No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Utilizing Neural Networks to Predict Freezing of Gait in Parkinson's Patients
Abstract
With the appropriate mathematical models, data from wearable devices can be used to help Parkinson's patients live safer and more independent lives. Inspired by this idea, the purpose of this study was to determine the viability of neural networks in predicting Freezing of Gait (FoG), a symptom of Parkinson's disease in which the patient's legs are suddenly rendered unable to move. A class of neural networks known as layered recurrent networks (LRNs) was applied to an open-source FoG experimental dataset donated to the Machine Learning Repository of the University of California at Irvine. The independent variables in this experiment -- the subject being tested, neural network architecture, and down sampling of the majority classes -- were each varied and compared against the performance of the neural network in predicting impending FoG events. It was determined that single-layered recurrent networks are a viable method of predicting FoG events given the volume of the training data available, though results varied between patients.
... Plantar pressure insole sensors that can be easily worn in a shoe have also been effective for FOG detection (24,25) and prediction (26)(27)(28) and have advantages in terms of wearability and simplicity. In addition to sensor type considerations, attempts have been made to reduce prediction system complexity by using only a single sensor input, such as a single shank-mounted accelerometer (29) or a waist-mounted inertial measurement unit (IMU) (30). A single-sensor system would eliminate the need for multisensor synchronization, reduce the number of sensors worn, reduce the amount of data to acquire and process, and may be more acceptable to end users. ...
... One approach to reduce the number of sensors would be to limit sensors to one side of the body. While single-side (7,9,(13)(14)(15)29) and bilateral (16) IMU sensors have been investigated for FOG prediction, the unilateral use of plantar pressure sensors compared to bilateral use has not been studied. ...
... However, these systems were person specific and may not be generalizable to new participants or they used multiple sensors on various parts of the body and are thus, not directly comparable to this study, which used a single sensor to create personindependent models. The sensitivity and specificity of the LAS model were comparable to other single-sensor FOG prediction studies in the literature (6,29,30,39). The best LAS model performed better for FOG prediction than a similar tree-based algorithm (AdaBoosted C4.5 decision tree) that used data from a single waist-mounted IMU (30). ...
Background
Freezing of gait (FOG) is an intermittent walking disturbance experienced by people with Parkinson's disease (PD). FOG has been linked to falling, injury, and overall reduced mobility. Wearable sensor-based devices can detect freezes already in progress and provide a cue to help the person resume walking. While this is helpful, predicting FOG episodes before onset and providing a timely cue may prevent the freeze from occurring. Wearable sensors mounted on various body parts have been used to develop FOG prediction systems. Despite the known asymmetry of PD motor symptom manifestation, the difference between the most affected side (MAS) and least affected side (LAS) is rarely considered in FOG detection and prediction studies.
Methods
To examine the effect of using data from the MAS, LAS, or both limbs for FOG prediction, plantar pressure data were collected during a series of walking trials and used to extract time and frequency-based features. Three datasets were created using plantar pressure data from the MAS, LAS, and both sides together. ReliefF feature selection was performed. FOG prediction models were trained using the top 5, 10, 15, 20, 25, or 30 features for each dataset.
Results
The best models were the MAS model with 15 features and the LAS and bilateral models with 5 features. The LAS model had the highest sensitivity (79.5%) and identified the highest percentage of FOG episodes (94.9%). The MAS model achieved the highest specificity (84.9%) and lowest false positive rate (1.9 false positives/walking trial). Overall, the bilateral model was best with 77.3% sensitivity and 82.9% specificity. In addition, the bilateral model identified 94.2% of FOG episodes an average of 0.8 s before FOG onset. Compared to the bilateral model, the LAS model had a higher false positive rate; however, the bilateral and LAS models were similar in all the other evaluation metrics.
