Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 3 de 3
Filtrar
Añadir filtros

Tipo del documento
Intervalo de año
1.
Ieee Sensors Journal ; 20(22):13674-13681, 2020.
Artículo | Web of Science | ID: covidwho-907569

RESUMEN

Coronavirus Disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronaviruses 2 (SARS-CoV-2) has become a serious global pandemic in the past few months and caused huge loss to human society worldwide. For such a large-scale pandemic, early detection and isolation of potential virus carriers is essential to curb the spread of the pandemic. Recent studies have shown that one important feature of COVID-19 is the abnormal respiratory status caused by viral infections. During the pandemic, many people tend to wear masks to reduce the risk of getting sick. Therefore, in this paper, we propose a portable non-contact method to screen the health conditions of people wearing masks through analysis of the respiratory characteristics from RGB-infrared sensors. We first accomplish a respiratory data capture technique for people wearing masks by using face recognition. Then, a bidirectional GRU neural network with an attention mechanism is applied to the respiratory data to obtain the health screening result. The results of validation experiments show that our model can identify the health status of respiratory with 83.69% accuracy, 90.23% sensitivity and 76.31% specificity on the real-world dataset. This work demonstrates that the proposed RGB-infrared sensors on portable device can be used as a pre-scan method for respiratory infections, which provides a theoretical basis to encourage controlled clinical trials and thus helps fight the current COVID-19 pandemic. The demo videos of the proposed system are available at: https://doi.org/10.6084/m9.figshare.12028032.

2.
Ann Transl Med ; 8(14): 878, 2020 Jul.
Artículo en Inglés | MEDLINE | ID: covidwho-721676

RESUMEN

BACKGROUND: The 2019 coronavirus disease (COVID-19) has become a global pandemic. To date, although many studies have reported on the computed tomography (CT) manifestations of COVID-19, the vascular enlargement sign (VES) of COVID-19 has not been deeply examined, with the few available studies reporting an inconsistent prevalence. We thus performed a systematic review and meta-analysis based on the best available studies to estimate the prevalence and identify the underlying differential diagnostic value of VES. METHODS: We searched nine English and Chinese language databases up to April 23, 2020. Studies that evaluated CT features of COVID-19 patients and reported VES, with or without comparison with other pneumonia were included. The methodologic quality was assessed using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Meta-analyses with random effects models were performed to calculate the aggregate prevalence and pooled odds ratios (ORs) of VES. We also conducted meta-regression and subgroup analyses to analyze heterogeneity. RESULTS: VES findings from a total of 1969 patients were summarized and pooled across 22 studies. Our analysis demonstrated that the prevalence of VES among COVID-19 patients was 69.37% [95% confidence interval (CI): 57.40-79.20%]. Compared with non-COVID-19 patients, VES manifestation was more frequently observed in confirmed COVID-19 patients (OR =6.43, 95% CI: 3.39-12.22). Studies that explicitly defined distribution of VES in the lesion area demonstrated a significantly higher prevalence (P=0.03). Subgroup analyses also revealed a relatively higher VES rate in studies with a sample size larger than 50, but the difference was not statistically significant. No significant difference in VES rates was found between different countries (China/Italy), regions (Hubei/outside Hubei), average age groups (over/less than 50-year-old), or slice thicknesses of CT scan. Extensive heterogeneity was identified across most estimates (I2>80%). Some of the variations (R2=19.73%) could be explained by VES distribution, and sample size. No significant publication bias was seen (P=0.29). CONCLUSIONS: VES on thoracic CT was found in almost two-thirds of COVID-19 patients, and was more prevalent compared with that of the non-COVID-19 patients, supporting a promising role for VES in identifying pneumonia caused by coronavirus.

3.
Ann Transl Med ; 8(12): 749, 2020 Jun.
Artículo en Inglés | MEDLINE | ID: covidwho-639128

RESUMEN

BACKGROUND: Since the outbreak of COVID-19 in January, 2020, the fever of unknown origin (FUO) emergency department has become the first station for disease prevention and identification in hospitals. Establishing a standardized FUO emergency department within a short period of time has become the key to preventing and controlling COVID-19 in densely populated Chinese cities. METHODS: Based on the lean management model, the research group established a process of less-link visits, which sees reduced contact between patients and physicians during diagnosis and treatment, and zero-contact consultation through lean workflow and value stream analysis. Three steps were implemented to improve the operations of the FUO emergency department: the rapid establishment of an isolation zone, the refinement of duty and protection configuration, and the use of Internet and technology to establish a full-process follow-up consultation system. RESULTS: (I) Tests related to COVID-19 screening are all completed in the FUO emergency department; (II) 12 new isolated observation rooms have been built; (III) hospital visiting time, waiting time for consultation, and the time from pre-examination to virus screening has been shortened from 18 to 8 hours, from 2 hours to 10 minutes, and from 34 to 3 hours, respectively; (IV) the transfer distance has been shortened from 450 to 20 m, and the observation time has been shortened from 72 to 26 hours. The median waiting time for image examination has been reduced from 40 to 3 minutes, and the moving distance has been shortened from 800 to 10 m; (V) the diagnosis and treatment process is facilitated by 5G, achieving zero contact between doctors and patients. CONCLUSIONS: Through the implantation of information technology, the local transformation of the site, the rational allocation of medical teams and the planned distribution of protective equipment, in a short period of time, individual medical institutions can set up a safe FUO emergency department to provide 24-hour screening and detention services. Establishing an FUO emergency department with lean management and realizing the management approach of combining daily operation with prevention and control could help China and other countries to handle the outbreak of fulminant infectious diseases.

SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA