Diagnosis of COVID-19 Infection via Association Rules of Cough Encoding

[摘要] COVID-19 has roused the scientific community, prompting calls for immediate solutions to avoid the infection or at least reduce the virus's spread. Despite the availability of several licensed vaccinations to boost human immunity against the disease, various mutated strains of the virus continue to emerge, posing a danger to the vaccine's ecacy against new mutations. As a result, the importance of the early detection of COVID-19 infection becomes evident. Cough is a prevalent symptom in all COVID-19 mutations. Unfortunately, coughing can be a symptom of various of diseases, including pneumonia and inuenza. Thus, identifying the coughing behavior might help clinicians diagnose the COVID-19 infection earlier and distinguish coronavirus-induced from non-coronavirus-induced coughs. From this perspective, this research proposes a novel approach for diagnosing COVID-19 infection based on cough sound. The main contributions of this study are the encoding of cough behavior, the investigation of its unique characteristics, and the representation of these traits as association rules. These rules are generated and distinguished with the help of data mining and machine learning techniques. Experiments on the Virufy COVID-19 open cough dataset reveal that cough encoding can provide the desired accuracy (100%).

[学科分类] 医学（综合）

[关键词] COVID-19;cough encoding;spectral features;Apriori algorithm;association rules;SVM