Wearable sensor-based quantitative gait analysis in Parkinson's disease patients with different motor subtypes.

Gait impairments are among the most common and disabling symptoms of Parkinson's disease and worsen as the disease progresses. Early detection and diagnosis of subtype-specific gait deficits, as well as progression monitoring, can help to implement effective and preventive personalized treatment for PD patients. Yet, the gait features have not been fully studied in PD and its motor subtypes. To characterize comprehensive and objective gait alterations and to identify the potential gait biomarkers for early diagnosis, subtype differentiation, and disease severity monitoring. We analyzed gait parameters related to upper/lower limbs, trunk and lumbar, and postural transitions from 24 tremor-dominant (TD) and 20 postural instability gait difficulty (PIGD) dominant PD patients who were in early stage and 39 matched healthy controls (HC) during the Timed Up and Go test using wearable sensors. Results show: (1) Both TD and PIGD groups showed restricted backswing range in bilateral lower extremities and more affected side (MAS) arm, reduced trunk and lumbar rotation range in the coronal plane, and low turning efficiency. The receiver operating characteristic (ROC) analysis revealed these objective gait features had high discriminative value in distinguishing both PD subtypes from the HC with the area under the curve (AUC) values of 0.7~0.9 (p < 0.01). (2) Subtle but measurable gait differences existed between TD and PIGD patients before the onset of clinically apparent gait impairment. (3) Specific gait parameters were significantly associated with disease severity in TD and PIGD subtypes. Objective gait biomarkers based on wearable sensors may facilitate timely and personalized gait treatments in PD subtypes through early diagnosis, subtype differentiation, and disease severity monitoring.

Using sustained vowels to identify patients with mild Parkinson's disease in a Chinese dataset.

Introduction: Parkinson's disease (PD) is the second most common neurodegenerative disease and affects millions of people. Accurate diagnosis and subsequent treatment in the early stages can slow down disease progression. However, making an accurate diagnosis of PD at an early stage is challenging. Previous studies have revealed that even for movement disorder specialists, it was difficult to differentiate patients with PD from healthy individuals until the average modified Hoehn-Yahr staging (mH&Y) reached 1.8. Recent researches have shown that dysarthria provides good indicators for computer-assisted diagnosis of patients with PD. However, few studies have focused on diagnosing patients with PD in the early stages, specifically those with mH&Y ≤ 1.5. Method: We used a machine learning algorithm to analyze voice features and developed diagnostic models for differentiating between healthy controls (HCs) and patients with PD, and for differentiating between HCs and patients with mild PD (mH&Y ≤ 1.5). The models were independently validated using separate datasets. Results: Our results demonstrate that, a remarkable diagnostic performance of the model in identifying patients with mild PD (mH&Y ≤ 1.5) and HCs, with area under the ROC curve 0.93 (95% CI: 0.851.00), accuracy 0.85, sensitivity 0.95, and specificity 0.75. Conclusion: The results of our study are helpful for screening PD in the early stages in the community and primary medical institutions where there is a lack of movement disorder specialists and special equipment.

Machine-learning model for the prediction of acute orthostatic hypotension after levodopa administration.

