scholarly journals Predicting Axial Impairment in Parkinson’s Disease through a Single Inertial Sensor

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 412
Author(s):  
Luigi Borzì ◽  
Ivan Mazzetta ◽  
Alessandro Zampogna ◽  
Antonio Suppa ◽  
Fernanda Irrera ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Regression Model ◽  
Support Vector Regression ◽  
Regression Models ◽  
Inertial Sensor ◽  
Measurement Unit ◽  
Support Vector ◽  
Model Parameters ◽  
The Impact

Background: Current telemedicine approaches lack standardised procedures for the remote assessment of axial impairment in Parkinson’s disease (PD). Unobtrusive wearable sensors may be a feasible tool to provide clinicians with practical medical indices reflecting axial dysfunction in PD. This study aims to predict the postural instability/gait difficulty (PIGD) score in PD patients by monitoring gait through a single inertial measurement unit (IMU) and machine-learning algorithms. Methods: Thirty-one PD patients underwent a 7-m timed-up-and-go test while monitored through an IMU placed on the thigh, both under (ON) and not under (OFF) dopaminergic therapy. After pre-processing procedures and feature selection, a support vector regression model was implemented to predict PIGD scores and to investigate the impact of L-Dopa and freezing of gait (FOG) on regression models. Results: Specific time- and frequency-domain features correlated with PIGD scores. After optimizing the dimensionality reduction methods and the model parameters, regression algorithms demonstrated different performance in the PIGD prediction in patients OFF and ON therapy (r = 0.79 and 0.75 and RMSE = 0.19 and 0.20, respectively). Similarly, regression models showed different performances in the PIGD prediction, in patients with FOG, ON and OFF therapy (r = 0.71 and RMSE = 0.27; r = 0.83 and RMSE = 0.22, respectively) and in those without FOG, ON and OFF therapy (r = 0.85 and RMSE = 0.19; r = 0.79 and RMSE = 0.21, respectively). Conclusions: Optimized support vector regression models have high feasibility in predicting PIGD scores in PD. L-Dopa and FOG affect regression model performances. Overall, a single inertial sensor may help to remotely assess axial motor impairment in PD patients.

scholarly journals Discrimination between healthy and patients with Parkinson’s disease from hand resting activity using inertial measurement unit

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Luciano Brinck Peres ◽  
Bruno Coelho Calil ◽  
Ana Paula Sousa Paixão Barroso da Silva ◽  
Valdeci Carlos Dionísio ◽  
Marcus Fraga Vieira ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Inertial Sensor ◽  
Correct Diagnosis ◽  
Measurement Unit ◽  
Support Vector ◽  
Svm Classifier ◽  
Muscle Rigidity ◽  
K Nearest Neighbor ◽  
Precision And Accuracy

Abstract Background Parkinson’s disease (PD) is a neurological disease that affects the motor system. The associated motor symptoms are muscle rigidity or stiffness, bradykinesia, tremors, and gait disturbances. The correct diagnosis, especially in the initial stages, is fundamental to the life quality of the individual with PD. However, the methods used for diagnosis of PD are still based on subjective criteria. As a result, the objective of this study is the proposal of a method for the discrimination of individuals with PD (in the initial stages of the disease) from healthy groups, based on the inertial sensor recordings. Methods A total of 27 participants were selected, 15 individuals previously diagnosed with PD and 12 healthy individuals. The data collection was performed using inertial sensors (positioned on the back of the hand and on the back of the forearm). Different numbers of features were used to compare the values of sensitivity, specificity, precision, and accuracy of the classifiers. For group classification, 4 classifiers were used and compared, those being [Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Naive Bayes (NB)]. Results When all individuals with PD were analyzed, the best performance for sensitivity and accuracy (0.875 and 0.800, respectively) was found in the SVM classifier, fed with 20% and 10% of the features, respectively, while the best performance for specificity and precision (0.933 and 0.917, respectively) was associated with the RF classifier fed with 20% of all the features. When only individuals with PD and score 1 on the Hoehn and Yahr scale (HY) were analyzed, the best performances for sensitivity, precision and accuracy (0.933, 0.778 and 0.848, respectively) were from the SVM classifier, fed with 40% of all features, and the best result for precision (0.800) was connected to the NB classifier, fed with 20% of all features. Conclusion Through an analysis of all individuals in this study with PD, the best classifier for the detection of PD (sensitivity) was the SVM fed with 20% of the features and the best classifier for ruling out PD (specificity) was the RF classifier fed with 20% of the features. When analyzing individuals with PD and score HY = 1, the SVM classifier was superior across the sensitivity, precision, and accuracy, and the NB classifier was superior in the specificity. The obtained result indicates that objective methods can be applied to help in the evaluation of PD.

