Semiautomated Algorithm for the Diagnosis of Multiple System Atrophy With Predominant Parkinsonism.

OBJECTIVE: Putaminal iron deposition is an important feature that helps differentiate multiple system atrophy with predominant parkinsonism (MSA-p) from Parkinson's disease (PD). Most previous studies used visual inspection or quantitative methods with manual manipulation to perform this differentiation. We investigated the value of a new semiautomated diagnostic algorithm using 3T-MR susceptibility-weighted imaging for MSA-p. METHODS: This study included 26 MSA-p, 68 PD, and 41 normal control (NC) subjects. The algorithm was developed in 2 steps: 1) determine the image containing the remarkable putaminal margin and 2) calculate the phase-shift values, which reflect the iron concentration. The next step was to identify the best differentiating conditions among several combinations. The highest phaseshift value of each subject was used to assess the most effective diagnostic set. RESULTS: The raw phase-shift values were present along the lateral margin of the putamen in each group. It demonstrates an anterior- to-posterior gradient that was identified most frequently in MSA-p. The average of anterior 5 phase shift values were used for normalization. The highest area under the receiver operating characteristic curve (0.874, 80.8% sensitivity, and 86.7% specificity) of MSA-p versus PD was obtained under the combination of 3 or 4 vertical pixels and one dominant side when the normalization methods were applied. In the subanalysis for the MSA-p patients with a longer disease duration, the performance of the algorithm improved. CONCLUSION: This algorithm detected the putaminal lateral margin well, provided insight into the iron distribution of the putaminal rim of MSA-p, and demonstrated good performance in differentiating MSA-p from PD.

Validation of Freezing-of-Gait Monitoring Using Smartphone.

BACKGROUND: Freezing of gait (FOG) is a commonly observed motor symptom for patients with Parkinson's disease (PD). The symptoms of FOG include reduced step lengths or motor blocks, even with an evident intention of walking. FOG should be monitored carefully because it not only lowers the patient's quality of life, but also significantly increases the risk of injury. INTRODUCTION: In previous studies, patients had to wear several sensors on the body and another computing device was needed to run the FOG detection algorithm. Moreover, the features used in the algorithm were based on low-level and hand-crafted features. In this study, we propose a FOG detection system based on a smartphone, which can be placed in the patient's daily wear, with a novel convolutional neural network (CNN). METHODS: The walking data of 32 PD patients were collected from the accelerometer and gyroscope embedded in the smartphone, located in the trouser pocket. The motion signals measured by the sensors were converted into the frequency domain and stacked into a 2D image for the CNN input. A specialized CNN model for FOG detection was determined through a validation process. RESULTS: We compared our performances with the results acquired by the previously reported settings. The proposed architecture discriminated the freezing events from the normal activities with an average sensitivity of 93.8% and a specificity of 90.1%. CONCLUSIONS: Using our methodology, the precise and continuous monitoring of freezing events with unconstrained sensing can assist patients in managing their chronic disease in daily life effectively.

Wrist sensor-based tremor severity quantification in Parkinson's disease using convolutional neural network.

Tremor is a commonly observed symptom in patients of Parkinson's disease (PD), and accurate measurement of tremor severity is essential in prescribing appropriate treatment to relieve its symptoms. We propose a tremor assessment system based on the use of a convolutional neural network (CNN) to differentiate the severity of symptoms as measured in data collected from a wearable device. Tremor signals were recorded from 92 PD patients using a custom-developed device (SNUMAP) equipped with an accelerometer and gyroscope mounted on a wrist module. Neurologists assessed the tremor symptoms on the Unified Parkinson's Disease Rating Scale (UPDRS) from simultaneously recorded video footages. The measured data were transformed into the frequency domain and used to construct a two-dimensional image for training the network, and the CNN model was trained by convolving tremor signal images with kernels. The proposed CNN architecture was compared to previously studied machine learning algorithms and found to outperform them (accuracy = 0.85, linear weighted kappa = 0.85). More precise monitoring of PD tremor symptoms in daily life could be possible using our proposed method.

