223 The Clinical Applications of Machine Learning in Plastic and Reconstructive Surgery: A Systematic Review. (4th May 2021)

• Record Type: Journal Article
• Authors: Mantelakis, A
• Is Part Of: British journal of surgery. Volume 108(2021)Supplement 2
• Publication Date: 2021-05-04
• Subjects: Surgery -- Periodicals; 617.005
• DOI: 10.1093/bjs/znab134.006
• Languages: English
• ISSNs: 0007-1323

Abstract

Abstract: Background: Machine learning (ML) is a set of models and methods that can automatically detect patterns in vast amounts of data and use this information to perform various kinds of decision-making under uncertain conditions. The aim of this review is to evaluate the applications of machine learning in plastic and reconstructive surgery. Method: EMBASE, MEDLINE and CENTRAL were searched from 1990 to 2020 for studies in which machine learning has been employed in the clinical setting of reconstructive surgery. Primary outcomes will be the evaluation of the accuracy of machine learning models in predicting a clinical diagnosis and post-surgical outcomes. Results: The database identified 1181 articles, of which 51 articles were included in this review. The clinical utility of these algorithms was to assist clinicians in diagnosis prediction (n = 22), outcome prediction (n = 21) and pre-operative planning (n = 8). The mean accuracy for diagnosis prediction, outcome prediction and pre-operative planning was 88.80%, 86.11% and 80.28% respectively. The most commonly used models were neural networks (n = 31), support vector machine (n = 13), decision trees/random forests (10) and logistic regression (n = 9). Discussion: ML has demonstrated excellent performance in diagnosis and outcome predictions, but it is still in its infancy. Further research is warranted to evaluate its applications.