Investigating the efficacy and importance of mobile-based assessments for Parkinson's disease: uncovering the potential of novel digital tests.

This study introduces PDMotion, a mobile application comprising 11 digital tests, including those adapted from the MDS-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part III and novel assessments, for remote Parkinson's Disease (PD) motor symptoms evaluation. Employing machine learning techniques on data from 50 PD patients and 29 healthy controls, PDMotion achieves accuracies of 0.878 for PD status prediction and 0.715 for severity assessment. A post-hoc explanation model is employed to assess the importance of features and tasks in diagnosis and severity evaluation. Notably, novel tasks that are not adapted from MDS-UPDRS Part III like the circle drawing, coordination test, and alternative tapping test are found to be highly important, suggesting digital assessments for PD can go beyond digitizing existing tests. The alternative tapping test emerges as the most significant task. Using its features alone achieves prediction accuracies comparable to the full task set, underscoring its potential as an independent screening tool. This study addresses a notable research gap by digitalizing a wide array of tests, including novel ones, and conducting a comparative analysis of their feature and task importance. These insights provide guidance for task selection and future development in PD mobile assessments, a field previously lacking such comparative studies.

Artificial intelligence-based video monitoring of movement disorders in the elderly: a review on current and future landscapes.

ABSTRACT: Due to global ageing, the burden of chronic movement and neurological disorders (Parkinson's disease and essential tremor) is rapidly increasing. Current diagnosis and monitoring of these disorders rely largely on face-to-face assessments utilising clinical rating scales, which are semi-subjective and time-consuming. To address these challenges, the utilisation of artificial intelligence (AI) has emerged. This review explores the advantages and challenges associated with using AI-driven video monitoring to care for elderly patients with movement disorders. The AI-based video monitoring systems offer improved efficiency and objectivity in remote patient monitoring, enabling real-time analysis of data, more uniform outcomes and augmented support for clinical trials. However, challenges, such as video quality, privacy compliance and noisy training labels, during development need to be addressed. Ultimately, the advancement of video monitoring for movement disorders is expected to evolve towards discreet, home-based evaluations during routine daily activities. This progression must incorporate data security, ethical considerations and adherence to regulatory standards.

Automatic labeling of Parkinson's Disease gait videos with weak supervision.

Motor dysfunction in Parkinson's Disease (PD) patients is typically assessed by clinicians employing the Movement Disorder Society's Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Such comprehensive clinical assessments are time-consuming, expensive, semi-subjective, and may potentially result in conflicting labels across different raters. To address this problem, we propose an automatic, objective, and weakly-supervised method for labeling PD patients' gait videos. The proposed method accepts videos of patients and classifies their gait scores as normal (Gait score in MDS-UPDRS = 0) or PD (MDS-UPDRS ≥ 1). Unlike previous work, the proposed method does not require a priori MDS-UPDRS ratings for training, utilizing only domain-specific knowledge obtained from neurologists. We propose several labeling functions that classify patients' gait and use a generative model to learn the accuracy of each labeling function in a self-supervised manner. Since results depended upon the estimated values of the patients' 3D poses, and existing pre-trained 3D pose estimators did not yield accurate results, we propose a weakly-supervised 3D human pose estimation method for fine-tuning pre-trained models in a clinical setting. Using leave-one-out evaluations, the proposed method obtains an accuracy of 89% on a dataset of 29 PD subjects - a significant improvement compared to previous work by 7%-10% depending upon the dataset. The method obtained state-of-the-art results on the Human3.6M dataset. Our results suggest that the use of labeling functions may provide a robust means to interpret and classify patient-oriented videos involving motor tasks.

An Individualized Multi-Modal Approach for Detection of Medication "Off" Episodes in Parkinson's Disease via Wearable Sensors.