High-accuracy automatic classification of Parkinsonian tremor severity using machine learning method.

MOTIVATION: Although clinical aspirations for new technology to accurately measure and diagnose Parkinsonian tremors exist, automatic scoring of tremor severity using machine learning approaches has not yet been employed. OBJECTIVE: This study aims to maximize the scientific validity of automatic tremor-severity classification using machine learning algorithms to score Parkinsonian tremor severity in the same manner as the unified Parkinson's disease rating scale (UPDRS) used to rate scores in real clinical practice. APPROACH: Eighty-five PD patients perform four tasks for severity assessment of their resting, resting with mental stress, postural, and intention tremors. The tremor signals are measured using a wristwatch-type wearable device with an accelerometer and gyroscope. Displacement and angle signals are obtained by integrating the acceleration and angular-velocity signals. Nineteen features are extracted from each of the four tremor signals. The optimal feature configuration is decided using the wrapper feature selection algorithm or principal component analysis, and decision tree, support vector machine, discriminant analysis, and k-nearest neighbour algorithms are considered to develop an automatic scoring system for UPDRS prediction. The results are compared to UPDRS ratings assigned by two neurologists. MAIN RESULTS: The highest accuracies are 92.3%, 86.2%, 92.1%, and 89.2% for resting, resting with mental stress, postural, and intention tremors, respectively. The weighted Cohen's kappa values are 0.745, 0.635 and 0.633 for resting, resting with mental stress, and postural tremors (almost perfect agreement), and 0.570 for intention tremors (moderate). SIGNIFICANCE: These results indicate the feasibility of the proposed system as a clinical decision tool for Parkinsonian tremor-severity automatic scoring.

Automatic Classification of Tremor Severity in Parkinson's Disease Using a Wearable Device.

Although there is clinical demand for new technology that can accurately measure Parkinsonian tremors, automatic scoring of Parkinsonian tremors using machine-learning approaches has not yet been employed. This study aims to fill this gap by proposing machine-learning algorithms as a way to predict the Unified Parkinson's Disease Rating Scale (UPDRS), which are similar to how neurologists rate scores in actual clinical practice. In this study, the tremor signals of 85 patients with Parkinson's disease (PD) were measured using a wrist-watch-type wearable device consisting of an accelerometer and a gyroscope. The displacement and angle signals were calculated from the measured acceleration and angular velocity, and the acceleration, angular velocity, displacement, and angle signals were used for analysis. Nineteen features were extracted from each signal, and the pairwise correlation strategy was used to reduce the number of feature dimensions. With the selected features, a decision tree (DT), support vector machine (SVM), discriminant analysis (DA), random forest (RF), and k-nearest-neighbor (kNN) algorithm were explored for automatic scoring of the Parkinsonian tremor severity. The performance of the employed classifiers was analyzed using accuracy, recall, and precision, and compared to other findings in similar studies. Finally, the limitations and plans for further study are discussed.

Tremor frequency characteristics in Parkinson's disease under resting-state and stress-state conditions.

Tremor characteristics-amplitude and frequency components-are primary quantitative clinical factors for diagnosis and monitoring of tremors. Few studies have investigated how different patient's conditions affect tremor frequency characteristics in Parkinson's disease (PD). Here, we analyzed tremor characteristics under resting-state and stress-state conditions. Tremor was recorded using an accelerometer on the finger, under resting-state and stress-state (calculation task) conditions, during rest tremor and postural tremor. The changes of peak power, peak frequency, mean frequency, and distribution of power spectral density (PSD) of tremor were evaluated across conditions. Patients whose tremors were considered more than "mild" were selected, for both rest (n=67) and postural (n=25) tremor. Stress resulted in both greater peak powers and higher peak frequencies for rest tremor (p<0.001), but not for postural tremor. Notably, peak frequencies were concentrated around 5 Hz under stress-state condition. The distributions of PSD of tremor were symmetrical, regardless of conditions. Tremor is more evident and typical tremor characteristics, namely a lower frequency as amplitude increases, are different in stressful condition. Patient's conditions directly affect neural oscillations related to tremor frequencies. Therefore, tremor characteristics in PD should be systematically standardized across patient's conditions such as attention and stress levels.