scholarly journals Regression Cloud Models and Their Applications in Energy Consumption of Data Center

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Yanshuang Zhou ◽  
Na Li ◽  
Hong Li ◽  
Yongqiang Zhang
Keyword(s):  
Linear Regression ◽  
Regression Model ◽  
Support Vector Regression ◽  
Nonlinear Regression ◽  
Regression Models ◽  
Energy Model ◽  
Support Vector ◽  
Support Vector Regression Model ◽  
Performance Counters ◽  
System Utilization

As cloud data center consumes more and more energy, both researchers and engineers aim to minimize energy consumption while keeping its services available. A good energy model can reflect the relationships between running tasks and the energy consumed by hardware and can be further used to schedule tasks for saving energy. In this paper, we analyzed linear and nonlinear regression energy model based on performance counters and system utilization and proposed a support vector regression energy model. For performance counters, we gave a general linear regression framework and compared three linear regression models. For system utilization, we compared our support vector regression model with linear regression and three nonlinear regression models. The experiments show that linear regression model is good enough to model performance counters, nonlinear regression is better than linear regression model for modeling system utilization, and support vector regression model is better than polynomial and exponential regression models.

scholarly journals Assessment of Functional Activities in Individuals with Parkinson’s Disease Using a Simple and Reliable Smartphone-Based Procedure

2020 ◽  
Vol 17 (11) ◽  
pp. 4123
Author(s):  
Pilar Serra-Añó ◽  
José Francisco Pedrero-Sánchez ◽  
Marta Inglés ◽  
Marta Aguilar-Rodríguez ◽  
Ismael Vargas-Villanueva ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Reaction Time ◽  
Postural Control ◽  
Neurodegenerative Disorder ◽  
Measurement Unit ◽  
Functional Activities ◽  
Sit To Stand ◽  
Study Participants ◽  
The Impact

Parkinson’s disease (PD) is a progressive neurodegenerative disorder leading to functional impairment. In order to monitor the progression of the disease and to implement individualized therapeutic approaches, functional assessments are paramount. The aim of this study was to determine the impact of PD on balance, gait, turn-to-sit and sit-to-stand by means of a single short-duration reliable test using a single inertial measurement unit embedded in a smartphone device. Study participants included 29 individuals with mild-to moderate PD (PG) and 31 age-matched healthy counterparts (CG). Functional assessment with FallSkip® included postural control (i.e., Medial-Lateral (ML) and Anterior-Posterior (AP) displacements), gait (Vertical (V) and Medial-Lateral (ML) ranges), turn-to-sit (time) and sit-to-stand (power) tests, total time and gait reaction time. Our results disclosed a reliable procedure (intra-class correlation coefficient (ICC) = 0.58–0.92). PG displayed significantly larger ML and AP displacements during the postural test, a decrease in ML range while walking and a longer time needed to perform the turn-to-sit task than CG (p < 0.05). No differences between groups were found for V range, sit-to-stand test, total time and reaction time (p > 0.05). In conclusion, people with mild-to-moderate PD exhibit impaired postural control, altered gait strategy and slower turn-to-sit performance than age-matched healthy people.

scholarly journals Real-Time Detection of Freezing Motions in Parkinson's Patients for Adaptive Gait Phase Synchronous Cueing

2021 ◽  
Vol 12 ◽  
Author(s):  
Ardit Dvorani ◽  
Vivian Waldheim ◽  
Magdalena C. E. Jochner ◽  
Christina Salchow-Hömmen ◽  
Jonas Meyer-Ohle ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Prediction Models ◽  
Inertial Sensor ◽  
Freezing Of Gait ◽  
Area Under The Curve ◽  
Support Vector ◽  
Average Performance ◽  
Gait Phase ◽  
Fog Detection

