scholarly journals Constructing Prediction Models for Freezing of Gait by Nomogram and Machine Learning: A Longitudinal Study

2021 ◽  
Vol 12 ◽  
Author(s):  
Kun Xu ◽  
Xiao-xia Zhou ◽  
Run-cheng He ◽  
Zhou Zhou ◽  
Zhen-hua Liu ◽  
...  
Keyword(s):  
Risk Factors ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Longitudinal Study ◽  
Prediction Models ◽  
Cox Regression ◽  
Freezing Of Gait ◽  
Training Set ◽  
Test Set ◽  
Clinical Measurements

Objectives: Although risk factors for freezing of gait (FOG) have been reported, there are still few prediction models based on cohorts that predict FOG. This 1-year longitudinal study was aimed to identify the clinical measurements closely linked with FOG in Chinese patients with Parkinson's disease (PD) and construct prediction models based on those clinical measurements using Cox regression and machine learning.Methods: The study enrolled 967 PD patients without FOG in the Hoehn and Yahr (H&Y) stage 1–3 at baseline. The development of FOG during follow-up was the end-point. Neurologists trained in movement disorders collected information from the patients on a PD medication regimen and their clinical characteristics. The cohort was assessed on the same clinical scales, and the baseline characteristics were recorded and compared. After the patients were divided into the training set and test set by the stratified random sampling method, prediction models were constructed using Cox regression and random forests (RF).Results: At the end of the study, 26.4% (255/967) of the patients suffered from FOG. Patients with FOG had significantly longer disease duration, greater age at baseline and H&Y stage, lower proportion in Tremor Dominant (TD) subtype, a higher proportion in wearing-off, levodopa equivalent daily dosage (LEDD), usage of L-Dopa and catechol-O-methyltransferase (COMT) inhibitors, a higher score in scales of Unified Parkinson's Disease Rate Scale (UPDRS), 39-item Parkinson's Disease Questionnaire (PDQ-39), Non-Motor Symptoms Scale (NMSS), Hamilton Depression Rating Scale (HDRS)-17, Parkinson's Fatigue Scale (PFS), rapid eye movement sleep behavior disorder questionnaire-Hong Kong (RBDQ-HK), Epworth Sleepiness Scale (ESS), and a lower score in scales of Parkinson's Disease Sleep Scale (PDSS) (P < 0.05). The risk factors associated with FOG included PD onset not being under the age of 50 years, a lower degree of tremor symptom, impaired activities of daily living (ADL), UPDRS item 30 posture instability, unexplained weight loss, and a higher degree of fatigue. The concordance index (C-index) was 0.68 for the training set (for internal validation) and 0.71 for the test set (for external validation) of the nomogram prediction model, which showed a good predictive ability for patients in different survival times. The RF model also performed well, the C-index was 0.74 for the test set, and the AUC was 0.74.Conclusions: The study found some new risk factors associated with the FOG including a lower degree of tremor symptom, unexplained weight loss, and a higher degree of fatigue through a longitudinal study, and constructed relatively acceptable prediction models.

The Relative Contribution of Physical and Cognitive Fall Risk Factors in People With Parkinson’s Disease

2013 ◽  
Vol 28 (3) ◽  
pp. 282-290 ◽  
Author(s):  
Serene S. Paul ◽  
Catherine Sherrington ◽  
Colleen G. Canning ◽  
Victor S. C. Fung ◽  
Jacqueline C. T. Close ◽  
...  
Keyword(s):  
Risk Factors ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Muscle Strength ◽  
Fall Prevention ◽  
Fall Risk ◽  
Freezing Of Gait ◽  
Prevention Strategies ◽  
Relative Contribution ◽  
Leg Muscle

