A novel model to predict severe COVID-19 and mortality using an artificial intelligence algorithm to interpret chest radiographs and clinical variables.

Background: Patients with coronavirus disease 2019 (COVID-19) could develop severe disease requiring admission to the intensive care unit (ICU). This article presents a novel method that predicts whether a patient will need admission to the ICU and assesses the risk of in-hospital mortality by training a deep-learning model that combines a set of clinical variables and features in chest radiographs. Methods: This was a prospective diagnostic test study. Patients with confirmed severe acute respiratory syndrome coronavirus 2 infection between March 2020 and January 2021 were included. This study was designed to build predictive models obtained by training convolutional neural networks for chest radiograph images using an artificial intelligence (AI) tool and a random forest analysis to identify critical clinical variables. Then, both architectures were connected and fine-tuned to provide combined models. Results: 2552 patients were included in the clinical cohort. The variables independently associated with ICU admission were age, fraction of inspired oxygen (F iO2 ) on admission, dyspnoea on admission and obesity. Moreover, the variables associated with hospital mortality were age, F iO2 on admission and dyspnoea. When implementing the AI model to interpret the chest radiographs and the clinical variables identified by random forest, we developed a model that accurately predicts ICU admission (area under the curve (AUC) 0.92±0.04) and hospital mortality (AUC 0.81±0.06) in patients with confirmed COVID-19. Conclusions: This automated chest radiograph interpretation algorithm, along with clinical variables, is a reliable alternative to identify patients at risk of developing severe COVID-19 who might require admission to the ICU.

Differentiating Cancerous and Non-cancerous Prostate Tissue Using Multi-scale Texture Analysis on MRI.

Prostate cancer (PCa) diagnosis is established by pathological examination via biopsies, which are associated with significant complications and false negatives. Using MRIs to identify locations with high probability of containing cancer could instead be used to guide the biopsy procedure. The present investigation aims to identify target regions within different prostatic zones on MRI with high probability of being cancerous for assisting in the decision of where and how to perform biopsy. Our approach involved extracting multi-scale texture features for capturing local patterns to distinguish cancer and healthy tissue in different T2W-MRI prostate zones. Three different classification models were fed by the proposed strategy, namely support vector machine (SVM), Adaboost, and Random Forest. SVM with a linear kernel showed the best classification performance, with AUC scores of 0.91 in the anterior fibromuscular stroma area, 0.85 in the peripheral zone, and 0.87 when classification is performed independently of the prostate zone. The proposed method demonstrated that discriminant multi-scale texture features can accurately identify regions of prostate cancer in a zone-specific fashion, via MRI.