ABSTRACT
Despite the globally reducing hospitalization rates and the much lower risks of Covid-19 mortality, accurate diagnosis of the infection stage and prediction of outcomes are clinically of interest. Advanced current technology can facilitate automating the process and help identifying those who are at higher risks of developing severe illness. Deep-learning schemes including Visual Transformer and Convolutional Neural Networks (CNNs), in particular, are shown to be powerful tools for predicting clinical outcomes when fed with either CT scan images or clinical data of patients. This paper demonstrates how a novel 3D data fusion approach through concatenating CT scan images with patients clinical data can remarkably improve the performance of Visual Transformer and CNN models in predicting Covid-19 infection outcomes. Here, we explore and represent comprehensive research on the efficiency of Video Swin Transformers and a number of CNN models fed with fusion datasets and CT scans only vs a set of conventional classifiers fed with patients clinical data only. A relatively large clinical dataset from 380 Covid-19 diagnosed patients was used to train/test the models. Results show that the 3D Video Swin Transformers fed with the fusion datasets of 64 sectional CT scans+67 (or 30 selected) clinical labels outperformed all other approaches for predicting outcomes in Covid-19-infected patients amongst all techniques (i.e., TPR=0.95, FPR=0.40, F0.5 score=0.82, AUC=0.77, Kappa=0.6). Results indicate possibilities of predicting the severity of outcome using patients CT images and clinical data collected at the time of admission to hospital.
ABSTRACT
IntroductionCoronavirus Disease 2019 (COVID -19) pandemic challenged the healthcare system drastically, and it was concomitant with a remarkable decline in surgeries and modified routine care of patients worldwide. This systematic review and meta-analysis aimed to compare the surgical complications before COVID -19 (Pre-COVID) and after COVID -19 (post-COVID) appearance using the Clavien-Dindo classification (CDC). Methodsbetween January 1, 2019, to November 3, 2021, we performed a comprehensive search in PubMed/Medline and Scopus for studies reporting the postoperative complications based on/transformable to CDC. ResultFrom 909 screened articles, 34 studies were included for systematic review. Among included articles, 11 were eligible for meta-analysis. Nineteen thousand one hundred thirty-seven patients (pre-COVID: 3522, post-COVID: 15615) were included, mostly undergoing elective surgeries (86.32%). According to CDC classification, there were no significant change between pre-COVID and post-COVID for grade 1 (Odds ratio (OR) and 95% confidence interval (95-CI): 0.99, 0.60-1.63, p=0.96), grade 2 (OR and 95-CI: 0.65, 0.42-1.01, p = 0.055), grade 3 (OR and 95-CI: 0.86, 0.48-1.57, p=0.64), grade 4 (OR and 95-CI: 0.85, 0.46-1.57, p =0.60). However, the postoperative mortality was lower before the COVID -19 outbreak (OR and 95-CI: 0.51, 0.27-0.95, p= 0.035). The included studies for systematic review and meta-analysis had a low risk of bias and unsignificant publication bias. ConclusionAlthough delivering routine surgery was challenging, the postoperative complications during the pandemic remained identical to the pre-pandemic era. The stricter patient selection tending to choose more critical states and more advanced clinical stages of the operated patients may explain some extent of higher mortality during the pandemic. Adopting preventive strategies helped deliver surgeries during the outbreak of COVID -19 while limiting the capacity of operations and admissions.