Conclusion
The LAS model would have similar FOG prediction performance to the bilateral model at the cost of slightly more false positives. Given the advantages of single sensor systems, the increased false positive rate may be acceptable to people with PD. Therefore, a single plantar pressure sensor placed on the LAS could be used to develop a FOG prediction system and produce performance similar to a bilateral system.
... specificity [36,38,55,66,76,80,85,86,88,89,91]. Neural networks for FOG prediction tended to perform slightly worse, up to 86% sensitivity, 80.25% specificity, and 89% precision [96,97,99]. ...
... Different NN subtypes have been used in FOG detection and prediction, such as convolutional [85,90] and recurrent [97,100] NN. Convolutional neural networks (CNN) have become popular in numerous applications, including medical image analysis, in part due their ability to recognize local patterns within images and because feature selection prior to implementation is not required [130,131]. ...
... CNN performed well for FOG detection [85], achieving 91.9% sensitivity and 89.5% specificity. Recurrent NN have recently been used for FOG prediction due to their applicability to time-series data [97,100]. Recurrent neural networks (RNN) utilize previous data in addition to current inputs during classification [132], thus giving the network "memory" to help recognize sequences [133]. ...
Freezing of gait (FOG) is a serious gait disturbance, common in mid- and late-stage Parkinson’s disease, that affects mobility and increases fall risk. Wearable sensors have been used to detect and predict FOG with the ultimate aim of preventing freezes or reducing their effect using gait monitoring and assistive devices. This review presents and assesses the state of the art of FOG detection and prediction using wearable sensors, with the intention of providing guidance on current knowledge, and identifying knowledge gaps that need to be filled and challenges to be considered in future studies. This review searched the Scopus, PubMed, and Web of Science databases to identify studies that used wearable sensors to detect or predict FOG episodes in Parkinson’s disease. Following screening, 74 publications were included, comprising 68 publications detecting FOG, seven predicting FOG, and one in both categories. Details were extracted regarding participants, walking task, sensor type and body location, detection or prediction approach, feature extraction and selection, classification method, and detection and prediction performance. The results showed that increasingly complex machine-learning algorithms combined with diverse feature sets improved FOG detection. The lack of large FOG datasets and highly person-specific FOG manifestation were common challenges. Transfer learning and semi-supervised learning were promising for FOG detection and prediction since they provided person-specific tuning while preserving model generalization.
... Their method achieved an accuracy of 78.8% at a PH of 4 s. Zia et al. [15] used acceleration data of a single sensor placed at the shank along with layered recurrent networks to predict FoG 5 s before its occurrence. However, their method obtained low prediction performance with an average precision of 0.66 and an average recall of 0.28 on three patients with PD. ...
Freezing of gait (FoG) is a widely observed movement disorder in Parkinson’s Disease patients (PD). Its prediction is crucial for effectively giving the cue to avoid FoG occurrence. However, present methods of prediction of FoG are inaccurate for large but practical prediction horizons (PH)s. Therefore, this work presents a comprehensive analysis of the electroencephalography (EEG) and inertial measurement units (IMU)s to predict FoG advance in time. An ensemble model consisting of two neural networks, EEGFoGNet and IMUFoGNet, was developed and tested at different PHs and ensemble weights. Moreover, the model is tested for two practical scenarios: clinical or research applications and personal uses. For clinical or research applications, stratified 5-Folds cross-validation was used. For personal uses, a transfer learning technique was used for learning user-specific FoG-related features. The model obtained the best accuracy of 92.1% at 1 second’s PH and the least accuracy of 86.2% at 5 seconds’ PH. The presented results are encouraging and show the proposed model’s clinical applicability. This study will also help practitioners in comparing the efficacy of different cueing methods.
... However, such a device has not been developed yet, mainly due to the difficulty in identifying an efficient approach to FOG prediction, with the main issue being the high inter-individuals and even intra-individuals variability among FOG episodes that therefore requires high degrees of flexibility in the proposed prediction algorithm [7] . This may suggest that complex approaches based on machine-learning techniques for instance, may solve this problem [11]- [15]. However, if the predictive algorithm requires too many stages of calculations (e.g., when selecting many complex features), it could induce unacceptable delays when computing power is limited as it is the case for many wearable devices, thus hampering real-time applications. ...
