CHIVID: A Rapid Deployment of Community and Home Isolation During COVID-19 Pandemics.

BACKGROUND: CHIVID is a telemedicine solution developed under tight time constraints that assists Thai healthcare practitioners in monitoring non-severe COVID-19 patients in isolation programs during crises. It assesses patient health and notifies healthcare practitioners of high-risk scenarios through a chatbot. The system was designed to integrate with the famous Thai messaging app LINE, reducing development time and enhancing user-friendliness, and the system allowed patients to upload a pulse oximeter image automatically processed by the PACMAN function to extract oxygen saturation and heart rate values to reduce patient input errors. METHODS: This article describes the proposed system and presents a mixed-methods study that evaluated the system's performance by collecting survey responses from 70 healthcare practitioners and analyzing 14,817 patient records. RESULTS: Approximately 71.4% of healthcare practitioners use the system more than twice daily, with the majority managing 1-10 patients, while 11.4% handle over 101 patients. The progress note is a function that healthcare practitioners most frequently use and are satisfied with. Regarding patient data, 58.9%(8,724/14,817) are male, and 49.7%(7,367/14,817) within the 18 to 34 age range. The average length of isolation was 7.6 days, and patients submitted progress notes twice daily on average. Notably, individuals aged 18 to 34 demonstrated the highest utilization rates for the PACMAN function. Furthermore, most patients, totaling over 95.52%(14,153/14,817), were discharged normally. CONCLUSION: The findings indicate that CHIVID could be one of the telemedicine solutions for hospitals with patient overflow and healthcare practitioners unfamiliar with telemedicine technology to improve patient care during a critical crisis. Clinical and Translational Impact Statement- CHIVID's success arises from seamlessly integrating telemedicine into third-party application within a limited timeframe and effectively using clinical decision support systems to address challenges during the COVID-19 crisis.

OCTAve: 2D En Face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning With Locality Augmentation.

OBJECTIVE: While the microvasculature annotation within Optical Coherence Tomography Angiography (OCTA) can be leveraged using deep-learning techniques, expensive annotation processes are required to create sufficient training data. One way to avoid the expensive annotation is to use a type of weak annotation in which only the center of the vessel is annotated. However, retaining the final segmentation quality with roughly annotated data remains a challenge. METHODS: Our proposed methods, called OCTAve, provide a new way of using weak-annotation for microvasculature segmentation. Since the centerline labels are similar to scribble annotations, we attempted to solve this problem by using the scribble-based weakly-supervised learning method. Even though the initial results look promising, we found that the method could be significantly improved by adding our novel self-supervised deep supervision method based on Kullback-Liebler divergence. RESULTS: The study on large public datasets with different annotation styles (i.e., ROSE, OCTA-500) demonstrates that our proposed method gives better quantitative and qualitative results than the baseline methods and a naive approach, with a p-value less than 0.001 on dice's coefficient and a lot fewer artifacts. CONCLUSION: The segmentation results are both qualitatively and quantitatively superior to baseline weakly-supervised methods when using scribble-based weakly-supervised learning augmented with self-supervised deep supervision, with an average drop in segmentation performance of less than 10%. SIGNIFICANCE: This work gives a new perspective on how weakly-supervised learning can be used to reduce the cost of annotating microvasculature, which can make the annotating process easier and reduce the amount of work for domain experts.

ANet: Autoencoder-Based Local Field Potential Feature Extractor for Evaluating an Antidepressant Effect in Mice After Administering Kratom Leaf Extracts.

Kratom (KT) typically exerts antidepressant (AD) effects. However, evaluating which form of KT extracts possesses AD properties similar to the standard AD fluoxetine (flu) remained challenging. Here, we adopted an autoencoder (AE)-based anomaly detector called ANet to measure the similarity of mice's local field potential (LFP) features that responded to KT leave extracts and AD flu. The features that responded to KT syrup had the highest similarity to those that responded to the AD flu at 87.11 ± 0.25%. This finding presents the higher feasibility of using KT syrup as an alternative substance for depressant therapy than KT alkaloids and KT aqueous, which are the other candidates in this study. Apart from the similarity measurement, we utilized ANet as a multi-task AE and evaluated the performance in discriminating multi-class LFP responses corresponding to the effect of different KT extracts and AD flu simultaneously. Furthermore, we visualized learned latent features among LFP responses qualitatively and quantitatively as t-SNE projection and maximum mean discrepancy distance, respectively. The classification results reported the accuracy and F1-score of 90.11 ± 0.11% and 90.08 ± 0.00%. In summary, the outcomes of this research might help therapeutic design devices for an alternative substance profile evaluation, such as Kratom-based form, in real-world applications.