Parkinson's disease is the second most common neurodegenerative disease worldwide reducing cognitive and motoric abilities of affected persons. Freezing of Gait (FoG) is one of the severe symptoms that is observed in the late stages of the disease and considerably impairs the mobility of the person and raises the risk of falls. Due to the pathology and heterogeneity of the Parkinsonian gait cycle, especially in the case of freezing episodes, the detection of the gait phases with wearables is challenging in Parkinson's disease. This is addressed by introducing a state-automaton-based algorithm for the detection of the foot's motion phases using a shoe-placed inertial sensor. Machine-learning-based methods are investigated to classify the actual motion phase as normal or FoG-affected and to predict the outcome for the next motion phase. For this purpose, spatio-temporal gait and signal parameters are determined from the segmented movement phases. In this context, inertial sensor fusion is applied to the foot's 3D acceleration and rate of turn. Support Vector Machine (SVM) and AdaBoost classifiers have been trained on the data of 16 Parkinson's patients who had shown FoG episodes during a clinical freezing-provoking assessment course. Two clinical experts rated the video-recorded trials and marked episodes with festination, shank trembling, shuffling, or akinesia. Motion phases inside such episodes were labeled as FoG-affected. The classifiers were evaluated using leave-one-patient-out cross-validation. No statistically significant differences could be observed between the different classifiers for FoG detection (p&gt;0.05). An SVM model with 10 features of the actual and two preceding motion phases achieved the highest average performance with 88.5 ± 5.8% sensitivity, 83.3 ± 17.1% specificity, and 92.8 ± 5.9% Area Under the Curve (AUC). The performance of predicting the behavior of the next motion phase was significantly lower compared to the detection classifiers. No statistically significant differences were found between all prediction models. An SVM-predictor with features from the two preceding motion phases had with 81.6 ± 7.7% sensitivity, 70.3 ± 18.4% specificity, and 82.8 ± 7.1% AUC the best average performance. The developed methods enable motion-phase-based FoG detection and prediction and can be utilized for closed-loop systems that provide on-demand gait-phase-synchronous cueing to mitigate FoG symptoms and to prevent complete motoric blockades.

scholarly journals The Data-Driven Multi-Step Approach for Dynamic Estimation of Buildings’ Interior Temperature

Energies ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 6654
Author(s):  
Stefano Villa ◽  
Claudio Sassanelli
Keyword(s):  
Machine Learning ◽  
Regression Model ◽  
Support Vector Regression ◽  
Regression Models ◽  
Absolute Error ◽  
Data Driven ◽  
Support Vector ◽  
Support Vector Regression Model ◽  
Prediction Horizon ◽  
Dynamic Estimation

Buildings are among the main protagonists of the world’s growing energy consumption, employing up to 45%. Wide efforts have been directed to improve energy saving and reduce environmental impacts to attempt to address the objectives fixed by policymakers in the past years. Meanwhile, new approaches using Machine Learning regression models surged in the modeling and simulation research context. This research develops and proposes an innovative data-driven black box predictive model for estimating in a dynamic way the interior temperature of a building. Therefore, the rationale behind the approach has been chosen based on two steps. First, an investigation of the extant literature on the methods to be considered for tests has been conducted, shrinking the field of investigation to non-recursive multi-step approaches. Second, the results obtained on a pilot case using various Machine Learning regression models in the multi-step approach have been assessed, leading to the choice of the Support Vector Regression model. The prediction mean absolute error on the pilot case is 0.1 ± 0.2 °C when the offset from the prediction instant is 15 min and grows slowly for further future instants, up to 0.3 ± 0.8 °C for a prediction horizon of 8 h. In the end, the advantages and limitations of the new data-driven multi-step approach based on the Support Vector Regression model are provided. Relying only on data related to external weather, interior temperature and calendar, the proposed approach is promising to be applicable to any type of building without needing as input specific geometrical/physical characteristics.

NO-REFERENCE VIDEO QUALITY MEASUREMENT WITH SUPPORT VECTOR REGRESSION

2009 ◽  
Vol 19 (06) ◽  
pp. 457-464 ◽  
Author(s):  
HUICHENG LIAN
Keyword(s):  
Regression Model ◽  
Support Vector Regression ◽  
Regression Models ◽  
Video Quality ◽  
Quality Measurement ◽  
Extraction Methods ◽  
Support Vector ◽  
Support Vector Regression Model ◽  
Novel Approach

A novel approach for no-reference video quality measurement is proposed in this paper. Firstly, various feature extraction methods are used to quantify the quality of videos. Then, a support vector regression model is trained and adopted to predict unseen samples. Six different regression models are compared with the support vector regression model. The experimental results indicate that the combination of different video quality features with a support vector regression model can outperform other methods for no-reference video quality measurement significantly.