Freezing of Gait (FOG) is among the most debilitating symptoms of Parkinson’s Disease (PD), characterized by a sudden inability to generate effective stepping. In preparation for the development of a real-time FOG prediction and intervention device, this work presents a novel FOG prediction algorithm based on detection of altered interlimb coordination of the legs, as measured using two inertial movement sensors and analyzed using a wavelet coherence algorithm.
Methods
: Fourteen participants with PD (in OFF state) were asked to walk in challenging conditions (e.g. with turning, dual-task walking, etc.) while wearing inertial motion sensors (waist, 2 shanks) and being videotaped. Occasionally, participants were asked to voluntarily stop (VOL). FOG and VOL events were identified by trained researchers based on videos. Wavelet analysis was performed on shank sagittal velocity signals and a synchronization loss threshold (SLT) was defined and compared between FOG and VOL. A proof-of-concept analysis was performed for a subset of the data to obtain preliminary classification characteristics of the novel measure.
Results
: 128 FOG and 42 VOL episodes were analyzed. SLT occurred earlier for FOG (MED=1.81 sec prior to stop, IQR=1.57) than for VOL events (MED=0.22 sec, IQR=0.76) (Z=-4.3, p<0.001, ES=1.15). These time differences were not related with measures of disease severity. Preliminary results demonstrate sensitivity of 98%, specificity of 42% (mostly due to ‘turns’ detection) and balanced accuracy of 70% for SLT-based prediction, with good differentiation between FOG and VOL.
Conclusions
: Wavelet analysis provides a relatively simple, promising approach for prediction of FOG in people with PD.
... However, better performance was expected from a NN solution for its clinical applications. In [14] Jonathan Zia et al. used acceleration data of a single sensor placed at the shank along with layered recurrent networks to predict FoG 5 seconds before its occurrence. However, their method obtained low prediction performance with an average precision of 0.66 and an average recall of 0.28 on three PD patients. ...
p>Freezing of gait (FoG) is a widely observed movement disorder in Parkinson’s Disease patients (PD). Its prediction is crucial for effectively giving the cue to avoid FoG occurrence. However, present methods of prediction of FoG are inaccurate for large but practical prediction horizons (PH)s. Therefore, this work presents a comprehensive analysis of the electroencephalography (EEG) and inertial measurement units (IMU)s to predict FoG advance in time. An ensemble model consisting of two neural networks, EEGFoGNet and IMUFoGNet, was developed and tested at different PHs and ensemble weights. Moreover, the model is tested for two practical scenarios: clinical or research applications and personal uses. For clinical or research applications, stratified 5-Folds cross-validation was used. For personal uses, a transfer learning technique was used for learning user-specific FoG-related features. The model obtained the best accuracy of 92.1% at 1 second’s PH and the least accuracy of 86.2% at 5 seconds’ PH. The presented results are encouraging and show the proposed model’s clinical applicability. This study will also help practitioners in comparing the efficacy of different cueing methods.</p
... However, better performance was expected from a NN solution for its clinical applications. In [14] Jonathan Zia et al. used acceleration data of a single sensor placed at the shank along with layered recurrent networks to predict FoG 5 seconds before its occurrence. However, their method obtained low prediction performance with an average precision of 0.66 and an average recall of 0.28 on three PD patients. ...
