Driver Drowsiness Detection: A Machine Learning Approach on Skin Conductance.

The majority of car accidents worldwide are caused by drowsy drivers. Therefore, it is important to be able to detect when a driver is starting to feel drowsy in order to warn them before a serious accident occurs. Sometimes, drivers are not aware of their own drowsiness, but changes in their body signals can indicate that they are getting tired. Previous studies have used large and intrusive sensor systems that can be worn by the driver or placed in the vehicle to collect information about the driver's physical status from a variety of signals that are either physiological or vehicle-related. This study focuses on the use of a single wrist device that is comfortable for the driver to wear and appropriate signal processing to detect drowsiness by analyzing only the physiological skin conductance (SC) signal. To determine whether the driver is drowsy, the study tests three ensemble algorithms and finds that the Boosting algorithm is the most effective in detecting drowsiness with an accuracy of 89.4%. The results of this study show that it is possible to identify when a driver is drowsy using only signals from the skin on the wrist, and this encourages further research to develop a real-time warning system for early detection of drowsiness.

Efficient Low-Frequency SSVEP Detection with Wearable EEG Using Normalized Canonical Correlation Analysis.

Recent studies show that the integrity of core perceptual and cognitive functions may be tested in a short time with Steady-State Visual Evoked Potentials (SSVEP) with low stimulation frequencies, between 1 and 10 Hz. Wearable EEG systems provide unique opportunities to test these brain functions on diverse populations in out-of-the-lab conditions. However, they also pose significant challenges as the number of EEG channels is typically limited, and the recording conditions might induce high noise levels, particularly for low frequencies. Here we tested the performance of Normalized Canonical Correlation Analysis (NCCA), a frequency-normalized version of CCA, to quantify SSVEP from wearable EEG data with stimulation frequencies ranging from 1 to 10 Hz. We validated NCCA on data collected with an 8-channel wearable wireless EEG system based on BioWolf, a compact, ultra-light, ultra-low-power recording platform. The results show that NCCA correctly and rapidly detects SSVEP at the stimulation frequency within a few cycles of stimulation, even at the lowest frequency (4 s recordings are sufficient for a stimulation frequency of 1 Hz), outperforming a state-of-the-art normalized power spectral measure. Importantly, no preliminary artifact correction or channel selection was required. Potential applications of these results to research and clinical studies are discussed.

The risk of infection in patients with multiple sclerosis treated with disease-modifying therapies: A Delphi consensus statement.

The risk of infection associated with immunomodulatory or immunosuppressive disease-modifying drugs (DMDs) in patients with multiple sclerosis (MS) has been increasingly addressed in recent scientific literature. A modified Delphi consensus process was conducted to develop clinically relevant, evidence-based recommendations to assist physicians with decision-making in relation to the risks of a wide range of infections associated with different DMDs in patients with MS. The current consensus statements, developed by a panel of experts (neurologists, infectious disease specialists, a gynaecologist and a neuroradiologist), address the risk of iatrogenic infections (opportunistic infections, including herpes and cryptococcal infections, candidiasis and listeria; progressive multifocal leukoencephalopathy; human papillomavirus and urinary tract infections; respiratory tract infections and tuberculosis; hepatitis and gastrointestinal infections) in patients with MS treated with different DMDs, as well as prevention strategies and surveillance strategies for the early identification of infections. In the discussion, more recent data emerged in the literature were taken into consideration. Recommended risk reduction and management strategies for infections include screening at diagnosis and before starting a new DMD, prophylaxis where appropriate, monitoring and early diagnosis.

Vaccinations in patients with multiple sclerosis: A Delphi consensus statement.

BACKGROUND: Patients with multiple sclerosis (MS) are at increased risk of infection. Vaccination can mitigate these risks but only if safe and effective in MS patients, including those taking disease-modifying drugs. METHODS: A modified Delphi consensus process (October 2017-June 2018) was used to develop clinically relevant recommendations for making decisions about vaccinations in patients with MS. A series of statements and recommendations regarding the efficacy, safety and timing of vaccine administration in patients with MS were generated in April 2018 by a panel of experts based on a review of the published literature performed in October 2017. RESULTS: Recommendations include the need for an 'infectious diseases card' of each patient's infectious and immunisation history at diagnosis in order to exclude and eventually treat latent infections. We suggest the implementation of the locally recommended vaccinations, if possible at MS diagnosis, otherwise with vaccination timing tailored to the planned/current MS treatment, and yearly administration of the seasonal influenza vaccine regardless of the treatment received. CONCLUSION: Patients with MS should be vaccinated with careful consideration of risks and benefits. However, there is an urgent need for more research into vaccinations in patients with MS to guide evidence-based decision making.

