analysis extracted features from the IMUs. Features were delivered to a neural network. F1-score evaluated model performance. Models achieved F1 scores of 0.96 and 0.78 using random and subject-wise splitting, respectively. Random splitting performance was mainly invariant to sensor location/count; however, subject-wise splitting showed best performance using lower-limb sensors. In general, stairs and sloped surfaces were easily predicted (F1 > 0.85) while banked surfaces were challenging, especially for subject-wise models (F1 ≈ 0.6). Neural networks can detect surfaces based on subtle changes in walking behavior captured by IMUs. Data splitting approaches and sensor location/count (subject-wise) have a non-negligible effect on model performance.

Machine Learning Approach to Support the Detection of Parkinson's Disease in IMU-Based Gait Analysis

The aim of this study was to determine which supervised machine learning (ML) algorithm can most accurately classify people with Parkinson’s disease (pwPD) from speed-matched healthy subjects (HS) based on a selected minimum set of IMU-derived gait features. Twenty-two gait features were extrapolated from the trunk acceleration patterns of 81 pwPD and 80 HS, including spatiotemporal, pelvic kinematics, and acceleration-derived gait stability indexes. After a three-level feature selection procedure, seven gait features were considered for implementing five ML algorithms: support vector machine (SVM), artificial neural network, decision trees (DT), random forest (RF), and K-nearest neighbors. Accuracy, precision, recall, and F1 score were calculated. SVM, DT, and RF showed the best classification performances, with prediction accuracy higher than 80% on the test set. The conceptual model of approaching ML that we proposed could reduce the risk of overrepresenting multicollinear gait features in the model, reducing the risk of overfitting in the test performances while fostering the explainability of the results.

Combined Intrinsic Local Functional Connectivity With Multivariate Pattern Analysis to Identify Depressed Essential Tremor

Background

Although depression is one of the most common neuropsychiatric symptoms in essential tremor (ET), the diagnosis biomarker and intrinsic brain activity remain unclear. We aimed to combine multivariate pattern analysis (MVPA) with local brain functional connectivity to identify depressed ET.

Methods

Based on individual voxel-level local brain functional connectivity (regional homogeneity, ReHo) mapping from 41 depressed ET, 43 non-depressed ET, and 45 healthy controls (HCs), the binary support vector machine (BSVM) and multiclass Gaussian Process Classification (MGPC) algorithms were used to identify depressed ET patients from non-depressed ET and HCs, the accuracy and permutations test were used to assess the classification performance.

Results

The MGPC algorithm was able to classify the three groups (depressed ET, non-depressed ET, and HCs) with a total accuracy of 84.5%. The BSVM algorithm achieved a better classification performance with total accuracy of 90.7, 88.64, and 90.48% for depressed ET vs. HCs, non-depressed ET vs. HCs, and depressed ET vs. non-depressed ET, and the sensitivity for them at 80.49, 76.64, and 80.49%, respectively. The significant discriminative features of depressed ET vs. HCs were primarily located in the cerebellar-motor-prefrontal gyrus-anterior cingulate cortex pathway, and for depressed ET vs. non-depressed ET located in the cerebellar-prefrontal gyrus-anterior cingulate cortex circuits. The partial correlation showed that the ReHo values in the bilateral middle prefrontal gyrus (positive) and the bilateral cerebellum XI (negative) were significantly correlated with clinical depression severity.

Conclusion

Our findings suggested that combined individual ReHo maps with MVPA not only could be used to identify depressed ET but also help to reveal the intrinsic brain activity changes and further act as the potential diagnosis biomarker in depressed ET patients.

Intraoperative Quantification of MDS-UPDRS Tremor Measurements Using 3D Accelerometry: A Pilot Study

The most frequently used method for evaluating tremor in Parkinson’s disease (PD) is currently the internationally standardized Movement Disorder Society—Unified PD Rating Scale (MDS-UPDRS). However, the MDS-UPDRS is associated with limitations, such as its inherent subjectivity and reliance on experienced raters. Objective motor measurements using accelerometry may overcome the shortcomings of visually scored scales. Therefore, the current study focuses on translating the MDS-UPDRS tremor tests into an objective scoring method using 3D accelerometry. An algorithm to measure and classify tremor according to MDS-UPDRS criteria is proposed. For this study, 28 PD patients undergoing neurosurgical treatment and 26 healthy control subjects were included. Both groups underwent MDS-UPDRS tests to rate tremor severity, while accelerometric measurements were performed at the index fingers. All measurements were performed in an off-medication state. Quantitative measures were calculated from the 3D acceleration data, such as tremor amplitude and area-under-the-curve of power in the 4−6 Hz range. Agreement between MDS-UPDRS tremor scores and objective accelerometric scores was investigated. The trends were consistent with the logarithmic relationship between tremor amplitude and MDS-UPDRS score reported in previous studies. The accelerometric scores showed a substantial concordance (>69.6%) with the MDS-UPDRS ratings. However, accelerometric kinetic tremor measures poorly associated with the given MDS-UPDRS scores (R2 < 0.3), mainly due to the noise between 4 and 6 Hz found in the healthy controls. This study shows that MDS-UDPRS tremor tests can be translated to objective accelerometric measurements. However, discrepancies were found between accelerometric kinetic tremor measures and MDS-UDPRS ratings. This technology has the potential to reduce rater dependency of MDS-UPDRS measurements and allow more objective intraoperative monitoring of tremor.