Clinicians' Tendencies to Under-Rate Parkinsonian Tremors in the Less Affected Hand.

The standard assessment method for tremor severity in Parkinson's disease is visual observation by neurologists using clinical rating scales. This is, therefore, a subjective rating that is dependent on clinical expertise. The objective of this study was to report clinicians' tendencies to under-rate Parkinsonian tremors in the less affected hand. This was observed through objective tremor measurement with accelerometers. Tremor amplitudes were measured objectively using tri-axis-accelerometers for both hands simultaneously in 53 patients with Parkinson's disease during resting and postural tremors. The videotaped tremor was rated by neurologists using clinical rating scales. The tremor measured by accelerometer was compared with clinical ratings. Neurologists tended to under-rate the less affected hand in resting tremor when the contralateral hand had severe tremor in Session I. The participating neurologists corrected this tendency in Session II after being informed of it. The under-rating tendency was then repeated by other uninformed neurologists in Session III. Kappa statistics showed high inter-rater agreements and high agreements between estimated scores derived from the accelerometer signals and the mean Clinical Tremor Rating Scale evaluated in every session. Therefore, clinicians need to be aware of this under-rating tendency in visual inspection of the less affected hand in order to make accurate tremor severity assessments.

Heart Rate Variability Monitoring during Sleep Based on Capacitively Coupled Textile Electrodes on a Bed.

In this study, we developed and tested a capacitively coupled electrocardiogram (ECG) measurement system using conductive textiles on a bed, for long-term healthcare monitoring. The system, which was designed to measure ECG in a bed with no constraints of sleep position and posture, included a foam layer to increase the contact region with the curvature of the body and a cover to ensure durability and easy installation. Nine healthy subjects participated in the experiment during polysomnography (PSG), and the heart rate (HR) coverage and heart rate variability (HRV) parameters were analyzed to evaluate the system. The experimental results showed that the mean of R-peak coverage was 98.0% (95.5%-99.7%), and the normalized errors of HRV time and spectral measures between the Ag/AgCl system and our system ranged from 0.15% to 4.20%. The root mean square errors for inter-beat (RR) intervals and HR were 1.36 ms and 0.09 bpm, respectively. We also showed the potential of our developed system for rapid eye movement (REM) sleep and wake detection as well as for recording of abnormal states.

Unconstrained detection of freezing of Gait in Parkinson's disease patients using smartphone.

Freezing of gait (FOG) is a common motor impairment to suffer an inability to walk, experienced by Parkinson's disease (PD) patients. FOG interferes with daily activities and increases fall risk, which can cause severe health problems. We propose a novel smartphone-based system to detect FOG symptoms in an unconstrained way. The feasibility of single device to sense gait characteristic was tested on the various body positions such as ankle, trouser pocket, waist and chest pocket. Using measured data from accelerometer and gyroscope in the smartphone, machine learning algorithm was applied to classify freezing episodes from normal walking. The performance of AdaBoost.M1 classifier showed the best sensitivity of 86% at the waist, 84% and 81% in the trouser pocket and at the ankle respectively, which is comparable to the results of previous studies.

Capacitive measurement of ECG for ubiquitous healthcare.