Surviving COVID-19 in Bergamo province: a post-acute outpatient re-evaluation.

Bergamo province was badly hit by the coronavirus disease 2019 (COVID-19) epidemic. We organised a public-funded, multidisciplinary follow-up programme for COVID-19 patients discharged from the emergency department or from the inpatient wards of 'Papa Giovanni XXIII' Hospital, the largest public hospital in the area. As of 31 July, the first 767 patients had completed the first post-discharge multidisciplinary assessment. Patients entered our programme at a median time of 81 days after discharge. Among them, 51.4% still complained of symptoms, most commonly fatigue and exertional dyspnoea, and 30.5% were still experiencing post-traumatic psychological consequences. Impaired lung diffusion was found in 19%. Seventeen per cent had D-dimer values two times above the threshold for diagnosis of pulmonary embolism (two unexpected and clinically silent pulmonary thrombosis were discovered by investigating striking D-dimer elevation). Survivors of COVID-19 exhibit a complex array of symptoms, whose common underlying pathology, if any, has still to be elucidated: a multidisciplinary approach is fundamental, to address the different problems and to look for effective solutions.

A machine learning approach for automated wide-range frequency tagging analysis in embedded neuromonitoring systems.

EEG is a standard non-invasive technique used in neural disease diagnostics and neurosciences. Frequency-tagging is an increasingly popular experimental paradigm that efficiently tests brain function by measuring EEG responses to periodic stimulation. Recently, frequency-tagging paradigms have proven successful with low stimulation frequencies (0.5-6Hz), but the EEG signal is intrinsically noisy in this frequency range, requiring heavy signal processing and significant human intervention for response estimation. This limits the possibility to process the EEG on resource-constrained systems and to design smart EEG based devices for automated diagnostic. We propose an algorithm for artifact removal and automated detection of frequency tagging responses in a wide range of stimulation frequencies, which we test on a visual stimulation protocol. The algorithm is rooted on machine learning based pattern recognition techniques and it is tailored for a new generation parallel ultra low power processing platform (PULP), reaching performance of more that 90% accuracy in the frequency detection even for very low stimulation frequencies (<1Hz) with a power budget of 56mW.

Lamivudine/dolutegravir dual therapy in HIV-infected, virologically suppressed patients.

BACKGROUND: Little is known about the applicability of dual treatments based on integrase inhibitors. We explored the combination of lamivudine + dolutegravir as an option when switching from standard cART in virologically suppressed patients. METHODS: In this prospective cohort we enrolled patients previously switched to 3TC + DTG who were 18 years or older, with no previous resistance mutations to the used drugs, having a HIV-RNA <50 copies/ml for 6 months or longer, negative for HBsAg and on a stable (>6 months) cART. RESULTS: Ninety-four individuals were included. They were mostly men (77.7%) with a mean age of 53 years. They presented 159 co-morbidities including cardiovascular, bone, hepatic, kidney, and CNS diseases. Because of these pathologies, they took 207 non-ARV drugs (mean 2.2 per patient). Median duration of viral suppression was 77.5 months (IQR 61). All subjects were prospectively followed up to week 24 and all remained on dual therapy during the whole period. Neither virological failure, nor viral blip was detected. The median CD4 count rose from 658 cells/mcl (IQR 403) to 724 cells/mcl (IQR 401) (P = 0.006) without a significant (P = 0.44) change in the CD4/CD8 ratio. A significant (P < 0.0001) increment of median creatinine from 0.87 mg/dl (IQR 0.34) to 0.95 mg/dl (IQR 0.29) was observed in the first 2 months but thereafter leveled on these values (1.00 mg/dl; IQR 0.35) (P = 0.111 compared to 2 months). The lipid profile slightly improved. The daily cost of cART was significantly (P < 0.0001) reduced of 6.89 euros (SD 6.10). DISCUSSION: Switching to a dual cART regimen based on lamivudine + dolutegravir maintains virological efficacy up to week 24, and is associated to slight improvements of the immunologic and metabolic status. The strategy allows to freely using concomitant medications for associated pathologies. The dual therapy is less expensive in economic terms. CONCLUSION: Although still limited evidence exists, a dolutegravir-based dual therapy in combination with lamivudine shows promising results to be confirmed in larger controlled trials.