BACKGROUND: Levodopa could induce orthostatic hypotension (OH) in Parkinson's disease (PD) patients. Accurate prediction of acute OH post levodopa (AOHPL) is important for rational drug use in PD patients. Here, we develop and validate a prediction model of AOHPL to facilitate physicians in identifying patients at higher probability of developing AOHPL. METHODS: The study involved 497 PD inpatients who underwent a levodopa challenge test (LCT) and the supine-to-standing test (STS) four times during LCT. Patients were divided into two groups based on whether OH occurred during levodopa effectiveness (AOHPL) or not (non-AOHPL). The dataset was randomly split into training (80%) and independent test data (20%). Several models were trained and compared for discrimination between AOHPL and non-AOHPL. Final model was evaluated on independent test data. Shapley additive explanations (SHAP) values were employed to reveal how variables explain specific predictions for given observations in the independent test data. RESULTS: We included 180 PD patients without AOHPL and 194 PD patients with AOHPL to develop and validate predictive models. Random Forest was selected as our final model as its leave-one-out cross validation performance [AUC_ROC 0.776, accuracy 73.6%, sensitivity 71.6%, specificity 75.7%] outperformed other models. The most crucial features in this predictive model were the maximal SBP drop and DBP drop of STS before medication (ΔSBP/ΔDBP). We achieved a prediction accuracy of 72% on independent test data. ΔSBP, ΔDBP, and standing mean artery pressure were the top three variables that contributed most to the predictions across all individual observations in the independent test data. CONCLUSIONS: The validated classifier could serve as a valuable tool for clinicians, offering the probability of a patient developing AOHPL at an early stage. This supports clinical decision-making, potentially enhancing the quality of life for PD patients.

Specific Distribution of Digital Gait Biomarkers in Parkinson's Disease Using Body-Worn Sensors and Machine Learning.

Gait impairment leads to reduced social activities and low quality of life in people with Parkinson's disease (PD). PD is associated with unique gait signs and distributions of gait features. The assessment of gait characteristics is crucial in the diagnosis and treatment of PD. At present, the number and distribution of gait features associated with different PD stages are not clear. Here, we used whole-body multinode wearable devices combined with machine learning to build a classification model of early PD (EPD) and mild PD (MPD). Our model exhibited significantly improved accuracy for the EPD and MPD groups compared with the healthy control (HC) group (EPD vs HC accuracy = 0.88, kappa = 0.75, AUC = 0.88; MPD vs HC accuracy = 0.94, kappa = 0.84, AUC = 0.90). Furthermore, the distribution of gait features was distinguishable among the HC, EPD, and MPD groups (EPD based on variability features [40%]; MPD based on amplitude features [30%]). Here, we showed promising gait models for PD classification and provided reliable gait features for distinguishing different PD stages. Further multicenter clinical studies are needed to generalize the findings.

Remote scoring models of rigidity and postural stability of Parkinson's disease based on indirect motions and a low-cost RGB algorithm.

Background and objectives: The Movement Disorder Society's Unified Parkinson's Disease Rating Scale Part III (MDS-UPDRS III) is mostly common used for assessing the motor symptoms of Parkinson's disease (PD). In remote circumstances, vision-based techniques have many strengths over wearable sensors. However, rigidity (item 3.3) and postural stability (item 3.12) in the MDS-UPDRS III cannot be assessed remotely since participants need to be touched by a trained examiner during testing. We developed the four scoring models of rigidity of the neck, rigidity of the lower extremities, rigidity of the upper extremities, and postural stability based on features extracted from other available and touchless motions. Methods: The red, green, and blue (RGB) computer vision algorithm and machine learning were combined with other available motions from the MDS-UPDRS III evaluation. A total of 104 patients with PD were split into a train set (89 individuals) and a test set (15 individuals). The light gradient boosting machine (LightGBM) multiclassification model was trained. Weighted kappa (k), absolute accuracy (ACC ± 0), and Spearman's correlation coefficient (rho) were used to evaluate the performance of model. Results: For model of rigidity of the upper extremities, k = 0.58 (moderate), ACC ± 0 = 0.73, and rho = 0.64 (moderate). For model of rigidity of the lower extremities, k = 0.66 (substantial), ACC ± 0 = 0.70, and rho = 0.76 (strong). For model of rigidity of the neck, k = 0.60 (moderate), ACC ± 0 = 0.73, and rho = 0.60 (moderate). For model of postural stability, k = 0.66 (substantial), ACC ± 0 = 0.73, and rho = 0.68 (moderate). Conclusion: Our study can be meaningful for remote assessments, especially when people have to maintain social distance, e.g., in situations such as the coronavirus disease-2019 (COVID-19) pandemic.

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.

Early detection of Parkinson's disease from multiple signal speech: Based on Mandarin language dataset.

