Feasibility of using machine learning for clinical decision support to optimize transfusion practices in trauma care

This dissertation evaluates how the decision-making regarding blood transfusion is done in trauma care and what variables are used. Then the variables discovered in the first part are evaluated statistically and used to build machine learning models to predict patients in need of blood transfusion, then the fusion model using tabular data and chest x-rays was build and evaluated. Lastly, weather data and time series were used to build a predictive model to predict trauma admissions.