EEGANet: Removal of Ocular Artifacts From the EEG Signal Using Generative Adversarial Networks.

The elimination of ocular artifacts is critical in analyzing electroencephalography (EEG) data for various brain-computer interface (BCI) applications. Despite numerous promising solutions, electrooculography (EOG) recording or an eye-blink detection algorithm is required for the majority of artifact removal algorithms. This reliance can hinder the model's implementation in real-world applications. This paper proposes EEGANet, a framework based on generative adversarial networks (GANs), to address this issue as a data-driven assistive tool for ocular artifacts removal (source code is available at https://github.com/IoBT-VISTEC/EEGANet). After the model was trained, the removal of ocular artifacts could be applied calibration-free without relying on the EOG channels or the eye blink detection algorithms. First, we tested EEGANet's ability to generate multi-channel EEG signals, artifacts removal performance, and robustness using the EEG eye artifact dataset, which contains a significant degree of data fluctuation. According to the results, EEGANet is comparable to state-of-the-art approaches that utilize EOG channels for artifact removal. Moreover, we demonstrated the effectiveness of EEGANet in BCI applications utilizing two distinct datasets under inter-day and subject-independent schemes. Despite the absence of EOG signals, the classification performance of the signals processed by EEGANet is equivalent to that of traditional baseline methods. This study demonstrates the potential for further use of GANs as a data-driven artifact removal technique for any multivariate time-series bio-signal, which might be a valuable step towards building next-generation healthcare technology.

MIN2Net: End-to-End Multi-Task Learning for Subject-Independent Motor Imagery EEG Classification.

OBJECTIVE: Advances in the motor imagery (MI)-based brain-computer interfaces (BCIs) allow control of several applications by decoding neurophysiological phenomena, which are usually recorded by electroencephalography (EEG) using a non-invasive technique. Despite significant advances in MI-based BCI, EEG rhythms are specific to a subject and various changes over time. These issues point to significant challenges to enhance the classification performance, especially in a subject-independent manner. METHODS: To overcome these challenges, we propose MIN2Net, a novel end-to-end multi-task learning to tackle this task. We integrate deep metric learning into a multi-task autoencoder to learn a compact and discriminative latent representation from EEG and perform classification simultaneously. RESULTS: This approach reduces the complexity in pre-processing, results in significant performance improvement on EEG classification. Experimental results in a subject-independent manner show that MIN2Net outperforms the state-of-the-art techniques, achieving an F1-score improvement of 6.72% and 2.23% on the SMR-BCI and OpenBMI datasets, respectively. CONCLUSION: We demonstrate that MIN2Net improves discriminative information in the latent representation. SIGNIFICANCE: This study indicates the possibility and practicality of using this model to develop MI-based BCI applications for new users without calibration.

Supervision of a self-driving vehicle unmasks latent sleepiness relative to manually controlled driving.

Human error has been implicated as a causal factor in a large proportion of road accidents. Automated driving systems purport to mitigate this risk, but self-driving systems that allow a driver to entirely disengage from the driving task also require the driver to monitor the environment and take control when necessary. Given that sleep loss impairs monitoring performance and there is a high prevalence of sleep deficiency in modern society, we hypothesized that supervising a self-driving vehicle would unmask latent sleepiness compared to manually controlled driving among individuals following their typical sleep schedules. We found that participants felt sleepier, had more involuntary transitions to sleep, had slower reaction times and more attentional failures, and showed substantial modifications in brain synchronization during and following an autonomous drive compared to a manually controlled drive. Our findings suggest that the introduction of partial self-driving capabilities in vehicles has the potential to paradoxically increase accident risk.

SleepPoseNet: Multi-View Learning for Sleep Postural Transition Recognition Using UWB.

Recognizing movements during sleep is crucial for the monitoring of patients with sleep disorders, and the utilization of ultra-wideband (UWB) radar for the classification of human sleep postures has not been explored widely. This study investigates the performance of an off-the-shelf single antenna UWB in a novel application of sleep postural transition (SPT) recognition. The proposed Multi-View Learning, entitled SleepPoseNet or SPN, with time series data augmentation aims to classify four standard SPTs. SPN exhibits an ability to capture both time and frequency features, including the movement and direction of sleeping positions. The data recorded from 38 volunteers displayed that SPN with a mean accuracy of 73.7 ±0.8 % significantly outperformed the mean accuracy of 59.9 ±0.7 % obtained from deep convolution neural network (DCNN) in recent state-of-the-art work on human activity recognition using UWB. Apart from UWB system, SPN with the data augmentation can ultimately be adopted to learn and classify time series data in various applications.

