Leveling Up: A Review of Machine Learning Models in the Cardiac ICU

Abstract

Machine learning has emerged as a significant tool to augment the medical decision-making process. Studies have steadily accrued detailing algorithms and models designed using machine learning to predict and anticipate pathologic states. The cardiac intensive care unit is an area where anticipation is crucial in the division between life and death. In this paper, we aim to review important studies describing the utility of machine learning algorithms to describe the future of artificial intelligence in the cardiac intensive care unit, especially in regards to the prediction of successful ventilatory weaning, acute respiratory distress syndrome, arrhythmia, and acute kidney injury.

Keywords: ARDS; Acute kidney injury; Artificial intelligence; Atrial fibrillation; Cardiac ICU; Machine learning; Precision health care; Sepsis; Ventilator weaning.