Towards Real-Time Prediction of Freezing of Gait in Patients With Parkinson’s Disease: Addressing the Class Imbalance Problem

Freezing of gait (FoG) is a common motor symptom in patients with Parkinson’s disease (PD). FoG impairs gait initiation and walking and increases fall risk. Intelligent external cueing systems implementing FoG detection algorithms have been developed to help patients recover gait after freezing. However, predicting FoG before its occurrence enables preemptive cueing and may prevent FoG. Such prediction remains challenging given the relative infrequency of freezing compared to non-freezing events. In this study, we investigated the ability of individual and ensemble classifiers to predict FoG. We also studied the effect of the ADAptive SYNthetic (ADASYN) sampling algorithm and classification cost on classifier performance. Eighteen PD patients performed a series of daily walking tasks wearing accelerometers on their ankles, with nine experiencing FoG. The ensemble classifier formed by Support Vector Machines, K-Nearest Neighbors, and Multi-Layer Perceptron using bagging techniques demonstrated highest performance (F1 = 90.7) when synthetic FoG samples were added to the training set and class cost was set as twice that of normal gait. The model identified 97.4% of the events, with 66.7% being predicted. This study demonstrates our algorithm’s potential for accurate prediction of gait events and the provision of preventive cueing in spite of limited event frequency.

Download Full-text

Abnormal Olfaction in Parkinson’s Disease Is Related to Faster Disease Progression

Behavioural Neurology ◽

10.1155/2015/976589 ◽

2015 ◽

Vol 2015 ◽

pp. 1-5 ◽

Cited By ~ 21

Author(s):

Sara Cavaco ◽

Alexandra Gonçalves ◽

Alexandre Mendes ◽

Nuno Vila-Chã ◽

Inês Moreira ◽

...

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Disease Progression ◽

Rating Scale ◽

Freezing Of Gait ◽

Motor Symptom ◽

Identification Test ◽

Disease Rating ◽

Abnormal Performance ◽

Smell Identification

Introduction. A possible association between olfactory dysfunction and Parkinson’s disease (PD) severity has been a topic of contention for the past 40 years. Conflicting reports may be partially explained by procedural differences in olfactory assessment and motor symptom evaluation.Methods. One hundred and sixty-six nondemented PD patients performed the Brief-Smell Identification Test and test scores below the estimated 20th percentile as a function of sex, age, and education (i.e., 80% specificity) were considered demographically abnormal. Patients underwent motor examination after 12 h without antiparkinsonian medication.Results. Eighty-two percent of PD patients had abnormal olfaction. Abnormal performance on the Brief-Smell Identification Test was associated with higher disease severity (i.e., Hoehn and Yahr, Unified Parkinson’s Disease Rating Scale-III, Freezing of Gait questionnaire, and levodopa equivalent dose), even when disease duration was taken into account.Conclusions. Abnormal olfaction in PD is associated with increased severity and faster disease progression.

Download Full-text

Hand Function as Predictor of Motor Symptom Severity in Individuals with Parkinson’s Disease

Gerontology ◽

10.1159/000511910 ◽

2021 ◽

pp. 1-8

Author(s):

Thiago da Silva Rocha Paz ◽

Vera Lúcia Santos de Britto ◽

Bruna Yamaguchi ◽

Vera Lúcia Israel ◽

Alessandra Swarowsky ◽

...

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Symptom Severity ◽

Rating Scale ◽

Handgrip Strength ◽

Statistical Significance ◽

Hand Function ◽

Freezing Of Gait ◽

Motor Symptom ◽

Cross Sectional

Introduction: Parkinson’s disease (PD) leads to deficits in upper limb strength and manual dexterity and consequently resulting in functional impairment. Handgrip strength is correlated with the motor symptom severity of the disease, but there is a gap in the literature about the influence of freezing in PD patients. Objective: The objective is to study the correlation between handgrip strength and motor symptom severity considering the freezing phenomenon and to verify variables that can predict Unified Parkinson’s Disease Rating Scale (UPDRS) III. Methods: This is a multicenter cross-sectional study in PD. 101 patients were divided into 2 groups: freezing of gait (FOG) (n = 51) and nonfreezing (nFOG) (n = 52). Freezing of Gait Questionnaire (FOGQ); UPDRS II and III sections; Hoehn and Yahr (HY) scale; handgrip dynamometry (HD); 9 Hole Peg Test (9-HPT) were assessed. Results: In both groups, HD was correlated to UPDRS III (nFOG: −0.308; FOG: −0.301), UPDRS total (nFOG: −0.379; FOG: −0.368), UPDRS item 23 (nFOG: −0.404; FOG: −0.605), and UPDRS item 24 (nFOG: −0.405; FOG: −0.515). For the correlation to UPDRS II (0.320) and 9-HPT (−0.323), only nFOG group presented significance. For the UPDRS 25 (−0.437), only FOG group presented statistical significance. The UPDRS III can be predicted by 9-HPT, age, and HY in nFOG patients (Adjusted R2 = 0.416). In FOG group, UPDRS III can be predicted by HD, 9-HPT, age, and HY (Adjusted R2 = 0.491). Conclusion: Handgrip strength showed to be predictive of motor impairment only in the FOG group. Our results showed clinical profile differences of motor symptoms considering freezers and nonfreezers with PD.