Background. In order to develop multifaceted fall prevention strategies for people with Parkinson’s disease (PD), greater understanding of the impact of physical and cognitive performance on falls is required. Objective. We aimed to identify the relative contribution of a comprehensive range of physical and cognitive risk factors to prospectively-measured falls in a large sample of people with PD and develop an explanatory multivariate fall risk model in this group. Methods. Measures of PD signs and symptoms, freezing of gait, balance, mobility, proprioception, leg muscle strength, and cognition were collected on 205 community-dwelling people with PD. Falls were monitored prospectively for 6 months using falls diaries. Results. A total of 120 participants (59%) fell during follow-up. Freezing of gait ( P < .001), dyskinesia ( P = .02), impaired anticipatory and reactive balance ( P < .001), impaired cognition ( P = .002), reduced leg muscle strength ( P = .006), and reduced proprioception ( P = .04) were significantly associated with future falls in univariate analyses. Freezing of gait (risk ratio [RR] = 1.03, 95% confidence interval [CI] = 1.00-1.05, P = .02), impaired anticipatory (RR = 1.01, 95% CI = 1.00-1.02, P = .03) and reactive (RR = 1.26, 95% CI = 1.01-1.58, P = .04) balance, and impaired orientation (RR = 1.28, 95% CI = 1.01-1.62, P = .04) maintained significant associations with falls in multivariate analysis. Conclusion. The study findings elucidate important physical and cognitive determinants of falls in people with PD and may assist in developing efficacious fall prevention strategies for this high-risk group.

scholarly journals Predicting the onset of freezing of gait in de novo Parkinson’s disease

2021 ◽  
Author(s):  
Fengting Wang ◽  
Yixin Pan ◽  
Miao Zhang ◽  
Kejia Hu
Keyword(s):  
Risk Factors ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
De Novo ◽  
Freezing Of Gait ◽  
Poor Quality ◽  
Csf Biomarkers ◽  
Genetic Characteristics ◽  
Progression Markers ◽  
Independent Risk Factors

AbstractFreezing of gait (FoG) is a debilitating symptom of Parkinson’s disease (PD) related to higher risks of falls and poor quality of life. In this study, we predicted the onset of FoG in PD patients using a battery of risk factors from patients enrolled in the Parkinson’s Progression Markers Initiative (PPMI) cohort. The endpoint was the presence of FoG, which was assessed every year during the five-year follow-up visit. Overall, 212 PD patients were included in analysis. Seventy patients (33.0%) developed FoG during the visit (pre-FoG group). Age, bradykinesia, TD/PIGD classification, fatigue, cognitive impairment, impaired autonomic functions and sleep disorder were found to be significantly different in patients from pre-FoG and non-FoG groups at baseline. The logistic regression model showed that motor factors such as TD/PIGD classification (OR = 2.67, 95% CI = 1.41-5.09), MDS-UPDRS part III score (OR = 1.05, 95% CI = 1.01-1.09) were associated with FoG occurrence. Several indicators representing non-motor symptoms such as SDMT total score (OR = 0.95, 95% CI = 0.91-0.98), HVLT immediate/Total recall (OR = 0.91, 95% CI = 0.86-0.97), MOCA (OR = 0.87, 95% CI = 0.76-0.99), Epworth Sleepiness Scale (OR = 1.13, 95% CI = 1.03-1.24), fatigue(OR = 1.98, 95% CI = 1.32-3.06), SCOPA-AUT gastrointestinal score (OR = 1.27, 95% CI = 1.09-1.49) and SCOPA-AUT urinary score (OR = 1.18, 95% CI = 1.06-1.32) were found to have the predictive value. PD patients that developed FoG showed a significant reduction of DAT uptake in the striatum. However, no difference at baseline was observed in genetic characteristics and CSF biomarkers between the two patient sets. Our model indicated that TD/PIGD classification, MDS-UPDRS total score, and Symbol Digit Modalities score were independent risk factors for the onset of FoG in PD patients. In conclusion, the combination of motor and non-motor features including the akinetic subtype and poor cognitive functions should be considered in identifying PD patients with high risks of FoG onset.

scholarly journals Longitudinal Risk Factor for Developing Depression in Parkinson's Disease

