Published in:
Open Access 01-12-2020 | Editorial
How machine learning could be used in clinical practice during an epidemic
Published in: Critical Care | Issue 1/2020
Login to get accessExcerpt
The COVID-19 epidemic is the cause of a crisis that is confronting the healthcare community with an unprecedented situation: emergency and intensive care units (ICU) are saturated, compelling physicians to make extremely hard decisions (triage). In such a resource-constrained situation, physicians need decision support systems that could help them to optimally stratify patient risk. In the present paper, we explain how machine learning (ML) could help clinical practitioners during the epidemic (Fig. 1), and we describe some challenges and perspectives that could direct future efforts in the field.
Fig. 1
Machine learning-based decision support systems can help clinical practice during an epidemic. Efficient diagnostic and accurate prediction of patient outcomes can ultimately lead to effective medical resource management. In contrast to traditional approaches, machine learning algorithms enable feature selection and design of non-linear models that improve prediction of clinical outcomes, and on-line training techniques allow upgrading of decision support systems, as the data regarding the epidemic increases
× ![]()
…