Relation of Ultrasound Morphologic Characteristics of Central Pulmonary Artery Thromboemboli to Their Ex Vivo Lysibility

Development of a Machine Learning-Assisted Model for the Early Detection of Severe COVID-19 Cases Combining Blood Test and Quantitative Computed Tomography Parameters

<sec> <title>Purpose:</title> This study aimed to identify severe Coronavirus Disease 2019 (COVID-19) cases combining blood test results and imaging parameters based on a machine learning classifier at the initial admission. </sec> <sec> <title>Materials and methods:</title> Ninety-five non-severe and 22 severe laboratory-confirmed COVID-19 cases treated between January 23, 2020 and March 25, 2020 were examined in this retrospective trial. Blood test results and chest computed tomography (CT) images were obtained at the initial admission. The lesions on CT images were segmented using an artificial intelligent (AI) tool. Then, quantitative CT (QCT) parameters, including the volume, percentage, ground glass opacity (GGO) percentage and heterogeneity of the lesions were calculated. Correlations of blood test results and QCT parameters were analyzed by the Pearson test first. Then, discriminative features for detecting severe cases were selected by both the independent samples t test and least absolute shrinkage and selection operator (LASSO) regression. Next, support vector machine (SVM), Gaussian naïve Bayes (GNB), Knearest neighbor (KNN), decision tree (DT), random forest (RF) and multi-layer perceptron-neural net (MLP-NN) algorithms were used as classifiers, and their accuracies were assessed by 10-fold-cross-validation. </sec> <sec> <title>Results:</title> Blood test indexes and CT parameters were moderately to medially correlated. Of all selected features, lesion percentage contributed mostly to the classification of the two groups, followed by lesion volume, patient age, lymphocyte count, neutrophil count, GGO percentage and tumor heterogeneity. RF-assisted identification had the highest accuracy of 91.38%, followed by GNB (87.83%), KNN (87.93%), SVM (86.21%), MLP-NN (85.34%) and DT (84.48%). </sec> <sec> <title>Conclusions:</title> The RF-assisted model combining blood test and QCT parameters is helpful in the identification of severe COVID-19 cases. </sec>

A triad algorithm for analysing individual ante- and post-mortem findings to improve the quality of intensive care

Autopsy is an important source of data for education and quality control. The aim of this study was comparison of ante- to post-mortem findings to detect weak points of intensive care unit (ICU) care. Patients who died in our 14-bed university medical ICU care and underwent an autopsy examination over 20 months (September 2007 to May 2009) were included. Modified Goldman's criteria were used to categorise discrepancies between diagnoses and post-mortem findings. A triad algorithm was constructed to analyse individual ante- to post-mortem findings. One hundred and seventy post-mortem examinations were conducted (45.6% autopsy rate). Major diagnostic discrepancies were detected in 20 patients (11.8%); four class I (2.4%) and 16 class II (9.4%). Massive pulmonary embolism with cardiac arrest was the most common class I discrepancy (75%). Triad analysis of major class I discrepancies showed that all patients had a history of chronic disease; the majority (75%) had a short ICU length of stay. In 75% adequate tests were used to detect disorders. There were interpretation problems of bedside data in complex emergency clinical conditions, especially with less experienced ICU physicians. Inappropriate or incorrectly interpreted diagnostic procedures were performed in more than half of cases with class II discrepancies (9/16, 56%). Abdominal ultrasonography was misleading in 31% (5/16) cases with class II discrepancies. In conclusion, triad algorithm analysis revealed problematic interpretation of bedside diagnostics in emergency cases by inexperienced physicians in class I major discrepancies detected at autopsy. No correct test and wrong interpretation of abdominal ultrasonography were major causes of class II discrepancies.

Acute ECG ST-segment elevation mimicking myocardial infarction in a patient with pulmonary embolism

Pulmonary embolism is a common cardiovascular emergency, but it is still often misdiagnosed due to its unspecific clinical symptoms. Elevated troponin concentrations are associated with greater morbidity and mortality in patients with pulmonary embolism. Right ventricular ischemia due to increased right ventricular afterload is believed to be underlying mechanism of elevated troponin values in acute pulmonary embolism, but a paradoxical coronary artery embolism through opened intra-artrial communication is another possible explanation as shown in our case report.