p>Freezing of gait (FoG) is a widely observed movement disorder in Parkinson’s Disease patients (PD). Its prediction is crucial for effectively giving the cue to avoid FoG occurrence. However, present methods of prediction of FoG are inaccurate for large but practical prediction horizons (PH)s. Therefore, this work presents a comprehensive analysis of the electroencephalography (EEG) and inertial measurement units (IMU)s to predict FoG advance in time. An ensemble model consisting of two neural networks, EEGFoGNet and IMUFoGNet, was developed and tested at different PHs and ensemble weights. Moreover, the model is tested for two practical scenarios: clinical or research applications and personal uses. For clinical or research applications, stratified 5-Folds cross-validation was used. For personal uses, a transfer learning technique was used for learning user-specific FoG-related features. The model obtained the best accuracy of 92.1% at 1 second’s PH and the least accuracy of 86.2% at 5 seconds’ PH. The presented results are encouraging and show the proposed model’s clinical applicability. This study will also help practitioners in comparing the efficacy of different cueing methods.</p
... In recent years, there has been a significant increase in the use of machine learning based computer-aided diagnosis (CAD) systems to diagnose diseases, sometimes even in early stages (Gupta, Kumar, Arora, & Raman, 2021;Kumar, Gupta, Arora, & Raman, 2021a, 2021bMasud et al., 2021). There has also been an increase in utilization of such CAD systems for diagnosing PD from various modalities like speech signals (Hariharan, Polat, & Sindhu, 2014;Zia, Tadayon, McDaniel, & Panchanathan, 2016), gait signals (Del Din, Godfrey, & Rochester, 2015;Khorasani & Daliri, 2014), magnetic resonance imaging (MRI) (Bouza, Yang, & Vemuri, 2020;Esmaeilzadeh, Yang, & Adeli, 2018;Huang et al., 2021), positron emission tomography (PET) (Hwang et al., 2018), single-photon emission computed tomography (SPECT) (Grover, Bhartia, Yadav, & Seeja, 2018;Pianpanit et al., 2020), Dopamine Transporter Scan (DaT Scan) (Eskofier et al., 2016;Sivanesan, Anwar, Talwar, Menaka, & Karthik, 2016), tremor signal (Hosseini & Makki, 2013), handwriting signal, handwritten images (Pereira, Pereira, Papa, Rosa, & Yang, 2016) and various other clinical features (CF) (Er, Cetin, Bascil, & Temurtas, 2016). ...
Parkinson’s disease (PD) is a chronic neurodegenerative disease of that predominantly affects the elderly in today’s world. For the diagnosis of the early stages of PD, effective and powerful automated techniques are needed by recent enabling technologies as a tool. In this study, we present a comprehensive review of papers from 2013 to 2021 on the diagnosis of PD and its subtypes using artificial neural networks (ANNs) and deep neural networks (DNNs). We present detailed information and analysis regarding the usage of various modalities, datasets, architectures and experimental configurations in a succinct manner. We also present an in-depth comparative analysis of various proposed architectures. Finally, we present a number of relevant future directions for researchers in this area.
... Zia et al. [41] proposed layered recurrent networks (LRN), a special type of neural networks, for predicting FOG in PD patients. The underlying of using this machine learning model is that LRN can capture time dependencies on signals from 3D accelerometers placed in the body. ...
Most of Parkinson’s disease (PD) patients present a set of motor and non-motor symptoms and behaviors that vary during the day and from day-to-day. In particular, freezing of gait (FOG) impairs their quality of life and increases the risk of falling. Smart technology like mobile communication and wearable sensors can be used for detection and prediction of FOG, increasing the understanding of the complex PD. There are surveys reviewing works on Parkinson and/or technologies used to manage this disease. In this review, we summarize and analyze works addressing FOG detection and prediction based on wearable sensors, vision and other devices. We aim to identify trends, challenges and opportunities in the development of FOG detection and prediction systems.
Freezing of gait (FoG) is one of the most distressing symptoms of Parkinson’s Disease (PD), commonly occurring in patients at middle and late stages of the disease. Automatic and accurate FoG detection and prediction have emerged as a promising tool for long-term monitoring of PD and implementation of gait assistance systems. This paper reviews the recent development of FoG detection and prediction using wearable sensors, with attention on identifying knowledge gaps that need to be filled in future research. This review searched the PubMed and Web of Science databases to collect studies that detect or predict FoG with wearable sensors. After screening, 89 of 270 articles were included. The data description, extracted features, detection/prediction methods, and classification performance were extracted from the articles. As the number of papers of this area is increasing, the performance has been steadily improved. However, small datasets and inconsistent evaluation processes still hinder the application of FoG detection and prediction with wearable sensors in clinical practice.