Parkinson's disease (PD) is a neurodegenerative disorder that negatively affects millions of people. Early detection is of vital importance. As recent researches showed dysarthria level provides good indicators to the computer-assisted diagnosis and remote monitoring of patients at the early stages. It is the goal of this study to develop an automatic detection method based on newest collected Chinese dataset. Unlike English, no agreement was reached on the main features indicating language disorders due to vocal organ dysfunction. Thus, one of our approaches is to classify the speech phonation and articulation with a machine learning-based feature selection model. Based on a relatively big sample, three feature selection algorithms (LASSO, mRMR, Relief-F) were tested to select the vocal features extracted from speech signals collected in a controlled setting, followed by four classifiers (Naïve Bayes, K-Nearest Neighbor, Logistic Regression and Stochastic Gradient Descent) to detect the disorder. The proposed approach shows an accuracy of 75.76%, sensitivity of 82.44%, specificity of 73.15% and precision of 76.57%, indicating the feasibility and promising future for an automatic and unobtrusive detection on Chinese PD. The comparison among the three selection algorithms reveals that LASSO selector has the best performance regardless types of vocal features. The best detection accuracy is obtained by SGD classifier, while the best resulting sensitivity is obtained by LR classifier. More interestingly, articulation features are more representative and indicative than phonation features among all the selection and classifying algorithms. The most prominent articulation features are F1, F2, DDF1, DDF2, BBE and MFCC.

MAO-B Polymorphism Associated with Progression in a Chinese Parkinson's Disease Cohort but Not in the PPMI Cohort.

Introduction: Genetic factors play an important role in Parkinson's disease (PD) risk. However, the genetic contribution to progression in Chinese PD patients has rarely been studied. This study investigated genetic associations with progression based on 30 PD risk loci common in a longitudinal cohort of Chinese PD patients and the Parkinson's Progression Markers Initiative (PPMI) cohort. Methods: PD patients from the true world (TW) Chinese PD longitudinal cohort and the PPMI cohort with demographic information and assessment scales were assessed. A panel containing 30 PD risk single nucleotide polymorphisms was tested. Progression rates of each scale were derived from random-effect slope values of mixed-effects regression models. Progression rates of multiple assessments were combined by using principal component analysis (PCA) to derive scores for composite, motor, and nonmotor progression. The association of genetic polymorphism and separate scales or PCA progression was analysed via linear regression. Results: In the Chinese PD cohort, MAOB rs1799836 was associated with progression based on the Montreal Cognitive Assessment, the top 3 principal components (PCs) of nonmotor PCA and PC1 of the composite PCA. In the PPMI cohort, both MDS-Unified Parkinson's Disease Rating Scale II and motor PC1 progression were associated with RIT2 rs12456492. The PARK16 haplotype was associated with Geriatric Depression Scale and the State-Trait Anxiety Inventory for Adults progression, and the SNCA haplotype was associated with the Hoehn-Yahr staging progression and motor PC1 progression. Ethnicity-stratified analysis showed that the association between MAOB rs1799836 and PD progression may be specific to Asian or Chinese patients. Conclusion: MAOB rs1799836 was associated with the progression of nonmotor symptoms, especially cognitive impairment, and the composite progression of motor and nonmotor symptoms within our Chinese PD cohort. The RIT2 rs12456492 and SNCA haplotypes were associated with motor function decline, and the PARK16 haplotype was associated with progression in mood in the PPMI cohort.

Recognition of Freezing of Gait in Parkinson's Disease Based on Machine Vision.

