Smart Pre-Screening of Patients for COVID-19 using Depth-wise Separable Convolutional Neural Network

Hospitals have become a breeding ground for pathogens, as well as an overcrowded and overburdened environment. Even the testing mechanisms and kits are limited and expensive to produce. Coronavirus Disease 2019 (COVID-19) is an infectious respiratory and vascular condition (blood vessel). COVID-19 condition has very similar symptoms to colds, flu, strep throat, and other viral and bacterial diseases. Cough is a common symptom found in many conditions of pulmonary illnesses. Many medical pieces of literature emphasize the importance of automated, objective and reliable cough audio signal analysing systems that promise to detect pulmonary disorders. Healthcare costs associated with consultations on pulmonary medicine impose heavy financial burdens on the patients. The audio analysis of cough is noninvasive and cheap for the diagnosis of pulmonary disorders. This study investigated whether sophisticated machine learning algorithms could help diagnose COVID-19 utilizing cough audio signals, thus aiming to improve the good health and well-being of people (SDG-3). The main challenge is finding large amounts of audio data for good accuracy and reduced complexity of the system to result in a predictable outcome. The other challenges are extracting the right features from the data with the latter being distinguishable from noise, finding the memory requirements of devices portable enough to sense, analyse the real-time cough audio data and produce predictions on the person's health conditions. For such diseases, we propose a mechanism that combines Machine Learning with Neural Network Techniques and Hardware. Cepstral coefficients can be determined by analysing cough audio signals utilising the hardware setup. Therefore, by pre-screening and only sending patients to a hospital who are more likely to be infected, we can reduce the burden on the healthcare system. © The Electrochemical Society

Complement c3 a-chain as an indicator of disease severity in COVID-19

INTRODUCTION: As we combat the novel coronavirus SARS-CoV-2, elucidating its immunological pathogenesis is vital for both understanding and treating the disease. A few case studies have suggested that the complement system may play an important role in the course of infection, but its specific role is unclear. Our group has shown that higher circulating levels of the complement C3, particularly C3 α-chain, can be a significant predictor of survival in septic shock patients. We therefore sought to investigate if a similar relationship could be seen in SARS-CoV-2. METHODS: Thirty-six COVID-19 patients were consented for this study. Serial blood samples were collected at different time points from 22 patients not in the ICU and 14 in the ICU at the time of collection. The plasma samples were analyzed using Western Blot for circulating C3 α-chain levels. Clinical data on hematologic, respiratory, renal and coagulation status were collected. The data were analyzed for differences in ICU and Non-ICU patients and for correlations of C3 α-chain levels and clinical parameters. RESULTS: In ICU patients, in mean levels of C3 α-chain had a statistically significant increase from Days 0-5 since admission to Days 16-20 (p = 0.042). C3 α-chain levels were positively correlated with time since admission (R = 0.5401, p = 0.0115). In ICU patients, C3 α-chain levels were negatively correlated with Creatinine levels (R = -0.4515, p<0.05), Neutrophil Percentage (R = -0.5525, p<0.001) and Absolute Count (R = -0.6297, p<0.001) and positively correlated with Lymphocyte Percentage (R= 0.6748, p<0.001). In Non-ICU patients, C3 α-chain levels were negatively correlated with Neutrophil Percentage (R = -0.4929, p<0.05), BUN levels (R = -0.5055, p<0.001), and positively correlated with Lymphocyte Percentage (R = 0.45, p<0.05) and Absolute Count (R = 0.6134, p<0.001) and platelet levels (R = 0.4636, p<0.05). CONCLUSIONS: In summary, levels of circulating C3 α- chain increased with time in ICU patients. C3 α-chain levels negatively correlated with renal injury markers and systemic neutrophil levels. Moreover, C3 α-chain levels positively correlated with circulating lymphocyte levels. These results indicate that native C3 is important in fighting against COVID-19 infection and may be a critical prognostic marker of disease progression.