COVID-19 Mortality Risk Prediction Using X-Ray Images

The pandemic caused by coronavirus COVID-19 has already had a massive impact in our societies terms of health, economy, and social distress. One the most common symptoms are lung problems like pneumonia, which can be detected using X-ray images. On other hand, popularity Machine Learning models grown exponentially recent years Deep techniques have become state-of-the-art for image classification tasks is widely used healthcare sector nowadays as support clinical decisions. This research aims to build prediction model based on Learning, including predict mortality risk particular patient given an some basic demographic data. Keeping this mind, paper three goals. First, we use For purpose, apply Convolutional Neural Networks well Transfer mitigate effect reduced amount COVID19 data available. Second, propose combine Network with data, gender age, input features final model, that will act second layer. layer aim improve goodness fit power first Finally, accordance principle reproducible research, experiments publicly available make implementations developed easily accessible via public repositories. Experiments over real dataset patients yield high AUROC values show two-layer framework obtain better results than single (CNN) achieving close perfect classification.