An AI-enabled Bias-Free Respiratory Disease Diagnosis Model using Cough Audio: A Case Study for COVID-19 (preprint)

Cough-based diagnosis for Respiratory Diseases (RDs) using Artificial Intelligence (AI) has attracted considerable attention, yet many existing studies overlook confounding variables in their predictive models. These variables can distort the relationship between cough recordings (input data) and RD status (output variable), leading to biased associations and unrealistic model performance. To address this gap, we propose the Bias Free Network (RBFNet), an end to end solution that effectively mitigates the impact of confounders in the training data distribution. RBFNet ensures accurate and unbiased RD diagnosis features, emphasizing its relevance by incorporating a COVID19 dataset in this study. This approach aims to enhance the reliability of AI based RD diagnosis models by navigating the challenges posed by confounding variables. A hybrid of a Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM) networks is proposed for the feature encoder module of RBFNet. An additional bias predictor is incorporated in the classification scheme to formulate a conditional Generative Adversarial Network (cGAN) which helps in decorrelating the impact of confounding variables from RD prediction. The merit of RBFNet is demonstrated by comparing classification performance with State of The Art (SoTA) Deep Learning (DL) model (CNN LSTM) after training on different unbalanced COVID-19 data sets, created by using a large scale proprietary cough data set. RBF-Net proved its robustness against extremely biased training scenarios by achieving test set accuracies of 84.1%, 84.6%, and 80.5% for the following confounding variables gender, age, and smoking status, respectively. RBF-Net outperforms the CNN-LSTM model test set accuracies by 5.5%, 7.7%, and 8.2%, respectively

MICaFVi: A Novel Magnetic Immuno-Capture Flow Virometry Nano-Based Diagnostic Tool for Detection of Coronaviruses.

COVID-19 has resulted in a pandemic that aggravated the world's healthcare systems, economies, and education, and caused millions of global deaths. Until now, there has been no specific, reliable, and effective treatment to combat the virus and its variants. The current standard tedious PCR-based tests have limitations in terms of sensitivity, specificity, turnaround time, and false negative results. Thus, an alternative, rapid, accurate, and sensitive diagnostic tool that can detect viral particles, without the need for amplification or viral replication, is central to infectious disease surveillance. Here, we report MICaFVi (Magnetic Immuno-Capture Flow Virometry), a novel precise nano-biosensor diagnostic assay for coronavirus detection which combines the MNP-based immuno-capture of viruses for enrichment followed by flow-virometry analysis, enabling the sensitive detection of viral particles and pseudoviruses. As proof of concept, virus-mimicking spike-protein-coated silica particles (VM-SPs) were captured using anti-spike-antibody-conjugated MNPs (AS-MNPs) followed by detection using flow cytometry. Our results showed that MICaFVi can successfully detect viral MERS-CoV/SARS-CoV-2-mimicking particles as well as MERS-CoV pseudoviral particles (MERSpp) with high specificity and sensitivity, where a limit of detection (LOD) of 3.9 µg/mL (20 pmol/mL) was achieved. The proposed method has great potential for designing practical, specific, and point-of-care testing for rapid and sensitive diagnoses of coronavirus and other infectious diseases.

Injection Injury Caused by Disinfectant During COVID-19: A Case Report.

High-pressure injection injury of the hand is a rare but severe emergency, which requires full attention and timely treatment. However, the early symptoms may not be obvious. As the swelling and necrosis progress, the condition gradually worsens, and in severe cases, it may end with amputation. We report a particular case of a hand injection injury, which occurred to a worker who worked overtime to produce disinfectant during the Coronavirus Disease-19 (COVID-19) pandemic. Because of the chemical toxicity of the disinfectant and pressure's damage, although the emergency debridement was promptly performed, we still lost some fingers in the end. In the existing disinfection product manuals, we have not seen any tips on dealing with tissue injection injury. It may reduce workers' attention to injuries, leading to delays in emergency operations.

Risk Perception of International Medical Students About Coronavirus (COVID-19) in China and Their Willingness to Fly Back.

PURPOSE: This study aimed to investigate the willingness of international medical students enrolled in Chinese universities to return to their home countries based on their risk perception of the recent outbreak of the novel coronavirus disease (COVID-19). MATERIALS AND METHODS: A well-structured questionnaire was incorporated into the WeChat survey, a special feature within this mobile application, similar to Google Docs. The questionnaire was sent to 1190 international medical students across China between January 1, 2020 and May 15, 2020. A total of 897 completed questionnaires were returned, indicating a 75% response rate. RESULTS: The survey findings show that the risk perception of international medical students about COVID-19 was low because of the strong preventive measures taken by the Chinese government against COVID-19. Moreover, they were willing to stay in China until the completion of their degrees. In contrast, students who have completed their degrees were willing to return home immediately if possible. CONCLUSION: These findings are of serious concern for developing countries where they come from because their return to their home countries may cause an epidemic outbreak in those regions.