A Prosthetic Hand Body Area Controller Based on Efficient Pattern Recognition Control Strategies.

Poliarticulated prosthetic hands represent a powerful tool to restore functionality and improve quality of life for upper limb amputees. Such devices offer, on the same wearable node, sensing and actuation capabilities, which are not equally supported by natural interaction and control strategies. The control in state-of-the-art solutions is still performed mainly through complex encoding of gestures in bursts of contractions of the residual forearm muscles, resulting in a non-intuitive Human-Machine Interface (HMI). Recent research efforts explore the use of myoelectric gesture recognition for innovative interaction solutions, however there persists a considerable gap between research evaluation and implementation into successful complete systems. In this paper, we present the design of a wearable prosthetic hand controller, based on intuitive gesture recognition and a custom control strategy. The wearable node directly actuates a poliarticulated hand and wirelessly interacts with a personal gateway (i.e., a smartphone) for the training and personalization of the recognition algorithm. Through the whole system development, we address the challenge of integrating an efficient embedded gesture classifier with a control strategy tailored for an intuitive interaction between the user and the prosthesis. We demonstrate that this combined approach outperforms systems based on mere pattern recognition, since they target the accuracy of a classification algorithm rather than the control of a gesture. The system was fully implemented, tested on healthy and amputee subjects and compared against benchmark repositories. The proposed approach achieves an error rate of 1.6% in the end-to-end real time control of commonly used hand gestures, while complying with the power and performance budget of a low-cost microcontroller.

sEMG-driven Hand Dynamics Estimation with Incremental Online Learning on a Parallel Ultra-Low-Power Microcontroller.

Surface electromyography (sEMG) is a State-of-the-Art (SoA) sensing modality for non-invasive human-machine interfaces for consumer, industrial, and rehabilitation use cases. The main limitation of the current sEMG-driven control policies is the sEMG's inherent variability, especially cross-session due to sensor repositioning; this limits the generalization of the Machine/Deep Learning (ML/DL) in charge of the signal-to-command mapping. The other hot front on the ML/DL side of sEMG-driven control is the shift from the classification of fixed hand positions to the regression of hand kinematics and dynamics, promising a more versatile and fluid control. We present an incremental online-training strategy for sEMG-based estimation of simultaneous multi-finger forces, using a small Temporal Convolutional Network suitable for embedded learning-on-device. We validate our method on the HYSER dataset, cross-day. Our incremental online training reaches a cross-day Mean Absolute Error (MAE) of (9.58 ± 3.89)% of the Maximum Voluntary Contraction on HYSER's RANDOM dataset of improvised, non-predefined force sequences, which is the most challenging and closest to real scenarios. This MAE is on par with an accuracy-oriented, non-embeddable offline training exploiting more epochs. Further, we demonstrate that our online training approach can be deployed on the GAP9 ultra-low power microcontroller, obtaining a latency of 1.49 ms and an energy draw of just 40.4 uJ per forward-backward-update step. These results show that our solution fits the requirements for accurate and real-time incremental training-on-device.

Real-Time Motor Unit Tracking from sEMG Signals with Adaptive ICA on a Parallel Ultra-Low Power Processor.

