IRUS Total

Machine learning for technical skill assessment in surgery: a systematic review

File Description SizeFormat 
2919_3_merged_1640173715.pdfAccepted version2.36 MBAdobe PDFView/Open
Title: Machine learning for technical skill assessment in surgery: a systematic review
Authors: Lam, K
Chen, J
Wang, Z
Iqbal, F
Darzi, A
Lo, B
Purkayastha, S
Kinross, J
Item Type: Journal Article
Abstract: Accurate and objective performance assessment is essential for both trainees and certified surgeons. However, existing methods can be time consuming, labor intensive and subject to bias. Machine learning (ML) has the potential to provide rapid, automated and reproducible feedback without the need for expert reviewers. We aimed to systematically review the literature and determine the ML techniques used for technical surgical skill assessment and identify challenges and barriers in the field. A systematic literature search, in accordance with the PRISMA statement, was performed to identify studies detailing the use of ML for technical skill assessment in surgery. Of the 1896 studies that were retrieved, 66 studies were included. The most common ML methods used were Hidden Markov Models (HMM, 14/66), Support Vector Machines (SVM, 17/66) and Artificial Neural Networks (ANN, 17/66). 40/66 studies used kinematic data, 19/66 used video or image data, and 7/66 used both. Studies assessed performance of benchtop tasks (48/66), simulator tasks (10/66), and real-life surgery (8/66). Accuracy rates of over 80% were achieved, although tasks and participants varied between studies. Barriers to progress in the field included a focus on basic tasks, lack of standardization between studies, and lack of datasets. ML has the potential to produce accurate and objective surgical skill assessment through the use of methods including HMM, SVM, and ANN. Future ML-based assessment tools should move beyond the assessment of basic tasks and towards real-life surgery and provide interpretable feedback with clinical value for the surgeon.
Issue Date: 3-Mar-2022
Date of Acceptance: 21-Jan-2022
URI: http://hdl.handle.net/10044/1/94832
DOI: 10.1038/s41746-022-00566-0
ISSN: 2398-6352
Publisher: Nature Research
Journal / Book Title: npj Digital Medicine
Volume: 5
Copyright Statement: ┬ęThe Author(s) 2022
Sponsor/Funder: Multi-Scale Medical Robotics Center Limited
Engineering & Physical Science Research Council (EPSRC)
Engineering & Physical Science Research Council (E
Funder's Grant Number: MEME_P84520
Keywords: Science & Technology
Life Sciences & Biomedicine
Health Care Sciences & Services
Medical Informatics
Publication Status: Published
Appears in Collections:Department of Surgery and Cancer
Faculty of Medicine
Institute of Global Health Innovation

This item is licensed under a Creative Commons License Creative Commons