Sedentarism is a common problem that can affect human health and wellbeing. Predicting sedentary behaviour is an emerging area that can benefit from data collected from sensors available in ubiquitous devices, such as wearables and smartphones. In this paper, we present an approach aiming at predicting the sedentary behaviour of a user from data collected from sensors installed in wearable/mobile devices. We compare personal and impersonal models using a real-life dataset consisting of sensing data of 48 users during 10 weeks. We found that impersonal models using Deep Neural Networks were able to accurately predict the subject’s future sedentary behaviour.
Walking has a significant impact on one’s quality of life. Freezing of Gait (FoG) is a typical symptom of Parkinson’s disease (PD). FoG is characterised by quick and abrupt transient falls, as a result of which the patient’s mobility is limited and their independence is lost. Thus, early detection of FoG in PD patients is necessary for diagnosis and rehabilitation. The present strategies for early detection of FoG are ineffective and have a low success rate. This study illustrates the comparative analysis of ML techniques (K Nearest Neighbors (KNN), Decision Trees, Random Forest, Support Vector Classifier (SVC), and Ada Boost Classifier), using time and statistical features to perform detection and prediction tasks on the publicly available DaphNet database. FoG prediction is highly patient dependent and achieved a peak F1 - score of 80% for one of the patients. The paper also present a combined analysis of all the patients which may aid in designing wearable sensors for detection. This system detects FoG with a precision value of about 81%.
Our understanding of Parkinson’s disease (PD), its symptoms and diagnosis have been expanded considerably since its formal description by James Parkinson two centuries ago [Prze17]. However, this common neurodegenerative disorder has still been a threat to the health and well-being of patients and an economic burden, since a complete treatment is still a formidable barrier. Impaired gait is one of the most characteristic symptoms in Parkinson’s disease. Assessment of movement impairments forms a basis for diagnosis, evaluation of the disease progress and the evaluation of therapeutic interventions. The emergence of wearable technologies has permitted the development of mobile systems for gait analysis. This technology enables us to record large amounts of patients’ data not only during clinical visits but also outside clinics. Data driven methods hold the potential to analyze the large volume of data to provide an objective disease assessment, improve current approaches to manage disease progression, and monitor patients outside clinics. This thesis aims to leverage data driven methods for the development of an objective gait assessment using mobile gait analysis systems. The present thesis answers three main open questions in this domain: development and comparison of four widely used data driven methods for gait segmentation, analysis of turning for on-shoe wearable sensors and interpretable classification of motor impairments. Regarding segmentation of gait sequence to individual strides, three existing segmen- tation methods are implemented and validated for PD population. For this applica- tion, a novel segmentation method is also introduced and implemented for the first time. These methods are evaluated on two data sets with different levels of data heterogeneity. This contribution presents a fair comparison of segmentation methods on an identical data set. Segmenting gait sequences is the first step in the following steps of research: turning analysis and assessing motor impairments in PD. Further, turning deficits are examined using an on-shoe mobile gait analysis system. A method is introduced for isolation of turning from the whole gait sequence based on the statistics of turning angles between two consecutive strides. Correlation of turn-derived spatio-temporal features with two widely used clinical scales is examined. This is a proof-of-concept for the feasibility of using on-shoe mobile gait analysis systems for turning analysis in PD. Turn-derived spatio-temporal features, then, are used in the next contribution. Finally, spatio-temporal features computed from straight walking as well as turning are used for the classification of different levels of motor impairments. Gaussian pro- cesses, a probabilistic machine learning method, is introduced for the first time for this application. The method provides the classification output as well as an explicit uncertainty measure, which captures the confidence of the method in the estimated output. The measure of uncertainty is particularly important in cases when the data set is small and noisy. A discussion regarding the properties of this type of data driven method and its evaluation is presented. To conclude, the present thesis centers on the development of data driven methods for objective assessment of gait in Parkinson’s disease. The works mentioned above contribute to the early diagnosis, evaluation of disease progression, assessment of therapeutic interventions and insights for long-term monitoring of patients outside clinics. Understanding the potentials and pitfalls of data driven methods in gait analysis leads to deeper insight into Parkinson’s disease and opens new doors for the disease management.
