Evaluation of Biomarkers in Critical Care and Perioperative Medicine: A Clinician’s Overview of Traditional Statistical Methods and Machine Learning Algorithms

• Published in: Anesthesiology (Philadelphia) Vol. 134; no. 1; pp. 15 - 25
• Main Authors: Soussi, Sabri, Collins, Gary S., Jüni, Peter, Mebazaa, Alexandre, Gayat, Etienne, Le Manach, Yannick
• Format: Journal Article
• Language: English
• Published: United States the American Society of Anesthesiologists, Inc. Wolters Kluwer Health, Inc 01.01.2021; Copyright by , the American Society of Anesthesiologists, Inc. Wolters Kluwer Health, Inc
• Subjects: Biomarkers; Critical Care - statistics & numerical data; Data Interpretation, Statistical; Humans; Machine Learning; Perioperative Medicine - statistics & numerical data; Risk Assessment
• ISSN: 0003-3022; 1528-1175; 1528-1175
• DOI: 10.1097/ALN.0000000000003600

SUMMARYInterest in developing and using novel biomarkers in critical care and perioperative medicine is increasing. Biomarkers studies are often presented with flaws in the statistical analysis that preclude them from providing a scientifically valid and clinically relevant message for clinicians. To improve scientific rigor, the proper application and reporting of traditional and emerging statistical methods (e.g., machine learning) of biomarker studies is required. This Readers’ Toolbox article aims to be a starting point to nonexpert readers and investigators to understand traditional and emerging research methods to assess biomarkers in critical care and perioperative medicine.