scholarly journals A Container-Attachable Inertial Sensor for Real-Time Hydration Tracking

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 4008 ◽  
Author(s):  
Henry Griffith ◽  
Yan Shi ◽  
Subir Biswas
Keyword(s):  
Regression Models ◽  
Large Scale ◽  
Inertial Sensors ◽  
Mutual Influence ◽  
Inertial Sensor ◽  
Measurement Unit ◽  
Percentage Error ◽  
Support Vector ◽  
Accelerometer Sensor ◽  
Fill Level

Various sensors have been proposed to address the negative health ramifications of inadequate fluid consumption. Amongst these solutions, motion-based sensors estimate fluid intake using the characteristics of drinking kinematics. This sensing approach is complicated due to the mutual influence of both the drink volume and the current fill level on the resulting motion pattern, along with differences in biomechanics across individuals. While motion-based strategies are a promising approach due to the proliferation of inertial sensors, previous studies have been characterized by limited accuracy and substantial variability in performance across subjects. This research seeks to address these limitations for a container-attachable triaxial accelerometer sensor. Drink volume is computed using support vector machine regression models with hand-engineered features describing the container’s estimated inclination. Results are presented for a large-scale data collection consisting of 1908 drinks consumed from a refillable bottle by 84 individuals. Per-drink mean absolute percentage error is reduced by 11.05% versus previous state-of-the-art results for a single wrist-wearable inertial measurement unit (IMU) sensor assessed using a similar experimental protocol. Estimates of aggregate consumption are also improved versus previously reported results for an attachable sensor architecture. An alternative tracking approach using the fill level from which a drink is consumed is also explored herein. Fill level regression models are shown to exhibit improved accuracy and reduced inter-subject variability versus volume estimators. A technique for segmenting the entire drink motion sequence into transport and sip phases is also assessed, along with a multi-target framework for addressing the known interdependence of volume and fill level on the resulting drink motion signature.

scholarly journals Facial tremor in patients with Parkinson’s disease: prevalence, determinants and impacts on disease progression

BMC Neurology ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Ruwei Ou ◽  
Qianqian Wei ◽  
Yanbing Hou ◽  
Lingyu Zhang ◽  
Kuncheng Liu ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Progression ◽  
Regression Models ◽  
Disease Duration ◽  
Rating Scale ◽  
Cox Regression ◽  
Binary Logistic Regression Analysis ◽  
Initial Symptom ◽  
The Impact

Abstract Background Facial (lip and jaw) tremor (FT) is associated with Parkinson’s disease (PD) but few studies have been conducted to explore its clinical profile. We performed this study to investigate the prevalence and clinical correlates of FT in PD, and further to evaluate its effect on disease progression. Methods A retrospective, cross-sectional (n = 2224) and longitudinal (n = 674) study was conducted. The presence of FT was based on a ≥ 1 score in the United PD Rating Scale (UPDRS) item 20A. Group comparisons were conducted, followed by a forward binary logistic regression analysis. Inverse probability of treatment weighting (IPTW) based on the propensity score and weighted or unweighted Cox regression models were used to explore the impact of FT on five clinical milestones including death, UPDRS III 11-point increase, Hoehn and Yahr (H&Y) stage reaching 3, dyskinesia development, and Montreal Cognitive Assessment 3-point decrease. Results FT was presented in 403 patients (18.1%), which showed increasing trends with disease duration and H&Y score. Age (P < 0.001), female (P < 0.001), disease duration (P = 0.001), speech (P = 0.011), rigidity (P = 0.026), rest tremor on limbs (P < 0.001), kinetic tremor on hands (P < 0.001), and axial symptoms (P = 0.013) were independent factors associated with FT. Both unweighted and weighted Cox regression models indicated that baseline FT and FT as the initial symptom were not associated with the five outcomes. Conclusions Our study suggested that FT was not uncommon and provided a deeper insight into the characteristics of FT in PD. The predict value of FT on long-term progronis of PD may need future longer follwe-up study.