Freezing of gait (FoG) is a common gait impairment among patients with advanced Parkinson's disease. FoG is associated with falls and negatively impacts the patient's quality of life. Wearable systems that detect FoG in real time have been developed to help patients resume walking by means of rhythmic cueing. Current methods focus on detection, which require FoG events to happen first, while their prediction opens the road to preemptive cueing, which might help subjects to avoid freeze altogether. We analyzed electrocardiography (ECG) and skinconductance (SC) data from 11 subjects who experience FoG in daily-life, and found statistically significant changes in ECG and SC data just before the FoG episodes, compared to normal walking. Based on these findings, we developed an anomaly-based algorithm for predicting gait freeze from relevant SC features. We were able to predict 71.3% from 184 FoG with an average of 4.2 seconds before a freeze episode happened. Our findings enable the possibility of wearable systems which predict with few seconds before an upcoming FoG from skin conductance, and start external cues to help the user avoid the gait freeze.
Freezing of gait is a common and disabling symptom in patients with parkinsonism, characterised by sudden and brief episodes of inability to produce effective forward stepping. These episodes typically occur during gait initiation or turning. Treatment is important because freezing of gait is a major risk factor for falls in parkinsonism, and a source of disability to patients. Various treatment approaches exist, including pharmacological and surgical options, as well as physiotherapy and occupational therapy, but evidence is inconclusive for many approaches, and clear treatment protocols are not available. To address this gap, we review medical and non-medical treatment strategies for freezing of gait and present a practical algorithm for the management of this disorder, based on a combination of evidence, when available, and clinical experience of the authors. Further research is needed to formally establish the merits of our proposed treatment protocol.
Copyright © 2015 Elsevier Ltd. All rights reserved.
Freezing of Gait (FOG) is a common symptom in the advanced stages of Parkinson's disease (PD), which significantly affects patients' quality of life. Treatment options offer limited benefit and there are currently no mechanisms able to effectively detect FOG before it occurs, allowing time for a sufferer to avert a freezing episode. Electroencephalography (EEG) offers a novel technique that may be able to address this problem. In this paper, we investigated the univariate and multivariate EEG features determined by both Fourier and wavelet analysis in the confirmation and prediction of FOG. The EEG power measures and network properties from 16 patients with PD and FOG were extracted and analyzed. It was found that both power spectral density and wavelet energy could potentially act as biomarkers during FOG. Information in the frequency domain of the EEG was found to provide better discrimination of EEG signals during transition to freezing than information coded in the time domain. The performance of the FOG prediction systems improved when the information from both domains was used. This combination resulted in a sensitivity of 86.0%, specificity of 74.4%, and accuracy of 80.2% when predicting episodes of freezing, outperforming current accelerometry-based tools for the prediction of FOG.
Freezing of gait (FoG) is a common gait impairment among patients with advanced Parkinson’s disease. FoG is associated with falls and negatively impact the patient’s quality of life. Wearable systems that detect FoG have been developed to help patients resume walking by means of auditory cueing. However, current methods for automated detection are not yet ideal. In this paper, we first compare feature learning approaches based on time-domain and statistical features to unsupervised ones based on principal components analysis. The latter systematically outperforms the former and also the standard in the field - Freezing Index by up to 8.1% in terms of F1-measure for FoG detection.
