Machine Learning for Clinical Outcome Prediction

Clinical decision-making in healthcare is already being influenced by predictions or recommendations made data-driven machines. Numerous machine learning applications have appeared the latest clinical literature, especially for outcome prediction models, with outcomes ranging from mortality and cardiac arrest to acute kidney injury arrhythmia. In this review article, we summarize state-of-the-art related works covering data processing, inference, model evaluation, context of models developed using extracted electronic health records. We also discuss limitations prominent modeling assumptions highlight opportunities future research.