Spike extraction by blind source separation (BSS) algorithms can successfully extract physiologically meaningful information from the sEMG signal, as they are able to identify motor unit (MU) discharges involved in muscle contractions. However, BSS approaches are currently restricted to isometric contractions, limiting their applicability in real-world scenarios. We present a strategy to track MUs across different dynamic hand gestures using adaptive independent component analysis (ICA): first, a pool of MUs is identified during isometric contractions, and the decomposition parameters are stored; during dynamic gestures, the decomposition parameters are updated online in an unsupervised fashion, yielding the refined MUs; then, a Pan-Tompkins-inspired algorithm detects the spikes in each MUs; finally, the identified spikes are fed to a classifier to recognize the gesture. We validate our approach on a 4-subject, 7-gesture + rest dataset collected with our custom 16-channel dry sEMG armband, achieving an average balanced accuracy of 85.58±14.91% and macro-F1 score of 85.86±14.48%. We deploy our solution onto GAP9, a parallel ultra-low-power microcontroller specialized for computation-intensive linear algebra applications at the edge, obtaining an energy consumption of 4.72 mJ @ 240 MHz and a latency of 121.3 ms for each 200 ms-long window of sEMG signal.

Minimizing artifact-induced false-alarms for seizure detection in wearable EEG devices with gradient-boosted tree classifiers.

Electroencephalography (EEG) is widely used to monitor epileptic seizures, and standard clinical practice consists of monitoring patients in dedicated epilepsy monitoring units via video surveillance and cumbersome EEG caps. Such a setting is not compatible with long-term tracking under typical living conditions, thereby motivating the development of unobtrusive wearable solutions. However, wearable EEG devices present the challenges of fewer channels, restricted computational capabilities, and lower signal-to-noise ratio. Moreover, artifacts presenting morphological similarities to seizures act as major noise sources and can be misinterpreted as seizures. This paper presents a combined seizure and artifacts detection framework targeting wearable EEG devices based on Gradient Boosted Trees. The seizure detector achieves nearly zero false alarms with average sensitivity values of [Formula: see text] for 182 seizures from the CHB-MIT dataset and [Formula: see text] for 25 seizures from the private dataset with no preliminary artifact detection or removal. The artifact detector achieves a state-of-the-art accuracy of [Formula: see text] (on the TUH-EEG Artifact Corpus dataset). Integrating artifact and seizure detection significantly reduces false alarms-up to [Formula: see text] compared to standalone seizure detection. Optimized for a Parallel Ultra-Low Power platform, these algorithms enable extended monitoring with a battery lifespan reaching 300 h. These findings highlight the benefits of integrating artifact detection in wearable epilepsy monitoring devices to limit the number of false positives.

Reducing False Alarms in Wearable Seizure Detection With EEGformer: A Compact Transformer Model for MCUs.

The long-term, continuous analysis of electroencephalography (EEG) signals on wearable devices to automatically detect seizures in epileptic patients is a high-potential application field for deep neural networks, and specifically for transformers, which are highly suited for end-to-end time series processing without handcrafted feature extraction. In this work, we propose a small-scale transformer detector, the EEGformer, compatible with unobtrusive acquisition setups that use only the temporal channels. EEGformer is the result of a hardware-oriented design exploration, aiming for efficient execution on tiny low-power micro-controller units (MCUs) and low latency and false alarm rate to increase patient and caregiver acceptance.Tests conducted on the CHB-MIT dataset show a 20% reduction of the onset detection latency with respect to the state-of-the-art model for temporal acquisition, with a competitive 73% seizure detection probability and 0.15 false-positive-per-hour (FP/h). Further investigations on a novel and challenging scalp EEG dataset result in the successful detection of 88% of the annotated seizure events, with 0.45 FP/h.We evaluate the deployment of the EEGformer on three commercial low-power computing platforms: the single-core Apollo4 MCU and the GAP8 and GAP9 parallel MCUs. The most efficient implementation (on GAP9) results in as low as 13.7 ms and 0.31 mJ per inference, demonstrating the feasibility of deploying the EEGformer on wearable seizure detection systems with reduced channel count and multi-day battery duration.

Increased prevalence of autoimmune thyroid disease after COVID-19: A single-center, prospective study.