The primary treatment for Parkinson's disease (PD) is supplementation of levodopa (L-dopa). With disease progression, people may experience motor and non-motor fluctuations, whereby the PD symptoms return before the next dose of medication. Paradoxically, in order to prevent wearing-off, one must take the next dose while still feeling well, as the upcoming off episodes can be unpredictable. Waiting until feeling wearing-off and then taking the next dose of medication is a sub-optimal strategy, as the medication can take up to an hour to be absorbed. Ultimately, early detection of wearing-off before people are consciously aware would be ideal. Towards this goal, we examined whether or not a wearable sensor recording autonomic nervous system (ANS) activity could be used to predict wearing-off in people on L-dopa. We had PD subjects on L-dopa record a diary of their on/off status over 24 hours while wearing a wearable sensor (E4 wristband®) that recorded ANS dynamics, including electrodermal activity (EDA), heart rate (HR), blood volume pulse (BVP), and skin temperature (TEMP). A joint empirical mode decomposition (EMD) / regression analysis was used to predict wearing-off (WO) time. When we used individually specific models assessed with cross-validation, we obtained > 90% correlation between the original OFF state logged by the patients and the reconstructed signal. However, a pooled model using the same combination of ASR measures across subjects was not statistically significant. This proof-of-principle study suggests that ANS dynamics can be used to assess the on/off phenomenon in people with PD taking L-dopa, but must be individually calibrated. More work is required to determine if individual wearing-off detection can take place before people become consciously aware of it.

Phytochemical Classification of Medicinal Plants Used in the Treatment of Kidney Disease Based on Traditional Persian Medicine.

Methods: This review was focused on studying the various secondary metabolites in model plants of Iranian herbal medicine known as treatment of kidney diseases in traditional Persian medicine textbooks including Makhzan-ol-Advieh, The Canon of Medicine, and Taghvim al-Abdan fi Tadbir al-Ensan. Results: Secondary metabolites of 94 medical plants belonging to 42 families were reported with their scientific and family name. Conclusion: Although herbal medicines are gaining rapid popularity among people and the pharmaceutical industry, the understandings of the phytochemical and therapeutic properties of medicinal plant are important for developing effective nephroprotective medicines. Therefore, the relationship between traditional uses and biological properties should be clearly verified through further studies.

Home EEG sleep assessment shows reduced slow-wave sleep in mild-moderate Alzheimer's disease.

Introduction: Sleep disturbances are common in Alzheimer's disease (AD), with estimates of prevalence as high as 65%. Recent work suggests that specific sleep stages, such as slow-wave sleep (SWS) and rapid eye movement (REM), may directly impact AD pathophysiology. A major limitation to sleep staging is the requirement for clinical polysomnography (PSG), which is often not well tolerated in patients with dementia. We have recently developed a deep learning model to reliably analyze lower quality electroencephalogram (EEG) data obtained from a simple, two-lead EEG headband. Here we assessed whether this methodology would allow for home EEG sleep staging in patients with mild-moderate AD. Methods: A total of 26 mild-moderate AD patients and 24 age-matched, healthy control participants underwent home EEG sleep recordings as well as actigraphy and subjective sleep measures through the Pittsburgh Sleep Quality Index (PSQI). Each participant wore the EEG headband for up to three nights. Sleep was staged using a deep learning model previously developed by our group, and sleep stages were correlated with actigraphy measures as well as PSQI scores. Results: We show that home EEG with a headband is feasible and well tolerated in patients with AD. Patients with mild-moderate AD were found to spend less time in SWS compared to healthy control participants. Other sleep stages were not different between the two groups. Actigraphy or the PSQI were not found to predict home EEG sleep stages. Discussion: Our data show that home EEG is well tolerated, and can ascertain reduced SWS in patients with mild-moderate AD. Similar findings have previously been reported, but using clinical PSG not suitable for the home environment. Home EEG will be particularly useful in future clinical trials assessing potential interventions that may target specific sleep stages to alter the pathogenesis of AD. Highlights: Home electroencephalogram (EEG) sleep assessments are important for measuring sleep in patients with dementia because polysomnography is a limited resource not well tolerated in this patient population.Simplified at-home EEG for sleep assessment is feasible in patients with mild-moderate Alzheimer's disease (AD).Patients with mild-moderate AD exhibit less time spent in slow-wave sleep in the home environment, compared to healthy control participants.Compared to healthy control participants, patients with mild-moderate AD spend more time in bed, with decreased sleep efficiency, and more awakenings as measured by actigraphy, but these measures do not correlate with EEG sleep stages.

Galvanic Vestibular Stimulation Effects on EEG Biomarkers of Motor Vigor in Parkinson's Disease.