Coexistent Osteoarthritis and Parkinson’s Disease: Data from the Parkinson’s Foundation Outcomes Project

2020 ◽  
Vol 10 (4) ◽  
pp. 1601-1610
Author(s):  
Jaimie A. Roper ◽  
Abigail C. Schmitt ◽  
Hanzhi Gao ◽  
Ying He ◽  
Samuel Wu ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Study Data ◽  
Functional Mobility ◽  
Quality Improvement Initiative ◽  
Timed Up And Go ◽  
Mobility Performance ◽  
Risk Of Mortality ◽  
The Impact

Background: The impact of concurrent osteoarthritis on mobility and mortality in individuals with Parkinson’s disease is unknown. Objective: We sought to understand to what extent osteoarthritis severity influenced mobility across time and how osteoarthritis severity could affect mortality in individuals with Parkinson’s disease. Methods: In a retrospective observational longitudinal study, data from the Parkinson’s Foundation Quality Improvement Initiative was analyzed. We included 2,274 persons with Parkinson’s disease. The main outcomes were the effects of osteoarthritis severity on functional mobility and mortality. The Timed Up and Go test measured functional mobility performance. Mortality was measured as the osteoarthritis group effect on survival time in years. Results: More individuals with symptomatic osteoarthritis reported at least monthly falls compared to the other groups (14.5% vs. 7.2% without reported osteoarthritis and 8.4% asymptomatic/minimal osteoarthritis, p = 0.0004). The symptomatic group contained significantly more individuals with low functional mobility (TUG≥12 seconds) at baseline (51.5% vs. 29.0% and 36.1%, p < 0.0001). The odds of having low functional mobility for individuals with symptomatic osteoarthritis was 1.63 times compared to those without reported osteoarthritis (p < 0.0004); and was 1.57 times compared to those with asymptomatic/minimal osteoarthritis (p = 0.0026) after controlling pre-specified covariates. Similar results hold at the time of follow-up while changes in functional mobility were not significant across groups, suggesting that osteoarthritis likely does not accelerate the changes in functional mobility across time. Coexisting symptomatic osteoarthritis and Parkinson’s disease seem to additively increase the risk of mortality (p = 0.007). Conclusion: Our results highlight the impact and potential additive effects of symptomatic osteoarthritis in persons with Parkinson’s disease.

A New Series Of 1,3-Dimethylxanthine Based Adenosine A2a Receptor Antagonists As A Non-Dopaminergic Treatment Of Parkinson’s Disease

2020 ◽  
Vol 17 ◽  
Author(s):  
Suman Rohilla ◽  
Ranju Bansal ◽  
Puneet Chauhan ◽  
Sonja Kachler ◽  
Karl-Norbert Klotz
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Molecular Docking ◽  
Binding Affinity ◽  
Docking Studies ◽  
Binding Modes ◽  
Molecular Docking Studies ◽  
In Silico Docking ◽  
Adenosine A2a Receptor Antagonists ◽  
The Impact

Background: Adenosine receptors (AR) have emerged as competent and innovative nondopaminergic targets for the development of potential drug candidates and thus constitute an effective and safer treatment approach for Parkinson’s disease (PD). Xanthine derivatives are considered as potential candidates for the treatment Parkinson’s disease due to their potent A2A AR antagonistic properties. Objective: The objectives of the work are to study the impact of substituting N7-position of 8-m/pchloropropoxyphenylxanthine structure on in vitro binding affinity of compounds with various AR subtypes, in vivo antiparkinsonian activity and binding modes of newly synthesized xanthines with A2A AR in molecular docking studies. Methods: Several new 7-substituted 8-m/p-chloropropoxyphenylxanthine analogues have been prepared. Adenosine receptor binding assays were performed to study the binding interactions with various subtypes and perphenazine induced rat catatonia model was used for antiparkinsonian activity. Molecular docking studies were performed using Schrödinger molecular modeling interface. Results: 8-para-substituted xanthine 9b bearing an N7-propyl substituent displayed the highest affinity towards A2A AR (Ki = 0.75 µM) with moderate selectivity versus other AR subtypes. 7-Propargyl analogue 9d produced significantly longlasting antiparkinsonian effects and also produced potent and selective binding affinity towards A2A AR. In silico docking studies further highlighted the crucial structural components required to develop xanthine derived potential A2A AR ligands as antiparkinsonian agents. Conclusion: A new series of 7-substituted 8-m/p-chloropropoxyphenylxanthines having good affinity for A2A AR and potent antiparkinsonian activity has been developed.

Sign in / Sign up

Export Citation Format

Share Document