Automated system for classification of COVID-19 infection from lung CT images based on machine learning and deep learning techniques.

The objectives of our proposed study were as follows: First objective is to segment the CT images using a k-means clustering algorithm for extracting the region of interest and to extract textural features using gray level co-occurrence matrix (GLCM). Second objective is to implement machine learning classifiers such as Naïve bayes, bagging and Reptree to classify the images into two image classes namely COVID and non-COVID and to compare the performance of the three pre-trained CNN models such as AlexNet, ResNet50 and SqueezeNet with that of the proposed machine learning classifiers. Our dataset consists of 100 COVID and non-COVID images which are pre-processed and segmented with our proposed algorithm. Following the feature extraction process, three machine learning classifiers (Naive Bayes, Bagging, and REPTree) were used to classify the normal and covid patients. We had implemented the three pre-trained CNN models such as AlexNet, ResNet50 and SqueezeNet for comparing their performance with machine learning classifiers. In machine learning, the Naive Bayes classifier achieved the highest accuracy of 97%, whereas the ResNet50 CNN model attained the highest accuracy of 99%. Hence the deep learning networks outperformed well compared to the machine learning techniques in the classification of Covid-19 images.

Persistent COVID-19 symptoms at least one month after diagnosis: A national survey.

BACKGROUND: Post-acute COVID-19 syndrome (PACS) is an important healthcare burden. We examined persistent symptoms in COVID-19 patients at least four weeks after the onset of infection, participants' return to pre-COVID-19 health status and associated risk factors. METHODS: Cross-sectional study was conducted (December 2020 to January 2021). A validated online questionnaire was sent to randomly selected individuals aged more than 14 years from a total of 1397,386 people confirmed to have COVID-19 at least 4 weeks prior to the start of this survey. This sample was drawn from the Saudi ministry of health COVID-19 testing registry system. RESULTS: Out of the 9507 COVID-19 patients who responded to the survey, 5946 (62.5%) of them adequately completed it. 2895 patients (48.7%) were aged 35-44 years, 64.4% were males, and 91.5% were Middle Eastern or North African. 79.4% experienced unresolved symptoms for at least 4 weeks after the disease onset. 9.3% were hospitalized with 42.7% visiting healthcare facility after discharge and 14.3% requiring readmission. The rates of main reported persistent symptoms in descending order were fatigue 53.5%, muscle and body ache 38.2%, loss of smell 35.0%, joint pain 30.5%, and loss of taste 29.1%. There was moderate correlation between the number of symptoms at the onset and post-four weeks of COVID-19 infection. Female sex, pre-existing comorbidities, increased number of baseline symptoms, longer hospital-stay, and hospital readmission were predictors of delayed return to baseline health state (p < 0.05). CONCLUSION: The symptoms of PACS are prevalent after contracting COVID-19 disease. Several risk factors could predict delayed return to baseline health state.