RESUMEN
BACKGROUND: Recovery from acute COVID-19 may be slow and incomplete: cases of Post-Acute Sequelae of COVID (PASC) are counted in millions, worldwide. We aimed to explore if and how the pre-existing Socio-economic-status (SES) influences such recovery. METHODS: We analyzed a database of 1536 consecutive patients from the first wave of COVID-19 in Italy (February-September 2020), previously admitted to our referral hospital, and followed-up in a dedicated multidisciplinary intervention. We excluded those seen earlier than 12 weeks (the conventional limit for a possible PASC syndrome), and those reporting a serious complication from the acute phase (possibly accounting for symptoms persistence). We studied whether the exposition to disadvantaged SES (estimated through the Italian Institute of Statistics's model - ISTAT 2017) was affecting recovery outcomes, that is: symptoms (composite endpoint, i.e. at least one among: dyspnea, fatigue, myalgia, chest pain or palpitations); Health-Related-Quality-of-Life (HRQoL, as by SF-36 scale); post-traumatic-stress-disorder (as by IES-R scale); and lung structural damage (as by impaired CO diffusion, DLCO). RESULTS: Eight-hundred and twenty-five patients were included in the analysis (median age 59 years; IQR: 50-69 years, 60.2% men), of which 499 (60.5%) were previously admitted to hospital and 27 (3.3%) to Intensive-Care Unit (ICU). Those still complaining of symptoms at follow-up were 337 (40.9%; 95%CI 37.5-42.2%), and 256 had a possible Post-Traumatic Stress Disorder (PTSD) (31%, 95%CI 28.7-35.1%). DLCO was reduced in 147 (19.6%, 95%CI 17.0-22.7%). In a multivariable model, disadvantaged SES was associated with a lower HRQoL, especially for items exploring physical health (Limitations in physical activities: OR = 0.65; 95%CI = 0.47 to 0.89; p = 0.008; AUC = 0.74) and Bodily pain (OR = 0.57; 95%CI = 0.40 to 0.82; p = 0.002; AUC = 0.74). We did not observe any association between SES and the other outcomes. CONCLUSIONS: Recovery after COVID-19 appears to be independently affected by a pre-existent socio-economic disadvantage, and clinical assessment should incorporate SES and HRQoL measurements, along with symptoms. The socioeconomic determinants of SARS-CoV-2 disease are not exclusive of the acute infection: this finding deserves further research and specific interventions.
Asunto(s)
COVID-19 , Síndrome Post Agudo de COVID-19 , Calidad de Vida , SARS-CoV-2 , Humanos , COVID-19/psicología , COVID-19/epidemiología , COVID-19/complicaciones , Italia/epidemiología , Masculino , Femenino , Persona de Mediana Edad , Anciano , Estudios de Cohortes , Factores Socioeconómicos , AdultoRESUMEN
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.
RESUMEN
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.
Asunto(s)
Electromiografía , Mano , Humanos , Mano/fisiología , Masculino , Procesamiento de Señales Asistido por Computador , Adulto , Fenómenos Biomecánicos , Aprendizaje Automático , Femenino , Aprendizaje ProfundoRESUMEN
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.
Asunto(s)
Epilepsia , Dispositivos Electrónicos Vestibles , Humanos , Algoritmos , Artefactos , Electroencefalografía , Epilepsia/diagnóstico , Convulsiones/diagnósticoRESUMEN
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.