We go a step further by analyzing FoG prediction, i.e., identification of patterns (pre-FoG) occurring before FoG episodes, based only on motion data. Until now this was only attempted using electroencephalography. With respect to the three-class problem (FoG vs. pre-FoG vs. normal locomotion), we show that FoG prediction performance is highly patient-dependent, reaching an F1-measure of 56% in the pre-FoG class for patients who exhibit enough gait degradation before FoG.
In this paper, we present a wearable assistant for Parkinson's disease (PD) patients with the freezing of gait (FOG) symptom. This wearable system uses on-body acceleration sensors to measure the patients' movements. It automatically detects FOG by analyzing frequency components inherent in these movements. When FOG is detected, the assistant provides a rhythmic auditory signal that stimulates the patient to resume walking. Ten PD patients tested the system while performing several walking tasks in the laboratory. More than 8 h of data were recorded. Eight patients experienced FOG during the study, and 237 FOG events were identified by professional physiotherapists in a post hoc video analysis. Our wearable assistant was able to provide online assistive feedback for PD patients when they experienced FOG. The system detected FOG events online with a sensitivity of 73.1% and a specificity of 81.6%. The majority of patients indicated that the context-aware automatic cueing was beneficial to them. Finally, we characterize the system performance with respect to the walking style, the sensor placement, and the dominant algorithm parameters.
An approach to the construction of classifiers from imbalanced datasets is
described. A dataset is imbalanced if the classification categories are not
approximately equally represented. Often real-world data sets are predominately
composed of "normal" examples with only a small percentage of "abnormal" or
"interesting" examples. It is also the case that the cost of misclassifying an
abnormal (interesting) example as a normal example is often much higher than
the cost of the reverse error. Under-sampling of the majority (normal) class
has been proposed as a good means of increasing the sensitivity of a classifier
to the minority class. This paper shows that a combination of our method of
over-sampling the minority (abnormal) class and under-sampling the majority
(normal) class can achieve better classifier performance (in ROC space) than
only under-sampling the majority class. This paper also shows that a
combination of our method of over-sampling the minority class and
under-sampling the majority class can achieve better classifier performance (in
ROC space) than varying the loss ratios in Ripper or class priors in Naive
Bayes. Our method of over-sampling the minority class involves creating
synthetic minority class examples. Experiments are performed using C4.5, Ripper
and a Naive Bayes classifier. The method is evaluated using the area under the
Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy.
To assess the effect of levodopa on distinct freezing of gait (FOG) subtypes in patients with 'off' FOG. Nineteen patients (12 men, mean age 62.0 +/- 8.4 years) with Parkinson's disease and clinically significant FOG during 'off' states were videotaped whilst walking 130 m during 'off' and 'on' states. Three independent observers characterized the type, duration, and clinical manifestations and quantified FOG by analyzing the videotapes. Their combined mean scores were used for statistical analysis. The intra-class correlation coefficient assessed inter-observer reliability. Wilcoxon and Friedman tests evaluated differences in mean frequencies of FOG characteristics. During 'off' states, FOG was elicited by turns (63%), starts (23%), walking through narrow spaces (12%) and reaching destinations (9%). These respective values were only 14, 4, 2 and 1% during 'on' states (P < 0.011). Moving forward with very small steps and leg trembling in place were the most common manifestations of FOG; total akinesia was rare. Most FOG episodes took <10 s and tended to be shorter during 'on' states. Levodopa significantly decreased FOG frequency (P < 0.0001) and the number of episodes with akinesia (P < 0.001). Distinction amongst FOG subtypes enables evaluation of distinctive therapeutic response. Levodopa helps in reducing the frequency and duration of 'off'-related FOG.
Prediction of Freezing of Gait in Parkinson's From Physiological Wearables: An Exploratory Study
- S Mazilu
- A Calatroni
- E Gazit
- A Mirelman
- J M Hausdorff
- G Troster