PSTCNN: Explainable COVID-19 diagnosis using PSO-guided self-tuning CNN

Since 2019, the coronavirus disease-19 (COVID-19) has been spreading rapidly worldwide, posing an unignorable threat to the global economy and human health. It is a disease caused by severe acute respiratory syndrome coronavirus 2, a single-stranded RNA virus of the genus Betacoronavirus. This virus is highly infectious and relies on its angiotensin-converting enzyme 2-receptor to enter cells. With the increase in the number of confirmed COVID-19 diagnoses, the difficulty of diagnosis due to the lack of global healthcare resources becomes increasingly apparent. Deep learning-based computer-aided diagnosis models with high generalisability can effectively alleviate this pressure. Hyperparameter tuning is essential in training such models and significantly impacts their final performance and training speed. However, traditional hyperparameter tuning methods are usually time-consuming and unstable. To solve this issue, we introduce Particle Swarm Optimisation to build a PSO-guided Self-Tuning Convolution Neural Network (PSTCNN), allowing the model to tune hyperparameters automatically. Therefore, the proposed approach can reduce human involvement. Also, the optimisation algorithm can select the combination of hyperparameters in a targeted manner, thus stably achieving a solution closer to the global optimum. Experimentally, the PSTCNN can obtain quite excellent results, with a sensitivity of 93.65% ± 1.86%, a specificity of 94.32% ± 2.07%, a precision of 94.30% ± 2.04%, an accuracy of 93.99% ± 1.78%, an F1-score of 93.97% ± 1.78%, Matthews Correlation Coefficient of 87.99% ± 3.56%, and Fowlkes-Mallows Index of 93.97% ± 1.78%. Our experiments demonstrate that compared to traditional methods, hyperparameter tuning of the model using an optimisation algorithm is faster and more effective. [ FROM AUTHOR]

A comparative study of SARS-CoV-2 nucleic acid assay for nasal swab and sputum samples

Objective: To analyze nucleic acid detection results of coronavirus disease 2019 (COVID-19) patients' nasal swabs and sputum specimens, and we provide reference for clinical sampling methods.

Early Viral Clearance and Antibody Kinetics of COVID-19 Among Asymptomatic Carriers.

Asymptomatic carriers contribute to the spread of Coronavirus Disease 2019 (COVID-19), but their clinical characteristics, viral kinetics, and antibody responses remain unclear. A total of 56 COVID-19 patients without symptoms at admission and 19 age-matched symptomatic patients were enrolled. RNA of SARS-CoV-2 was tested using transcriptase quantitative PCR, and the total antibodies (Ab), IgG, IgA, and IgM against the SARS-CoV-2 were tested using Chemiluminescence Microparticle Immuno Assay. Among 56 patients without symptoms at admission, 33 cases displayed symptoms and 23 remained asymptomatic throughout the follow-up period. 43.8% of the asymptomatic carriers were children and none of the asymptomatic cases had recognizable changes in C-reactive protein or interleukin-6, except one 64-year-old patient. The initial threshold cycle value of nasopharyngeal SARS-CoV-2 in asymptomatic carriers was similar to that in pre-symptomatic and symptomatic patients, but the positive viral nucleic acid detection period of asymptomatic carriers (9.63 days) was shorter than pre-symptomatic patients (13.6 days). There were no obvious differences in the seropositive conversion rate of total Ab, IgG, and IgA among the three groups, though the rates of IgM varied largely. The average peak IgG and IgM COI of asymptomatic cases was 3.5 and 0.8, respectively, which is also lower than those in symptomatic patients with peaked IgG and IgM COI of 4.5 and 2.4 (p < 0.05). Young COVID-19 patients seem to be asymptomatic cases with early clearance of SARS-CoV-2 and low levels of IgM generation but high total Ab, IgG, and IgA. Our findings provide empirical information for viral clearance and antibody kinetics of asymptomatic COVID-19 patients.

Clinical Outcomes in 55 Patients With Severe Acute Respiratory Syndrome Coronavirus 2 Who Were Asymptomatic at Hospital Admission in Shenzhen, China.

An epidemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has spread unexpectedly in Wuhan, Hubei Province, China, since December 2019. There are few reports about asymptomatic contacts of infected patients identified as positive for SARS-CoV-2 through screening. We studied the epidemiological and clinical outcomes in 55 asymptomatic carriers who were laboratory confirmed to be positive for SARS-CoV-2 through nucleic acid testing of pharyngeal swab samples. The asymptomatic carriers seldom occurred among young people (aged 18-29 years) who had close contact with infected family members. In the majority of patients, the outcome was mild or ordinary 2019 novel coronavirus disease during hospitalization.