Background: Impaired motor vigor (MV) is a critical aspect of Parkinson's disease (PD) pathophysiology. While MV is predominantly encoded in the basal ganglia, deriving (cortical) EEG measures of MV may provide valuable targets for modulation via galvanic vestibular stimulation (GVS). Objective: To find EEG features predictive of MV and examine the effects of high-frequency GVS. Methods: Data were collected from 20 healthy control (HC) and 18 PD adults performing 30 trials total of a squeeze bulb task with sham or multi-sine (50-100 Hz "GVS1" or 100-150 Hz "GVS2") stimuli. For each trial, we determined the time to reach maximum force after a "Go" signal, defined MV as the inverse of this time, and used the EEG data 1-sec prior to this time for prediction. We utilized 53 standard EEG features, including relative spectral power, harmonic parameters, and amplitude and phase of bispectrum corresponding to standard EEG bands from each of 27 EEG channels. We then used LASSO regression to select a sparse set of features to predict MV. The regression weights were examined, and separate band-specific models were developed by including only band-specific features (Delta, Theta, Alpha-low, Alpha-high, Beta, Gamma). The correlation between MV prediction and measured MV was used to assess model performance. Results: Models utilizing broadband EEG features were capable of accurately predicting MV (controls: 75%, PD: 81% of the variance). In controls, all EEG bands performed roughly equally in predicting MV, while in the PD group, the model using only beta band features did not predict MV well compared to other bands. Despite having minimal effects on the EEG feature values themselves, both GVS stimuli had significant effects on MV and profound effects on MV predictability via the EEG. With the GVS1 stimulus, beta-band activity in PD subjects became more closely associated with MV compared to the sham condition. With GVS2 stimulus, MV could no longer be accurately predicted from the EEG. Conclusions: EEG features can be a proxy for MV. However, GVS stimuli have profound effects on the relationship between EEG and MV, possibly via direct vestibulo-basal ganglia connections not measurable by the EEG.

Data-Driven Prediction of Fatigue in Parkinson's Disease Patients.

Introduction: Numerous non-motor symptoms are associated with Parkinson's disease (PD) including fatigue. The challenge in the clinic is to detect relevant non-motor symptoms while keeping patient-burden of questionnaires low and to take potential subgroups such as sex differences into account. The Fatigue Severity Scale (FSS) effectively detects clinically significant fatigue in PD patients. Machine learning techniques can determine which FSS items best predict clinically significant fatigue yet the choice of technique is crucial as it determines the stability of results. Methods: 182 records of PD patients were analyzed with two machine learning algorithms: random forest (RF) and Boruta. RF and Boruta calculated feature importance scores, which measured how much impact an FSS item had in predicting clinically significant fatigue. Items with the highest feature importance scores were the best predictors. Principal components analysis (PCA) grouped highly related FSS items together. Results: RF, Boruta and PCA demonstrated that items 8 ("Fatigue is among my three most disabling symptoms") and 9 ("Fatigue interferes with my work, family or social life") were the most important predictors. Item 5 ("Fatigue causes frequent problems for me") was an important predictor for females, and item 6 ("My fatigue prevents sustained physical functioning") was important for males. Feature importance scores' standard deviations were large for RF (14-66%) but small for Boruta (0-5%). Conclusion: The clinically most informative questions may be how disabling fatigue is compared to other symptoms and interference with work, family and friends. There may be some sex-related differences with frequency of fatigue-related complaints in females and endurance-related complaints in males yielding significant information. Boruta but not RF yielded stable results and might be a better tool to determine the most relevant components of abbreviated questionnaires. Further research in this area would be beneficial in order to replicate these findings with other machine learning algorithms, and using a more representative sample of PD patients.

A Deep Learning Strategy for Automatic Sleep Staging Based on Two-Channel EEG Headband Data.

Sleep disturbances are common in Alzheimer's disease and other neurodegenerative disorders, and together represent a potential therapeutic target for disease modification. A major barrier for studying sleep in patients with dementia is the requirement for overnight polysomnography (PSG) to achieve formal sleep staging. This is not only costly, but also spending a night in a hospital setting is not always advisable in this patient group. As an alternative to PSG, portable electroencephalography (EEG) headbands (HB) have been developed, which reduce cost, increase patient comfort, and allow sleep recordings in a person's home environment. However, naïve applications of current automated sleep staging systems tend to perform inadequately with HB data, due to their relatively lower quality. Here we present a deep learning (DL) model for automated sleep staging of HB EEG data to overcome these critical limitations. The solution includes a simple band-pass filtering, a data augmentation step, and a model using convolutional (CNN) and long short-term memory (LSTM) layers. With this model, we have achieved 74% (±10%) validation accuracy on low-quality two-channel EEG headband data and 77% (±10%) on gold-standard PSG. Our results suggest that DL approaches achieve robust sleep staging of both portable and in-hospital EEG recordings, and may allow for more widespread use of ambulatory sleep assessments across clinical conditions, including neurodegenerative disorders.

