Brain computer interface (BCI) is an assistive technology, which decodes neurophysiological signals generated by the human brain and translates them into control signals to control external devices, e.g., wheelchairs. One problem challenging noninvasive BCI technologies is the limited control dimensions from decoding movements of, mainly, large body parts, e.g., upper and lower limbs. It has been reported that complicated dexterous functions, i.e., finger movements, can be decoded in electrocorticography (ECoG) signals, while it remains unclear whether noninvasive electroencephalography (EEG) signals also have sufficient information to decode the same type of movements. Phenomena of broadband power increase and low-frequency-band power decrease were observed in EEG in the present study, when EEG power spectra were decomposed by a principal component analysis (PCA). These movement-related spectral structures and their changes caused by finger movements in EEG are consistent with observations in previous ECoG study, as well as the results from ECoG data in the present study. The average decoding accuracy of 77.11% over all subjects was obtained in classifying each pair of fingers from one hand using movement-related spectral changes as features to be decoded using a support vector machine (SVM) classifier. The average decoding accuracy in three epilepsy patients using ECoG data was 91.28% with the similarly obtained features and same classifier. Both decoding accuracies of EEG and ECoG are significantly higher than the empirical guessing level (51.26%) in all subjects (p<0.05). The present study suggests the similar movement-related spectral changes in EEG as in ECoG, and demonstrates the feasibility of discriminating finger movements from one hand using EEG. These findings are promising to facilitate the development of BCIs with rich control signals using noninvasive technologies.

Early detection of Atrial Fibrillation (AFib) is crucial to prevent stroke recurrence. New tools for monitoring cardiac rhythm are important for risk stratification and stroke prevention. As many of new approaches to longterm AFib detection are now based on photoplethysmogram (PPG) recordings from wearable devices, ensuring high PPG signal-to-noise ratios is a fundamental requirement for a robust detection of AFib episodes. Traditionally, signal quality assessment is often based on the evaluation of similarity between pulses to derive signal quality indices. There are limitations to using this approach for accurate assessment of PPG quality in the presence of arrhythmia, as in the case of AFib, mainly due to substantial changes in pulse morphology. In this paper, we first tested the performance of algorithms selected from a body of studies on PPG quality assessment using a dataset of PPG recordings from patients with AFib. We then propose machine learning approaches for PPG quality assessment in 30-s segments of PPG recording from 13 stroke patients admitted to the University of California San Francisco (UCSF) neuro intensive care unit and another dataset of 3764 patients from one of the five UCSF general intensive care units. We used data acquired from two systems, fingertip PPG (fPPG) from a bedside monitor system, and radial PPG (rPPG) measured using a wearable commercial wristband. We compared various supervised machine learning techniques including knearest neighbors, decisions trees, and a two-class support vector machine (SVM). SVM provided the best performance. fPPG signals were used to build the model and achieved 0.9477 accuracy when tested on the data from the fPPG exclusive to the test set, and 0.9589 accuracy when tested on the rPPG data.

Existing research in infants has correlated electroencephalography (EEG) measures of power and coherence to cognitive development and to locomotor experience, but only in infants older than 5 months of age. Our goal was to explore the relationship between EEG measures of power and coherence and motor skill development in younger infants who are developing reaching skill. Twenty-one infants with typical development between 38 and 203 days of age participated. Longitudinal EEG recording sessions were recorded in monthly increments, with 3–5 sessions acquired for 19 participants and 1 session for 2 participants, resulting in 71 sessions in total. EEG variables of interest were relative power in the 6–9 Hz range and coherence between selected electrode pairs. We describe the development of the peak in relative power in the 6–9 Hz frequency band of EEG; it is not present around 1 month of age and starts to appear across the following months. Coherence generally increased in the bilateral frontal-parietal networks, while the interhemispheric connectivity in motor cortices generally decreased. The results of this relatively small pilot study provide a foundational description of neural function changes observed as motor skills are changing across the first half year of life. This is a first step in understanding experience-dependent plasticity of the infant brain and has the potential to aid in the early detection of atypical brain development.

Photoplethysmography (PPG) is a ubiquitous physiological measurement that detects beat-to-beat pulsatile blood volume changes and hence has a potential for monitoring cardiovascular conditions, particularly in ambulatory settings. A PPG dataset that is created for a particular use case is often imbalanced, due to a low prevalence of the pathological condition it targets to predict and the paroxysmal nature of the condition as well. To tackle this problem, we propose log-spectral matching GAN (LSM-GAN), a generative model that can be used as a data augmentation technique to alleviate the class imbalance in a PPG dataset to train a classifier. LSM-GAN utilizes a novel generator that generates a synthetic signal without a up-sampling process of input white noises, as well as adds the mismatch between real and synthetic signals in frequency domain to the conventional adversarial loss. In this study, experiments are designed focusing on examining how the influence of LSM-GAN as a data augmentation technique on one specific classification task - atrial fibrillation (AF) detection using PPG. We show that by taking spectral information into consideration, LSM-GAN as a data augmentation solution can generate more realistic PPG signals.

Parkinson's disease is a progressive neurodegenerative disease with complex, heterogeneous motor and non-motor symptoms. The current evidence shows that there is still a marked heterogeneity in the subtyping of Parkinson's disease using both clinical and data-driven approaches. Another challenge posed in PD subtyping is the reproducibility of previously identified PD subtypes. These issues require additional results to confirm previous findings and help reconcile discrepancies, as well as establish a standardized application of cluster analysis to facilitate comparison and reproducibility of identified PD subtypes. Our study aimed to address this gap by investigating subtypes of Parkinson's disease using comprehensive clinical (motor and non-motor features) data retrieved from 408 de novo Parkinson's disease patients with the complete clinical data in the Parkinson's Progressive Marker Initiative database. A standardized k-means cluster analysis approach was developed by taking into consideration of common practice and recommendations from previous studies. All data analysis codes were made available online to promote data comparison and validation of reproducibility across research groups. We identified two distinct PD subtypes, termed the severe motor-non-motor subtype (SMNS) and the mild motor- non-motor subtype (MMNS). SMNS experienced symptom onset at an older age and manifested more intense motor and non-motor symptoms than MMNS, who experienced symptom onset at a younger age and manifested milder forms of Parkinson's symptoms. The SPECT imaging makers supported clinical findings such that the severe motor-non-motor subtype showed lower binding values than the mild motor- non-motor subtype, indicating more significant neural damage at the nigral pathway. In addition, SMNS and MMNS show distinct motor (ANCOVA test: F = 47.35, p< 0.001) and cognitive functioning (F = 33.93, p< 0.001) progression trends. Such contrast between SMNS and MMNS in both motor and cognitive functioning can be consistently observed up to 3 years following the baseline visit, demonstrating the potential prognostic value of identified PD subtypes.