Download Full-text

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

Frontiers in Neurology ◽

10.3389/fneur.2021.720516 ◽

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>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.

Download Full-text

Effects of Gait Inducing Assist for Patients with Parkinson’s Disease on Double Support Phase During Gait

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2020.p0798 ◽

2020 ◽

Vol 32 (4) ◽

pp. 798-811

Author(s):

Ai Higuchi ◽

Junichiro Shiraishi ◽

Yuichi Kurita ◽

Tomohiro Shibata ◽

◽

...

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Freezing Of Gait ◽

Step Length ◽

Motor Symptom ◽

Elderly Subjects ◽

Healthy Elderly ◽

Wide Range ◽

Healthy Elderly Subjects ◽

Support Phase

Parkinson’s disease (PD) is a common progressive neurodegenerative disease that affects a wide range of motor and non-motor symptoms. Freezing of gait (FOG) is such a motor symptom of PD that frequently results in falling, and almost half of PD patients suffer from FOG. In this study, we investigated the effectiveness of a robotic assistance system called UPS-PD, which was developed to suppress FOG. The double limb support phase (DLS) in a 10-m straight-line walking task, the gait time and step counts were measured in five PD subjects. In addition, the safety of the UPS-PD in a healthy person was investigated using OpenSim, and the DLS parameters in four healthy elderly subjects were evaluated. In the experiment with the PD patients, the DLS parameters of two subjects showed an improvement. Furthermore, the step length of one subject and the step length and walking speed of the other subject were improved. Moreover, there were no problems in terms of instability of gait in both the PD patients. The UPS-PD did not adversely affect the gait of healthy elderly subjects and the walking of a healthy subject model in the simulation. Therefore, the UPS-PD is considered to be a useful device for improving walking in PD patients.

Download Full-text

Relationship between Freezing of Gait and Anxiety in Parkinson’s Disease Patients: A Systemic Literature Review

Parkinson s Disease ◽

10.1155/2019/6836082 ◽

2019 ◽

Vol 2019 ◽

pp. 1-24 ◽

Cited By ~ 2

Author(s):

Ivan Witt ◽

Hooman Ganjavi ◽

Penny MacDonald

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Literature Review ◽

Outcome Measures ◽

English Language ◽

Case Reports ◽

Freezing Of Gait ◽

Anxiety Reduction ◽

Motor Symptom ◽

Number Of Patients

Freezing of gait (FOG) is experienced by a significant number of patients with Parkinson’s disease (PD). The pathophysiology of this disabling motor symptom remains unclear, and there are no effective therapies. Anxiety has previously been posited as a contributing factor to gait freezing. There have been few studies directly investigating this topic, and a comprehensive literature review is lacking. The objective of this paper was to systematically review the evidence associating anxiety with the presence, severity, and progression of FOG in PD patients. The PubMed, EMBASE, and PsycINFO databases were searched up to September 19, 2018, for English-language, peer-reviewed articles that explored anxiety and FOG as outcome measures in a PD population base. Review articles, case reports, and articles that assessed gait disorders other than FOG were excluded, yielding a total of 26 articles in the final analysis. Of these 26 studies, 16 had a significant relationship between anxiety outcome measure and either presence or severity of FOG. There was great variability among studies in terms of outcome measures for both FOG and anxiety. Despite this heterogeneity, most studies relate anxiety and FOG. Standardized, high-validity outcome measures of anxiety and FOG are needed. Future exploration should aim to clarify the role of anxiety in FOG as a causal factor, pathophysiological marker, and manifestation of a common pathophysiological process versus a consequence of FOG itself. Clarifying the relationship between anxiety and FOG could reveal anxiety reduction as a therapy for FOG.

Download Full-text