Severe/critical COVID-19 early warning system based on machine learning algorithms using novel imaging scores

BACKGROUND Early identification of severe/critical coronavirus disease 2019(COVID-19)is crucial for timely treatment and intervention.Chest computed tomography(CT)score has been shown to be a significant factor in the diagnosis and treatment of pneumonia,however,there is currently a lack of effective early warning systems for severe/critical COVID-19 based on dynamic CT evolution.AIM To develop a severe/critical COVID-19 prediction model using a combination of imaging scores,clinical features,and biomarker levels.METHODS This study used an improved scoring system to extract and describe the chest CT characteristics of COVID-19 patients.The study also took into consideration the general clinical indicators such as dyspnea,oxygen saturation,alternative lengthening of telomeres(ALT),and androgen suppression treatment(AST),which are commonly associated with severe/critical COVID-19 cases.The study employed lasso regression to evaluate and rank the significance of different disease characteristics.RESULTS The results showed that blood oxygen saturation,ALT,IL-6/IL-10,combined score,ground glass opacity score,age,crazy paving mode score,qsofa,AST,and overall lung involvement score were key factors in predicting severe/critical COVID-19 cases.The study established a COVID-19 severe/critical early warning system using various machine learning algorithms,including XGBClassifier,Logistic Regression,MLPClassifier,RandomForestClassifier,and AdaBoost Classifier.The study concluded that the prediction model based on the improved CT score and machine learning algorithms is a feasible method for early detection of severe/critical COVID-19 evolution.CONCLUSION The findings of this study suggest that a prediction model based on improved CT scores and machine learning algorithms is effective in detecting the early warning signals of severe/critical COVID-19.

Evaluation of coronary artery bypass graft patency using three-dimensional reconstruction and flow study of electron beam tomography

Objective To establish and evaluate two protocols for the noninvasive visualization and assessment of coronary artery bypass graft (CABG) patency on electron beam tomography (EBT).Methods Two hundred and fourteen consecutive patients who underwent coronary artery bypass graft surgery were scanned using both EBT angiography with 3-dimensional reconstruction and EBT flow study with time-density-curve analysis.Results There were 589 CABGs evaluated in this study (10 grafts were excluded because of artifacts). Among them, 133 (98.5％) of 135 arterial grafts were patent, and 345 (77.7％) of 444 saphenous-vein grafts were patent. Within 5 years or between 5 and 10 years after operation, arterial graft patency exceeded venous graft patency (P ＜ 0.001 ). Three-dimensional EBT angiography achieved higher sensitivity, specificity and accuracy (97.7％, 94.1％ and 96.7％, respectively) than did EBT flow study (88.4％, 82.4％ and 85.2％, respectively) for evaluating occlusion or patency of CABG. The intra-graft flow of patent arterial and venous grafts were 4.9 ± 2.2 mi · min-1 · g-1 and 6.9 ± 2.8 mi · min-1 · g-1,respectively (P＜0.001).Conclusion The combination of EBT three-dimensional reconstruction and flow study can be more effective in the assessment of CABG anatomy and quantification of patent CABG blood flow.