Can an unsupervised deep learning model identify distinct hypotension endotypes in surgical and critically ill patients?
An unsupervised deep learning model can classify hypotension into four distinct endotypes, which could help guide causal treatments in critically ill and surgical patients.
Unsupervised deep learning identified four endotypes of hypotension in surgical and critically ill patients: vasodilation, hypovolaemia, myocardial depression, and bradycardia. The algorithm provides the probability of each endotype for each hypotensive data point. Identifying hypotensive endotypes could guide clinicians to causal treatments for hypotension.
Jian et al. (Wed,) studied this question.