The technology for measuring ECG using capacitive electrodes and its applications are reviewed. Capacitive electrodes are built with a high-input-impedance preamplifier and a shield on their rear side. Guarding and driving ground are used to reduce noise. An analysis of the intrinsic noise shows that the thermal noise caused by the resistance in the preamplifier is the dominant factor of the intrinsic noise. A fully non-contact capacitive measurement has been developed using capacitive grounding and applied to a non-intrusive ECG measurement in daily life. Many ongoing studies are examining how to enhance the quality and ease of applying electrodes, thus extending their applications in ubiquitous healthcare from attached-on-object measurements to wearable or EEG measurements.

Unconstrained sleep apnea monitoring using polyvinylidene fluoride film-based sensor.

We established and tested an unconstrained sleep apnea monitoring method using a polyvinylidene (PVDF) film-based sensor for continuous and accurate monitoring of apneic events occurred during sleep. Twenty-six sleep apnea patients and six normal subjects participated in this study. Subjects' respiratory signals were measured using the PVDF-based sensor during polysomnography. The PVDF sensor comprised a 4 × 1 array, and a thin silicon pad was placed over the sensor to prevent damage. Total thickness of the merged system was approximately 1.1 mm which was thin enough to prevent the subject from being consciously aware of its presence. It was designed to be placed under subjects' backs and installed between a bed cover and mattress. The proposed method was based on the standard deviation of the PVDF signals, and it was applied to a test set for detecting apneic events. The method's performance was assessed by comparing the results with a sleep physician's manual scoring. The correlation coefficient for the apnea-hypopnea index (AHI) values between the methods was 0.94 (p < 0.001). The areas under the receiver operating curves at three AHI threshold levels (>5, >15, and >20) for sleep apnea diagnosis were 0.98, 0.99, and 0.98, respectively. For min-by-min apnea detection, the method classified sleep apnea with an average sensitivity of 72.9%, specificity of 90.6%, accuracy of 85.5%, and kappa statistic of 0.60. The developed system and method can be applied to sleep apnea detection in home or ambulatory monitoring.

Estimation of body postures on bed using unconstrained ECG measurements.

We developed and tested a system for estimating body postures on a bed using unconstrained measurements of electrocardiogram (ECG) signals using 12 capacitively coupled electrodes and a conductive textile sheet. Thirteen healthy subjects participated in the experiment. After detecting the channels in contact with the body among the 12 electrodes, the features were extracted on the basis of the morphology of the QRS (Q wave, R wave, and S wave of ECG) complex using three main steps. The features were applied to linear discriminant analysis, support vector machines with linear and radial basis function (RBF) kernels, and artificial neural networks (one and two layers), respectively. SVM with RBF kernel had the highest performance with an accuracy of 98.4% for estimation of four body postures on the bed: supine, right lateral, prone, and left lateral. Overall, although ECG data were obtained from few sensors in an unconstrained manner, the performance was better than the results that have been reported to date. The developed system and algorithm can be applied to the obstructive apnea detection and analyses of sleep quality or sleep stages, as well as body posture detection for the management of bedsores.

Conductive polymer foam surface improves the performance of a capacitive EEG electrode.

In this paper, a new conductive polymer foam-surfaced electrode was proposed for use as a capacitive EEG electrode for nonintrusive EEG measurements in out-of-hospital environments. The current capacitive electrode has a rigid surface that produces an undefined contact area due to its stiffness, which renders it unable to conform to head curvature and locally isolates hairs between the electrode surface and scalp skin, making EEG measurement through hair difficult. In order to overcome this issue, a conductive polymer foam was applied to the capacitive electrode surface to provide a cushioning effect. This enabled EEG measurement through hair without any conductive contact with bare scalp skin. Experimental results showed that the new electrode provided lower electrode-skin impedance and higher voltage gains, signal-to-noise ratios, signal-to-error ratios, and correlation coefficients between EEGs measured by capacitive and conventional resistive methods compared to a conventional capacitive electrode. In addition, the new electrode could measure EEG signals, while the conventional capacitive electrode could not. We expect that the new electrode presented here can be easily installed in a hat or helmet to create a nonintrusive wearable EEG apparatus that does not make users look strange for real-world EEG applications.