Background: Freezing of gait (FOG) is a common clinical manifestation of Parkinson's disease (PD), mostly occurring in the intermediate and advanced stages. FOG is likely to cause patients to fall, resulting in fractures, disabilities and even death. Currently, the pathogenesis of FOG is unclear, and FOG detection and screening methods have various defects, including subjectivity, inconvenience, and high cost. Due to limited public healthcare and transportation resources during the COVID-19 pandemic, there are greater inconveniences for PD patients who need diagnosis and treatment. Objective: A method was established to automatically recognize FOG in PD patients through videos taken by mobile phone, which is time-saving, labor-saving, and low-cost for daily use, which may overcome the above defects. In the future, PD patients can undergo FOG assessment at any time in the home rather than in the hospital. Methods: In this study, motion features were extracted from timed up and go (TUG) test and the narrow TUG (Narrow) test videos of 50 FOG-PD subjects through a machine learning method; then a motion recognition model to distinguish between walking and turning stages and a model to recognize FOG in these stages were constructed using the XGBoost algorithm. Finally, we combined these three models to form a multi-stage FOG recognition model. Results: We adopted the leave-one-subject-out (LOSO) method to evaluate model performance, and the multi-stage FOG recognition model achieved a sensitivity of 87.5% sensitivity and a specificity of 79.82%. Conclusion: A method to realize remote PD patient FOG recognition based on mobile phone video is presented in this paper. This method is convenient with high recognition accuracy and can be used to rapidly evaluate FOG in the home environment and remotely manage FOG-PD, or screen patients in large-scale communities.

Recognition of freezing of gait in Parkinson's disease based on combined wearable sensors.

Freezing of gait is a common gait disorder among patients with advanced Parkinson's disease and is associated with falls. This paper designed the relevant experimental procedures to obtain FoG signals from PD patients. Accelerometers, gyroscopes, and force sensing resistor sensors were placed on the lower body of patients. On this basis, the research on the optimal feature extraction method, sensor configuration, and feature quantity selection in the FoG detection process is carried out. Thirteen typical features consisting of time domain, frequency domain and statistical features were extracted from the sensor signals. Firstly, we used the analysis of variance (ANOVA) to select features through comparing the effectiveness of two feature selection methods. Secondly, we evaluated the detection effects with different combinations of sensors to get the best sensors configuration. Finally, we selected the optimal features to construct FoG recognition model based on random forest. After comprehensive consideration of factors such as detection performance, cost, and actual deployment requirements, the 35 features obtained from the left shank gyro and accelerometer, and 78.39% sensitivity, 91.66% specificity, 88.09% accuracy, 77.58% precision and 77.98% f-score were achieved. This objective FoG recognition method has high recognition accuracy, which will be helpful for early FoG symptoms screening and treatment.

Bilateral globus pallidus interna deep brain stimulation in Parkinson's disease: Therapeutic effects and motor outcomes prediction in a short-term follow up.

Objective: We aimed to compare the motor effect of bilateral globus pallidus interna (GPi) deep brain stimulation (DBS) on motor subtypes of Parkinson's disease (PD) patients and identify preoperative predictive factors of short-term motor outcome. Methods: We retrospectively investigated bilateral GPi DBS clinical outcomes in 55 PD patients in 1 year follow up. Motor outcome was measured by the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS) part III before and 1 year after surgery. Clinical outcomes were compared among different motor subtypes. Preoperative predictors of motor outcome were assessed by performing univariate and multivariate linear regression and logistic regression analyses. Results: At 1 year following implantation, GPi DBS significantly improved the off-medication MDS-UPDRS III scores in all motor subtype cohorts, with prominent improvement in tremor. No significant difference of postoperative motor symptoms changes was found except greater tremor improvement achieved in both the tremor-dominant (TD) and indeterminate (IND) patients compared to the postural instability and gait difficulty (PIGD) patients. High percentage of PIGD patients were weak responders to DBS. Better levodopa responsiveness and more severe tremor predicted greater overall improvement of motor function in the entire cohort. Similarly, both levodopa responsiveness and tremor improvement were confirmed as predictors for motor improvement in PIGD patients. Conclusion: Bilateral GPi DBS could effectively improve motor outcomes in PD patients regardless of motor subtypes. Both TD and IND patients obtained larger tremor improvement. The intensity of levodopa responsiveness and the severity of tremor could serve as predictors of motor improvement 1 year after GPi DBS.