Introduction: Thyroid dysfunctions associated with SARS-CoV-2 acute infection have been extensively described since the beginning of COVID-19 pandemics. Conversely, few data are available on the occurrence of thyroid autoimmunity after COVID-19 resolution. We assessed the prevalence of autoimmune thyroid disease (ATD) and thyroid dysfunctions in COVID-19 survivors three months after hospital admission. Design and methods: Single-center, prospective, observational, cohort study performed at ASST Papa Giovanni XXIII Hospital, Bergamo, Italy. 599 COVID-19 survivors were prospectively evaluated for thyroid function and autoimmunity thyroperoxidase antibodies (TPOAb), thyroglobulin antibodies (TgAb). When a positive antibody concentration was detected, thyroid ultrasound was performed. Multiple logistic regression model was used to estimate the association between autoimmunity and demographic characteristics, respiratory support, and comorbidities. Autoimmunity results were compared to a cohort of 498 controls referred to our Institution for non-thyroid diseases before the pandemic onset. A sensitivity analysis comparing 330 COVID-19 patients with 330 age and sex-matched controls was performed. Results: Univariate and multivariate analysis found that female sex was positively associated (OR 2.01, SE 0.48, p = 0.003), and type 2 diabetes (T2DM) was negatively associated (OR 0.36, SE 0.16, p = 0.025) with thyroid autoimmunity; hospitalization, ICU admission, respiratory support, or COVID-19 treatment were not associated with thyroid autoimmunity (p > 0.05). TPOAb prevalence was greater in COVID-19 survivors than in controls: 15.7% vs 7.7%, p = 0.002. Ultrasonographic features of thyroiditis were present in 94.9% of the evaluated patients with positive antibodies. TSH was within the normal range in 95% of patients. Conclusions: Autoimmune thyroid disease prevalence in COVID-19 survivors was doubled as compared to age and sex-matched controls, suggesting a role of SARS-CoV-2 in eliciting thyroid autoimmunity.

Vaccination Recommendations in Solid Organ Transplant Adult Candidates and Recipients.

Prevention of infections is crucial in solid organ transplant (SOT) candidates and recipients. These patients are exposed to an increased infectious risk due to previous organ insufficiency and to pharmacologic immunosuppression. Besides infectious-related morbidity and mortality, this vulnerable group of patients is also exposed to the risk of acute decompensation and organ rejection or failure in the pre- and post-transplant period, respectively, since antimicrobial treatments are less effective than in the immunocompetent patients. Vaccination represents a major preventive measure against specific infectious risks in this population but as responses to vaccines are reduced, especially in the early post-transplant period or after treatment for rejection, an optimal vaccination status should be obtained prior to transplantation whenever possible. This review reports the currently available data on the indications and protocols of vaccination in SOT adult candidates and recipients.

BioWolf16: a 16-channel, 24-bit, 4kSPS Ultra-Low Power Platform for Wearable Clinical-grade Bio-potential Parallel Processing and Streaming.

Low-power wearable systems are essential for medical and industrial applications, but they face crucial implementation challenges when providing energy-efficient compact design while increasing the number of available channels, sampling rate and overall processing power. This work presents a small (39×41mm) wireless embedded low-power HMI device for ExG signals, offering up to 16 channels sampled at up to 4kSPS. By virtue of the high sampling rate and medical-grade signal quality (i.e. compliant with the IFCN standards), BioWolf16 is capable of accurate gesture recognition and enables the possibility to acquire data for neural spikes extraction. When employed over an EMG gesture recognition paradigm, the system achieves 90.24% classification accuracy over nine gestures (16 channels @4kSPS) while requiring only 16mW of power (57h of continuous operation) when deployed on Mr. Wolf MCU, part of the system architecture. The system can also provide up to 14h of real-time data streaming (4kSPS), which can further be extended to 23h when reducing the sampling rate to 1kSPS. Our results also demonstrate that this design outperforms many features of current state-of-the-art systems. Clinical Relevance - This work establishes that BioWolf16 is a wearable ultra-low power device enabling advanced multi-channel streaming and processing of medical-grade EMG signal, that can expand research opportunities and applications in healthcare and industrial scenarios.

Energy-Efficient Tree-Based EEG Artifact Detection.