Co-evolution of machine learning and digital technologies to improve monitoring of Parkinson's disease motor symptoms

Parkinson’s disease (PD) is a neurodegenerative disorder characterized by motor impairments such as tremor, bradykinesia, dyskinesia, and gait abnormalities. Current protocols assess PD symptoms during clinic visits and can be subjective. Patient diaries can help clinicians evaluate at-home symptoms, but can be incomplete or inaccurate. Therefore, researchers have developed in-home automated methods to monitor PD symptoms to enable data-driven PD diagnosis and management. We queried the US National Library of Medicine PubMed database to analyze the progression of the technologies and computational/machine learning methods used to monitor common motor PD symptoms. A sub-set of roughly 12,000 papers was reviewed that best characterized the machine learning and technology timelines that manifested from reviewing the literature. The technology used to monitor PD motor symptoms has advanced significantly in the past five decades. Early monitoring began with in-lab devices such as needle-based EMG, transitioned to in-lab accelerometers/gyroscopes, then to wearable accelerometers/gyroscopes, and finally to phone and mobile & web application-based in-home monitoring. Significant progress has also been made with respect to the use of machine learning algorithms to classify PD patients. Using data from different devices (e.g., video cameras, phone-based accelerometers), researchers have designed neural network and non-neural network-based machine learning algorithms to categorize PD patients across tremor, gait, bradykinesia, and dyskinesia. The five-decade co-evolution of technology and computational techniques used to monitor PD motor symptoms has driven significant progress that is enabling the shift from in-lab/clinic to in-home monitoring of PD symptoms.

Analysing gait patterns in degenerative lumbar spine diseases: a literature review

OBJECTIVES

To collate the current state of knowledge and explore differences in the spatiotemporal gait patterns of degenerative lumbar spine diseases: lumbar spinal stenosis (LSS), lumbar disc herniation (LDH) and low back pain (LBP).

BACKGROUND

LBP is common presenting complaint with degenerative lumbar spine disease being a common cause. In particular, the gait patterns of LSS, LDH and mechanical-type (facetogenic and discogenic) LBP is not established.

METHODS

A search of the literature was conducted to determine the changes in spatial and temporal gait metrics involved with each type of degenerative lumbar spine disease. A search of databases including Medline, Embase and PubMed from their date of inception to April 18th, 2021 was performed to screen, review and identify relevant studies for qualitative synthesis. Seventeen relevant studies were identified for inclusion in the present review. Of these, 5 studies investigated gait patterns in LSS, 10 studies investigated LBP and 2 studies investigated LDH. Of these, 4 studies employed wearable accelerometry in LSS (2 studies) and LBP (2 studies).

CONCLUSIONS

Previous studies suggest degenerative diseases of the lumbar spine have unique patterns of gait deterioration. LSS is characterised by asymmetry and variability. Spatiotemporal gait deterioration in gait velocity, cadence with increased double-support duration and gait variability are distinguishing features in LDH. LBP involves marginal abnormalities in temporal and spatial gait metrics. Previous studies suggest degenerative diseases of the lumbar spine have unique patterns of gait deterioration. Gait asymmetry and variability, may be relevant metrics for distinguishing between the gait profiles of lumbar spine diseases.

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.

The application of artificial intelligence and custom algorithms with inertial wearable devices for gait analysis and detection of gait-altering pathologies in adults: A scoping review of literature

Background

The purpose of this scoping review was to explore the current applications of objective gait analysis using inertial measurement units, custom algorithms and artificial intelligence algorithms in detecting neurological and musculoskeletal gait altering pathologies from healthy gait patterns.

Methods

Literature searches were conducted of four electronic databases (Medline, PubMed, Embase and Web of Science) to identify studies that assessed the accuracy of these custom gait analysis models with inputs derived from wearable devices. Data was collected according to the preferred reporting items for systematic reviews and meta-analysis statement guidelines.

