ABSTRACT
Although face masks as personal protective equipment (PPE) are recommended to control respiratory diseases with the on-going COVID-19 pandemic, improper handling and disinfection increase the risk of cross-contamination and compromise the effectiveness of PPE. Here, we prepared a self-cleaning mask based on a highly efficient aggregation-induced emission photosensitizer (TTCP-PF6) that can destroy pathogens by generating Type I and Type II reactive oxygen species (ROS). The respiratory pathogens, including influenza A virus H1N1 strain and Streptococcus pneumoniae (S. pneumoniae) can be inactivated within 10 min of ultra-low power (20 W/m2) white light or simulated sunlight irradiation. This TTCP-PF6-based self-cleaning strategy can also be used against other airborne pathogens, providing a strategy for dealing with different microbes.
Subject(s)
COVID-19 , Influenza A Virus, H1N1 Subtype , Wearable Electronic Devices , Humans , Photosensitizing Agents , COVID-19/prevention & control , Pandemics/prevention & controlSubject(s)
COVID-19 , Pharmaceutical Preparations , High-Throughput Screening Assays , Humans , Peptide Hydrolases , SARS-CoV-2ABSTRACT
The pandemic of Coronavirus Disease 2019 (COVID-19) is causing enormous loss of life globally. Prompt case identification is critical. The reference method is the real-time reverse transcription PCR (RT-PCR) assay, whose limitations may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before the onset of symptoms. We tested the hypothesis that the application of deep learning (DL) to 3D CT images could help identify COVID-19 infections. Using data from 920 COVID-19 and 1,073 non-COVID-19 pneumonia patients, we developed a modified DenseNet-264 model, COVIDNet, to classify CT images to either class. When tested on an independent set of 233 COVID-19 and 289 non-COVID-19 pneumonia patients, COVIDNet achieved an accuracy rate of 94.3% and an area under the curve of 0.98. As of March 23, 2020, the COVIDNet system had been used 11,966 times with a sensitivity of 91.12% and a specificity of 88.50% in six hospitals with PCR confirmation. Application of DL to CT images may improve both efficiency and capacity of case detection and long-term surveillance.