In the context of epilepsy monitoring, EEG artifacts are often mistaken for seizures due to their morphological simi-larity in both amplitude and frequency, making seizure detection systems susceptible to higher false alarm rates. In this work we present the implementation of an artifact detection algorithm based on a minimal number of EEG channels on a parallel ultra-low-power (PULP) embedded platform. The analyses are based on the TUH EEG Artifact Corpus dataset and focus on the temporal electrodes. First, we extract optimal feature models in the frequency domain using an automated machine learning framework, achieving a 93.95% accuracy, with a 0.838 F1 score for a 4 temporal EEG channel setup. The achieved accuracy levels surpass state-of-the-art by nearly 20%. Then, these algorithms are parallelized and optimized for a PULP platform, achieving a 5.21x improvement of energy-efficient compared to state-of-the-art low-power implementations of artifact detection frameworks. Combining this model with a low-power seizure detection algorithm would allow for 300h of continuous monitoring on a 300 mAh battery in a wearable form factor and power budget. These results pave the way for implementing affordable, wearable, long-term epilepsy monitoring solutions with low false-positive rates and high sensitivity, meeting both patients' and caregivers' requirements. Clinical relevance- The proposed EEG artifact detection framework can be employed on wearable EEG recording devices, in combination with EEG-based epilepsy detection algorithms, for improved robustness in epileptic seizure detection scenarios.

A Wireless System for EEG Acquisition and Processing in an Earbud Form Factor with 600 Hours Battery Lifetime.

In recent years, in-ear electroencephalography (EEG) was demonstrated to record signals of similar quality compared to standard scalp-based EEG, and clinical applications of objective hearing threshold estimations have been reported. Existing devices, however, still lack important features. In fact, most of the available solutions are based on wet electrodes, require to be connected to external acquisition platforms, or do not offer on-board processing capabilities. Here we overcome all these limitations, presenting an ear-EEG system based on dry electrodes that includes all the acquisition, processing, and connectivity electronics directly in the ear bud. The earpiece is equipped with an ultra-low power analog front-end for analog-to-digital conversion, a low-power MEMS microphone, a low-power inertial measurement unit, and an ARM Cortex-M4 based microcontroller enabling on-board processing and Bluetooth Low Energy connectivity. The system can stream raw EEG data or perform data processing directly in-ear. We test the device by analysing its capability to detect brain response to external auditory stimuli, achieving 4 and 1.3 mW power consumption for data streaming or on board processing, respectively. The latter allows for 600 hours operation on a PR44 zinc-air battery. To the best of our knowledge, this is the first wireless and fully self-contained ear-EEG system performing on-board processing, all embedded in a single earbud. Clinical relevance- The proposed ear-EEG system can be employed for diagnostic tasks such as objective hearing threshold estimations, outside of clinical settings, thereby enabling it as a point-of-care solution. The long battery lifetime is also suitable for a continuous monitoring scenario.

An Ensemble of Hyperdimensional Classifiers: Hardware-Friendly Short-Latency Seizure Detection With Automatic iEEG Electrode Selection.

We propose a new algorithm for detecting epileptic seizures. Our algorithm first extracts three features, namely mean amplitude, line length, and local binary patterns that are fed to an ensemble of classifiers using hyperdimensional (HD) computing. These features are embedded into prototype vectors representing ictal (during seizures) and interictal (between seizures) brain states are constructed. These vectors can be computed at different spatial scales ranging from a single electrode up to many electrodes. This flexibility allows our algorithm to identify the electrodes that discriminate best between ictal and interictal brain states. We assess our algorithm on the SWEC-ETHZ iEEG dataset that includes 99 short-time iEEG seizures recorded with 36 to 100 electrodes from 16 drug-resistant epilepsy patients. Using k-fold cross-validation and all electrodes, our algorithm surpasses state-of-the-art algorithms yielding significantly shorter latency (8.81 s vs. 11.57 s) in seizure onset detection, and higher specificity (97.31% vs. 94.84%) and accuracy (96.85% vs. 95.42%). We can further reduce the latency of our algorithm to 3.74 s by allowing a slightly higher percentage of false alarms (2% specificity loss). Using only the top 10% of the electrodes ranked by our algorithm, we still maintain superior latency, sensitivity, and specificity compared to the other algorithms with all the electrodes. We finally demonstrate the suitability of our algorithm to deployment on low-cost embedded hardware platforms, thanks to its robustness to noise/artifacts affecting the signal, its low computational complexity, and the small memory-footprint on a RISC-V microcontroller.