Results

A total of 23 eligible studies were identified for inclusion in the present review, including 10 custom algorithms articles and 13 artificial intelligence algorithms articles. Nine studies evaluated patients with Parkinson’s disease of varying severity and subtypes. Support vector machine was the commonest adopted artificial intelligence algorithm model, followed by random forest and neural networks. Overall classification accuracy was promising for articles that use artificial intelligence algorithms, with nine articles achieving more than 90% accuracy.

Conclusions

Current applications of artificial intelligence algorithms are reasonably effective discrimination between pathological and non-pathological gait. Of these, machine learning algorithms demonstrate the additional capacity to handle complicated data input, when compared to other custom algorithms. Notably, there has been increasing application of machine learning algorithms for conducting gait analysis. More studies are needed with unsupervised methods and in non-clinical settings to better reflect the community and home-based usage.

Identifying Depressed Essential Tremor Using Resting-State Voxel-Wise Global Brain Connectivity: A Multivariate Pattern Analysis

Background and Objective: Although depression is one of the most common non-motor symptoms in essential tremor (ET), its pathogenesis and diagnosis biomarker are still unknown. Recently, machine learning multivariate pattern analysis (MVPA) combined with connectivity mapping of resting-state fMRI has provided a promising way to identify patients with depressed ET at the individual level and help to reveal the brain network pathogenesis of depression in patients with ET.

Methods: Based on global brain connectivity (GBC) mapping from 41 depressed ET, 49 non-depressed ET, 45 primary depression, and 43 healthy controls (HCs), multiclass Gaussian process classification (GPC) and binary support vector machine (SVM) algorithms were used to identify patients with depressed ET from non-depressed ET, primary depression, and HCs, and the accuracy and permutation tests were used to assess the classification performance.

Results: While the total accuracy (40.45%) of four-class GPC was poor, the four-class GPC could discriminate depressed ET from non-depressed ET, primary depression, and HCs with a sensitivity of 70.73% (P < 0.001). At the same time, the sensitivity of using binary SVM to discriminate depressed ET from non-depressed ET, primary depression, and HCs was 73.17, 80.49, and 75.61%, respectively (P < 0.001). The significant discriminative features were mainly located in cerebellar-motor-prefrontal cortex circuits (P < 0.001), and a further correlation analysis showed that the GBC values of significant discriminative features in the right middle prefrontal gyrus, bilateral cerebellum VI, and Crus 1 were correlated with clinical depression severity in patients with depressed ET.

Conclusion: Our findings demonstrated that GBC mapping combined with machine learning MVPA could be used to identify patients with depressed ET, and the GBC changes in cerebellar-prefrontal cortex circuits not only posed as the significant discriminative features but also helped to understand the network pathogenesis underlying depression in patients with ET.

Diagnostic AI Modeling and Pseudo Time Series Profiling of AD and PD Based on Individualized Serum Proteome Data

Background: Parkinson’s disease (PD), Alzheimer’s disease (AD) are common neurodegenerative disease, while mild cognitive impairment (MCI) may be happened in the early stage of AD or PD. Blood biomarkers are considered to be less invasive, less cost and more convenient, and there is tremendous potential for the diagnosis and prediction of neurodegenerative diseases. As a recently mentioned field, artificial intelligence (AI) is often applied in biology and shows excellent results. In this article, we use AI to model PD, AD, MCI data and analyze the possible connections between them.

Method: Human blood protein microarray profiles including 156 CT, 50 MCI, 132 PD, 50 AD samples are collected from Gene Expression Omnibus (GEO). First, we used bioinformatics methods and feature engineering in machine learning to screen important features, constructed artificial neural network (ANN) classifier models based on these features to distinguish samples, and evaluated the model’s performance with classification accuracy and Area Under Curve (AUC). Second, we used Ingenuity Pathway Analysis (IPA) methods to analyse the pathways and functions in early stage and late stage samples of different diseases, and potential targets for drug intervention by predicting upstream regulators.