Effects of Unilateral Stimulation in Parkinson's Disease: A Randomized Double-Blind Crossover Trial.

INTRODUCTION: Previous studies have shown that subthalamic nucleus (STN) and unilateral globus pallidus interna (GPi) are similarly effective in the deep brain stimulation (DBS) treatment of motor symptoms. However, the counterintuitively more common clinical application of STN DBS makes us hypothesize that STN is superior to GPi in the treatment of motor symptoms. METHODS: In this prospective, double-blind, randomized crossover study, idiopathic PD patients treated with combined unilateral STN and contralateral GPi DBS (STN in one brain hemisphere and GPi in the other) for 2 to 3 years were enrolled. The MDS UPDRS-III total score and subscale scores for axial and bilateral limb symptoms were assessed preoperatively and at 2- to 3-year follow-up in four randomized, double-blinded conditions: (1) Med-STN+GPi-, (2) Med-STN-GPi+, (3) Med+STN+GPi-, and (4) Med+STN-GPi+. RESULTS: Eight patients had completed 30 trials of assessment. Compared with the preoperative Med- state, in the Med-STN+GPi- condition, the cardinal symptoms in both sides of the body were all improved. In the Med-STN-GPi+ condition, symptoms of the GPi-stim limb were improved, while only tremor was improved on the ipsilateral side, although all axial symptoms showed aggravation. Compared with the preoperative Med+ state, in the Med+STN+GPi- state, cardinal symptoms were improved on both sides, except that tremor was worsened on the STN-stim side. In the Med+STN-GPi+ state, the overall motor symptoms were aggravated compared with the preoperative Med+ state. Most axial symptoms worsened at acute unilateral STN or GPi DBS onset, compared to both preoperative Med- and Med+ states. No side effects associated with this study were seen. CONCLUSIONS: Improvement in motor symptoms was greater in all sub-scores favoring STN. The effects of STN+ were seen on both sides of the body, while GPi+ mainly acted on the contralateral side.

Motor Progression in Early-Stage Parkinson's Disease: A Clinical Prediction Model and the Role of Cerebrospinal Fluid Biomarkers.

Background: The substantial heterogeneity of clinical symptoms and lack of reliable progression markers in Parkinson's disease (PD) present a major challenge in predicting accurate progression and prognoses. Increasing evidence indicates that each component of the neurovascular unit (NVU) and blood-brain barrier (BBB) disruption may take part in many neurodegenerative diseases. Since some portions of CSF are eliminated along the neurovascular unit and across the BBB, disturbing the pathways may result in changes of these substances. Methods: Four hundred seventy-four participants from the Parkinson's Progression Markers Initiative (PPMI) study (NCT01141023) were included in the study. Thirty-six initial features, including general information, brief clinical characteristics and the current year's classical scale scores, were used to build five regression models to predict PD motor progression represented by the coming year's Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part III score after redundancy removal and recursive feature elimination (RFE)-based feature selection. Then, a threshold range was added to the predicted value for more convenient model application. Finally, we evaluated the CSF and blood biomarkers' influence on the disease progression model. Results: Eight hundred forty-nine cases were included in the study. The adjusted R2 values of three different categories of regression model, linear, Bayesian and ensemble, all reached 0.75. Models of the same category shared similar feature combinations. The common features selected among the categories were the MDS-UPDRS Part III score, Montreal Cognitive Assessment (MOCA) and Rapid Eye Movement Sleep Behavior Disorder Questionnaire (RBDSQ) score. It can be seen more intuitively that the model can achieve certain prediction effect through threshold range. Biomarkers had no significant impact on the progression model within the data in the study. Conclusions: By using machine learning and routinely gathered assessments from the current year, we developed multiple dynamic models to predict the following year's motor progression in the early stage of PD. These methods will allow clinicians to tailor medical management to the individual and identify at-risk patients for future clinical trials examining disease-modifying therapies.