Simultaneous Analysis of 2D Echo Views for Left Atrial Segmentation and Disease Detection.

We propose a joint information approach for automatic analysis of 2D echocardiography (echo) data. The approach combines a priori images, their segmentations and patient diagnostic information within a unified framework to determine various clinical parameters, such as cardiac chamber volumes, and cardiac disease labels. The main idea behind the approach is to employ joint Independent Component Analysis of both echo image intensity information and corresponding segmentation labels to generate models that jointly describe the image and label space of echo patients on multiple apical views, instead of independently. These models are then both used for segmentation and volume estimation of cardiac chambers such as the left atrium and for detecting pathological abnormalities such as mitral regurgitation. We validate the approach on a large cohort of echoes obtained from 6,993 studies. We report performance of the proposed approach in estimation of the left-atrium volume and detection of mitral-regurgitation severity. A correlation coefficient of 0.87 was achieved for volume estimation of the left atrium when compared to the clinical report. Moreover, we classified patients that suffer from moderate or severe mitral regurgitation with an average accuracy of 82%.

Reward maximization justifies the transition from sensory selection at childhood to sensory integration at adulthood.

In a multisensory task, human adults integrate information from different sensory modalities--behaviorally in an optimal Bayesian fashion--while children mostly rely on a single sensor modality for decision making. The reason behind this change of behavior over age and the process behind learning the required statistics for optimal integration are still unclear and have not been justified by the conventional Bayesian modeling. We propose an interactive multisensory learning framework without making any prior assumptions about the sensory models. In this framework, learning in every modality and in their joint space is done in parallel using a single-step reinforcement learning method. A simple statistical test on confidence intervals on the mean of reward distributions is used to select the most informative source of information among the individual modalities and the joint space. Analyses of the method and the simulation results on a multimodal localization task show that the learning system autonomously starts with sensory selection and gradually switches to sensory integration. This is because, relying more on modalities--i.e. selection--at early learning steps (childhood) is more rewarding than favoring decisions learned in the joint space since, smaller state-space in modalities results in faster learning in every individual modality. In contrast, after gaining sufficient experiences (adulthood), the quality of learning in the joint space matures while learning in modalities suffers from insufficient accuracy due to perceptual aliasing. It results in tighter confidence interval for the joint space and consequently causes a smooth shift from selection to integration. It suggests that sensory selection and integration are emergent behavior and both are outputs of a single reward maximization process; i.e. the transition is not a preprogrammed phenomenon.

Learning active fusion of multiple experts' decisions: an attention-based approach.

In this letter, we propose a learning system, active decision fusion learning (ADFL), for active fusion of decisions. Each decision maker, referred to as a local decision maker, provides its suggestion in the form of a probability distribution over all possible decisions. The goal of the system is to learn the active sequential selection of the local decision makers in order to consult with and thus learn the final decision based on the consultations. These two learning tasks are formulated as learning a single sequential decision-making problem in the form of a Markov decision process (MDP), and a continuous reinforcement learning method is employed to solve it. The states of this MDP are decisions of the attended local decision makers, and the actions are either attending to a local decision maker or declaring final decisions. The learning system is punished for each consultation and wrong final decision and rewarded for correct final decisions. This results in minimizing the consultation and decision-making costs through learning a sequential consultation policy where the most informative local decision makers are consulted and the least informative, misleading, and redundant ones are left unattended. An important property of this policy is that it acts locally. This means that the system handles any nonuniformity in the local decision maker's expertise over the state space. This property has been exploited in the design of local experts. ADFL is tested on a set of classification tasks, where it outperforms two well-known classification methods, Adaboost and bagging, as well as three benchmark fusion algorithms: OWA, Borda count, and majority voting. In addition, the effect of local experts design strategy on the performance of ADFL is studied, and some guidelines for the design of local experts are provided. Moreover, evaluating ADFL in some special cases proves that it is able to derive the maximum benefit from the informative local decision makers and to minimize attending to redundant ones.