Potential Applications of Mobile and Wearable Devices for Psychological Support During the COVID-19 Pandemic: A Review.

The coronavirus disease 19 (COVID-19) pandemic that has been raging in 2020 does affect not only the physical state but also the mental health of the general population, particularly, that of the healthcare workers. Given the unprecedented large-scale impacts of the COVID-19 pandemic, digital technology has gained momentum as invaluable social interaction and health tracking tools in this time of great turmoil, in part due to the imposed state-wide mobilization limitations to mitigate the risk of infection that might arise from in-person socialization or hospitalization. Over the last five years, there has been a notable increase in the demand and usage of mobile and wearable devices as well as their adoption in studies of mental fitness. The purposes of this scoping review are to summarize evidence on the sweeping impact of COVID-19 on mental health as well as to evaluate the merits of the devices for remote psychological support. We conclude that the COVID-19 pandemic has inflicted a significant toll on the mental health of the population, leading to an upsurge in reports of pathological stress, depression, anxiety, and insomnia. It is also clear that mobile and wearable devices (e.g., smartwatches and fitness trackers) are well placed for identifying and targeting individuals with these psychological burdens in need of intervention. However, we found that most of the previous studies used research-grade wearable devices that are difficult to afford for the normal consumer due to their high cost. Thus, the possibility of replacing the research-grade wearable devices with the current smartwatch is also discussed.

MetaSleepLearner: A Pilot Study on Fast Adaptation of Bio-Signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning.

Identifying bio-signals based-sleep stages requires time-consuming and tedious labor of skilled clinicians. Deep learning approaches have been introduced in order to challenge the automatic sleep stage classification conundrum. However, the difficulties can be posed in replacing the clinicians with the automatic system due to the differences in many aspects found in individual bio-signals, causing the inconsistency in the performance of the model on every incoming individual. Thus, we aim to explore the feasibility of using a novel approach, capable of assisting the clinicians and lessening the workload. We propose the transfer learning framework, entitled MetaSleepLearner, based on Model Agnostic Meta-Learning (MAML), in order to transfer the acquired sleep staging knowledge from a large dataset to new individual subjects (source code is available at https://github.com/IoBT-VISTEC/MetaSleepLearner). The framework was demonstrated to require the labelling of only a few sleep epochs by the clinicians and allow the remainder to be handled by the system. Layer-wise Relevance Propagation (LRP) was also applied to understand the learning course of our approach. In all acquired datasets, in comparison to the conventional approach, MetaSleepLearner achieved a range of 5.4% to 17.7% improvement with statistical difference in the mean of both approaches. The illustration of the model interpretation after the adaptation to each subject also confirmed that the performance was directed towards reasonable learning. MetaSleepLearner outperformed the conventional approaches as a result from the fine-tuning using the recordings of both healthy subjects and patients. This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.

Orientation-modulated attention effect on visual evoked potential: Application for PIN system using brain-computer interface.

This research demonstrates the orientation-modulated attention effect on visual evoked potential. We combined this finding with our previous findings about the motion-modulated attention effect and used the result to develop novel visual stimuli for a personal identification number (PIN) application based on a brain-computer interface (BCI) framework. An electroencephalography amplifier with a single electrode channel was sufficient for our application. A computationally inexpensive algorithm and small datasets were used in processing. Seven healthy volunteers participated in experiments to measure offline performance. Mean accuracy was 83.3% at 13.9 bits/min. Encouraged by these results, we plan to continue developing the BCI-based personal identification application toward real-time systems.

Investigation of P300 response characteristics through human color vision-based visual stimulation.

In this study, we propose visual stimulation based on the primary colors (red, green, and blue) in order to investigate the characteristics of the P300 response. Eleven healthy volunteers participated in our experiment, and their brain signals were recorded by electroencephalography (EEG). Using two basic measures referred to as `on-peak' and `off-peak' for comparison of the P300 response among the participants, we found that the P300 response varies depending on the color of the stimulus. The results of this investigation are expected to contribute to various existing and future EEG-based applications.