Geospatial Features Influencing the Formation of COVID-19 Clusters

Machine Learning methods have been used to combat COVID-19 since the pandemic has started in year 2020. In this regard, most studies have focused on detecting and identifying the characteristics of SARS-CoV-2, especially via image processing. Some studies have applied machine learning for contact tracing to minimise the transmission of COVID-19 cases. Limited work has, however, reported on how geospatial features have an influence on the transmission of COVID-19 and formation of clusters at local scale. Therefore, this paper has aimed to study the importance of geospatial features that had resorted to COVID-19 cluster formation in Kuala Lumpur, Malaysia in year 2021. Several datasets were used in this work, which have included the address details of confirmed positive COVID-19 cases and the details of nearby residential areas and Points of Interest (POI) located within the federal territory of Kuala Lumpur. The datasets were pre-processed and transformed into an analytical dataset for conducting empirical investigations. Various feature selection methods were applied, including the Boruta Algorithm, Chi-square (Chi2) Test, Extra Trees Classifier (ETC), Recursive Feature Elimination (RFE) method, and Deep Learning Autoencoder (DLA). Detailed investigations on the top-n features were performed to elicit a set of optimal features. Subsequently, several machine learning models were trained using the optimal features, including Logistic Regression (LR), Random Forest Classifier (RFC), Naïve Bayes Classifier (NBC), and Extreme Gradient Boosting (XGBoost). It was revealed that Boruta produced the optimal number of features with n = 96, whereas RFC achieved the best prediction results compared to other classifiers, with around 95% accuracy. Consequently, the findings in this paper help to recognize the geospatial features that have impacts on the formation of COVID-19 and other infectious disease clusters at local scale. © 2022, Success Culture Press. All rights reserved.

DECOVID-CT: Lightweight 3D CNN for COVID-19 Infection Prediction

The COVID-19 pandemic has become a critical threat to global health and the economy since its first outbreak in 2019. The standard diagnosis for COVID-19, Reverse Transcription Polymerase Chain Reaction (RT-PCR) is time consuming, and has lower sensitivity compared to CT-scans. Therefore, CT-scans can be used as a complementary method, alongside RT-PCR tests for COVID-19 infection prediction. However, manually reviewing CT scans is time consuming. In this paper, we propose DECOVID-CT, a deep learning model based on 3D convolutional neural network (CNN) for the detection of COVID-19 infection with CT images. The model is trained and tested on the RICORD dataset, a multinational dataset, for higher robustness. Our model achieved an accuracy of 100%, for predicting COVID-19 positive images. © 2022 IEEE.

Implementing hybrid telerehabilitation following major cardiac surgery during COVID-19 pandemic in Hong Kong

Background: Aerobic exercise is a critical component of cardiac rehabilitation (CR) for patients (pts) who have undergone cardiac surgery. Exercise-based CR is ideally home-based and directly supervised by a trained physiotherapist. During COVID-19 pandemic in Hong Kong, there was increasing emphasis on social distancing and caregiving strategies to better reach pts outside hospital. As most cardiac surgeries were performed on urgent clinical needs including heart transplantation and aortic dissection, we implemented hybrid telerehabilitation (HTR) with transition to the use of remote care in order to continue comprehensive CR. We report the functional outcome of HTR group compared with usual care (UC) group. Methods: From 7/2020 to10/2021, 36 pts ( 67% men, mean age 57±9.2 years) were enrolled into HTR (n=18) and UC (n=18) groups respectively for 12 weeks' duration. Demographics in both groups were similar. Types of cardiac surgeries were heart transplant (n=5;14%), CABG (n=6;17%), valvular surgery (n=17;47%) and aorta operation (n=8;22%). An individualized exercise prescription for HTR at home was determined based on initial standardized assessments in hospital and tailored to fit lifestyle and home environment. For HTR group, the goal is set at 150 minutes of low to moderate-intensity aerobic exercise per week at home. Exercise is progressed weekly based on daily metrics recorded by wearable device (exercise log and % target heart rate reserve (THRR) attained) and rate of perceived exertion (RPE). These were reported by pts through an online survey after each exercise session which were reviewed daily, with progress follow-up by phone calls or text messages on a weekly basis. Functional capacity parameters were evaluated using symptom limited exercise treadmill test (ETT) and 6 minute walk test (6MWT). The advised level is based on the current activity level of the patient using a MET score list at intake by the physiotherapist. Handgrip and quadriceps strength were measured. Results: All pts participated the programs. Both groups demonstrated significant improvement in MET scores and 6MWT after completion of CR programs.(Table ) Average exercise time at home was reported to be 379 ±98 minutes/ week (72% achieved >150 minutes/ week). Compared with UC, HTR showed significantly increased%change in MET score at baseline and upon completion of CR (22.1% vs 7%;p=0.02) and 6MWT (11.1% vs 5.3%;p=0.01). The effect muscle strength were similar in both groups with improving trend but no significant% change at baseline and end of CR. Conclusion: Significant improvement in functional status can be demonstrated in comprehensive individualized HTR program in pts after major cardiac surgery. Adoption of digital technology with full integration into standard cardiac rehabilitation program should be recommended. (Table Presented).