2021 ◽  
Author(s):  
Tarek Eid Antar ◽  
Huw R Morris ◽  
Faraz Faghri ◽  
Hampton Leonard ◽  
Mike Nalls ◽  
...  
Keyword(s):  
Risk Factors ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Depressive Symptoms ◽  
Regression Model ◽  
Cox Regression ◽  
Disease Patient ◽  
Daily Activities ◽  
Cox Regression Model ◽  
Antidepressant Use

Background Despite the established importance of identifying depression in Parkinson's disease, our understanding of the factors which place the Parkinson's disease patient at future risk of depression is limited. Methods Our sample consisted of 874 patients from two longitudinal cohorts, PPMI and PDBP, with median follow-up durations of 7 and 3 years respectively. Risk factors for depression at baseline were determined using logistic regression. A Cox regression model was then used to identify baseline factors that predisposed the non-depressed patient to develop depressive symptoms that were sustained for at least one year, while adjusting for antidepressant use and cognitive impairment. Common predictors between the two cohorts were identified with a random-effects meta-analysis. Results We found in our analyses that the majority of baseline non-depressed patients would develop sustained depressive symptoms at least once during the course of the study. Probable REM sleep disorder (pRBD), age, duration of diagnosis, impairment in daily activities, mild constipation, and antidepressant use were among the baseline risk factors for depression in either cohort. Our Cox regression model indicated that pRBD, impairment in daily activities, hyposmia, and mild constipation could serve as longitudinal predictors of sustained depressive symptoms. Conclusions We identified several potential risk factors to aid physicians in the early detection of depression in Parkinson's disease patients. Our findings also underline the importance of adjusting for multiple covariates when analyzing risk factors for depression.

scholarly journals Association of fall risk factors and non-motor symptoms in patients with early Parkinson’s disease

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Kyum-Yil Kwon ◽  
Suyeon Park ◽  
Eun Ji Lee ◽  
Mina Lee ◽  
Hyunjin Ju
Keyword(s):  
Risk Factors ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Freezing Of Gait ◽  
Prior History ◽  
Motor Symptoms ◽  
Related Factors ◽  
Related Risk ◽  
History Of ◽  
Non Motor Symptoms

AbstractThe association of non-motor symptoms (NMSs) with fall-related factors in patients with Parkinson’s disease (PD) remains to be further elucidated in the early stages of the disease. Eighty-six patients with less than 5 years of the onset of PD were retrospectively enrolled in the study. We assessed potential fall-related risk factors including (1) a history of falls during the past year (faller versus non-faller), (2) the fear of falling (FoF), and (3) the freezing of gait (FoG). Different types of NMSs were measured using the Montreal Cognitive Assessment (MoCA), the Beck Depression Inventory (BDI), the Beck Anxiety Inventory (BAI), the Parkinson’s disease Fatigue Scale (PFS), and the Scales for Outcomes in Parkinson’s disease—Autonomic dysfunction (SCOPA-AUT). The faller group (37.2%) showed higher scores for BDI, BAI, PFS, and SCOPA-AUT, compared to the non-faller group. From logistic regression analyses, the prior history of falls was related to the gastrointestinal domain of SCOPA-AUT, FoF was associated with BAI, and gastrointestinal and urinary domains of SCOPA-AUT, and FoG was linked to BAI and gastrointestinal domain of SCOPA-AUT. In conclusion, we found that fall-related risk factors in patients with early PD were highly connected with gastrointestinal dysautonomia.

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 Progression of postural control and gait deficits in Parkinson's disease and freezing of gait: A longitudinal study

2016 ◽  
Vol 28 ◽  
pp. 73-79 ◽  
Author(s):  
Griet Vervoort ◽  
Aniek Bengevoord ◽  
Carolien Strouwen ◽  
Esther M.J. Bekkers ◽  
Elke Heremans ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Longitudinal Study ◽  
Postural Control ◽  
Freezing Of Gait
Sign in / Sign up

Export Citation Format

Share Document