Result: We used different classifier to construct the model and finally found that ANN model would outperform the traditional machine learning model. In summary, three different classifiers were constructed to be used in different application scenarios, First, we incorporated 6 indicators, including EPHA2, MRPL19, SGK2, to build a diagnostic model for AD with a test set accuracy of up to 98.07%. Secondly, incorporated 15 indicators such as ERO1LB, FAM73B, IL1RN to build a diagnostic model for PD, with a test set accuracy of 97.05%. Then, 15 indicators such as XG, FGFR3 and CDC37 were incorporated to establish a four-category diagnostic model for both AD and PD, with a test set accuracy of 98.71%. All classifier models have an auc value greater than 0.95. Then, we verified that the constructed feature engineering filtered out fewer important features but contained more information, which helped to build a better model. In addition, by classifying the disease types more carefully into early and late stages of AD, MCI, and PD, respectively, we found that early PD may occur earlier than early MCI. Finally, there are 24 proteins that are both differentially expressed proteins and upstream regulators in the disease group versus the normal group, and these proteins may serve as potential therapeutic targets and targets for subsequent studies.

Conclusion: The feature engineering we build allows better extraction of information while reducing the number of features, which may help in subsequent applications. Building a classifier based on blood protein profiles using deep learning methods can achieve better classification performance, and it can help us to diagnose the disease early. Overall, it is important for us to study neurodegenerative diseases from both diagnostic and interventional aspects.

Positive impact of short-term gait rehabilitation in Parkinson patients: a combined approach based on statistics and machine learning

Parkinson's disease is the second most common neurodegenerative disorder in the world. Assumed that gait dysfunctions represent a major motor symptom for the pathology, gait analysis can provide clinicians quantitative information about the rehabilitation outcome of patients. In this scenario, wearable inertial systems for gait analysis can be a valid tool to assess the functional recovery of patients in an automatic and quantitative way, helping clinicians in decision making. Aim of the study is to evaluate the impact of the short-term rehabilitation on gait and balance of patients with Parkinson's disease. A cohort of 12 patients with Idiopathic Parkinson's disease performed a gait analysis session instrumented by a wearable inertial system for gait analysis: Opal System, by APDM Inc., with spatial and temporal parameters being analyzed through a statistic and machine learning approach. Six out of fourteen motion parameters exhibited a statistically significant difference between the measurements at admission and at discharge of the patients, while the machine learning analysis confirmed the separability of the two phases in terms of Accuracy and Area under the Receiving Operating Characteristic Curve. The rehabilitation treatment especially improved the motion parameters related to the gait. The study shows the positive impact on the gait of a short-term rehabilitation in patients with Parkinson's disease and the feasibility of the wearable inertial devices, that are increasingly spreading in clinical practice, to quantitatively assess the gait improvement.

Recent trends in artificial intelligence-driven identification and development of anti-neurodegenerative therapeutic agents

Neurological disorders affect various aspects of life. Finding drugs for the central nervous system is a very challenging and complex task due to the involvement of the blood-brain barrier, P-glycoprotein, and the drug's high attrition rates. The availability of big data present in online databases and resources has enabled the emergence of artificial intelligence techniques including machine learning to analyze, process the data, and predict the unknown data with high efficiency. The use of these modern techniques has revolutionized the whole drug development paradigm, with an unprecedented acceleration in the central nervous system drug discovery programs. Also, the new deep learning architectures proposed in many recent works have given a better understanding of how artificial intelligence can tackle big complex problems that arose due to central nervous system disorders. Therefore, the present review provides comprehensive and up-to-date information on machine learning/artificial intelligence-triggered effort in the brain care domain. In addition, a brief overview is presented on machine learning algorithms and their uses in structure-based drug design, ligand-based drug design, ADMET prediction, de novo drug design, and drug repurposing. Lastly, we conclude by discussing the major challenges and limitations posed and how they can be tackled in the future by using these modern machine learning/artificial intelligence approaches.

A deep explainable artificial intelligent framework for neurological disorders discrimination

Pathological hand tremor (PHT) is a common symptom of Parkinson's disease (PD) and essential tremor (ET), which affects manual targeting, motor coordination, and movement kinetics. Effective treatment and management of the symptoms relies on the correct and in-time diagnosis of the affected individuals, where the characteristics of PHT serve as an imperative metric for this purpose. Due to the overlapping features of the corresponding symptoms, however, a high level of expertise and specialized diagnostic methodologies are required to correctly distinguish PD from ET. In this work, we propose the data-driven [Formula: see text] model, which processes the kinematics of the hand in the affected individuals and classifies the patients into PD or ET. [Formula: see text] is trained over 90 hours of hand motion signals consisting of 250 tremor assessments from 81 patients, recorded at the London Movement Disorders Centre, ON, Canada. The [Formula: see text] outperforms its state-of-the-art counterparts achieving exceptional differential diagnosis accuracy of [Formula: see text]. In addition, using the explainability and interpretability measures for machine learning models, clinically viable and statistically significant insights on how the data-driven model discriminates between the two groups of patients are achieved.