Assistive artificial intelligence for ultrasound image interpretation in regional anaesthesia: an external validation study.

Humans Nerve Block / methods Artificial Intelligence Ultrasonography, Interventional / methods Anesthesia, Conduction / methods Ultrasonography
anatomy artificial intelligence machine learning regional anaesthesia translational AI ultrasonography ultrasound

Journal

British journal of anaesthesia
ISSN: 1471-6771
Titre abrégé: Br J Anaesth
Pays: England
ID NLM: 0372541

Informations de publication

Date de publication:
02 2023
Historique:
received: 06 04 2022
revised: 01 06 2022
accepted: 27 06 2022
pubmed: 21 8 2022
medline: 24 1 2023
entrez: 20 8 2022
Statut: ppublish

Résumé

Ultrasonound is used to identify anatomical structures during regional anaesthesia and to guide needle insertion and injection of local anaesthetic. ScanNav Anatomy Peripheral Nerve Block (Intelligent Ultrasound, Cardiff, UK) is an artificial intelligence-based device that produces a colour overlay on real-time B-mode ultrasound to highlight anatomical structures of interest. We evaluated the accuracy of the artificial-intelligence colour overlay and its perceived influence on risk of adverse events or block failure. Ultrasound-guided regional anaesthesia experts acquired 720 videos from 40 volunteers (across nine anatomical regions) without using the device. The artificial-intelligence colour overlay was subsequently applied. Three more experts independently reviewed each video (with the original unmodified video) to assess accuracy of the colour overlay in relation to key anatomical structures (true positive/negative and false positive/negative) and the potential for highlighting to modify perceived risk of adverse events (needle trauma to nerves, arteries, pleura, and peritoneum) or block failure. The artificial-intelligence models identified the structure of interest in 93.5% of cases (1519/1624), with a false-negative rate of 3.0% (48/1624) and a false-positive rate of 3.5% (57/1624). Highlighting was judged to reduce the risk of unwanted needle trauma to nerves, arteries, pleura, and peritoneum in 62.9-86.4% of cases (302/480 to 345/400), and to increase the risk in 0.0-1.7% (0/160 to 8/480). Risk of block failure was reported to be reduced in 81.3% of scans (585/720) and to be increased in 1.8% (13/720). Artificial intelligence-based devices can potentially aid image acquisition and interpretation in ultrasound-guided regional anaesthesia. Further studies are necessary to demonstrate their effectiveness in supporting training and clinical practice. NCT04906018.

Sections du résumé

BACKGROUND
Ultrasonound is used to identify anatomical structures during regional anaesthesia and to guide needle insertion and injection of local anaesthetic. ScanNav Anatomy Peripheral Nerve Block (Intelligent Ultrasound, Cardiff, UK) is an artificial intelligence-based device that produces a colour overlay on real-time B-mode ultrasound to highlight anatomical structures of interest. We evaluated the accuracy of the artificial-intelligence colour overlay and its perceived influence on risk of adverse events or block failure.
METHODS
Ultrasound-guided regional anaesthesia experts acquired 720 videos from 40 volunteers (across nine anatomical regions) without using the device. The artificial-intelligence colour overlay was subsequently applied. Three more experts independently reviewed each video (with the original unmodified video) to assess accuracy of the colour overlay in relation to key anatomical structures (true positive/negative and false positive/negative) and the potential for highlighting to modify perceived risk of adverse events (needle trauma to nerves, arteries, pleura, and peritoneum) or block failure.
RESULTS
The artificial-intelligence models identified the structure of interest in 93.5% of cases (1519/1624), with a false-negative rate of 3.0% (48/1624) and a false-positive rate of 3.5% (57/1624). Highlighting was judged to reduce the risk of unwanted needle trauma to nerves, arteries, pleura, and peritoneum in 62.9-86.4% of cases (302/480 to 345/400), and to increase the risk in 0.0-1.7% (0/160 to 8/480). Risk of block failure was reported to be reduced in 81.3% of scans (585/720) and to be increased in 1.8% (13/720).
CONCLUSIONS
Artificial intelligence-based devices can potentially aid image acquisition and interpretation in ultrasound-guided regional anaesthesia. Further studies are necessary to demonstrate their effectiveness in supporting training and clinical practice.
CLINICAL TRIAL REGISTRATION
NCT04906018.

Identifiants

DOI: 10.1016/j.bja.2022.06.031 PMID: 35987706 PMC: PMC9900723
pubmed: 35987706
pii: S0007-0912(22)00351-8
doi: 10.1016/j.bja.2022.06.031
pmc: PMC9900723
pii:
doi:

Banques de données

ClinicalTrials.gov
['NCT04906018']

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

217-225

Subventions

Organisme : Medical Research Council
ID : MR/T019050/1
Pays : United Kingdom

Commentaires et corrections

Type : CommentIn

Informations de copyright

Copyright © 2022 The Author(s). Published by Elsevier Ltd.. All rights reserved.

Références

Reg Anesth Pain Med. 2021 Jul;46(7):571-580
pubmed: 34145070
BJA Educ. 2018 Feb;18(2):52-56
pubmed: 33456810
Br J Anaesth. 1989 Sep;63(3):326-9
pubmed: 2679832
Psychol Sci. 2013 Sep;24(9):1848-53
pubmed: 23863753
Reg Anesth Pain Med. 2009 Jan-Feb;34(1):40-6
pubmed: 19258987
Reg Anesth Pain Med. 2016 Mar-Apr;41(2):181-94
pubmed: 26695878
J Ultrasound. 2022 Jun;25(2):145-153
pubmed: 33675031
NPJ Digit Med. 2021 Sep 15;4(1):137
pubmed: 34526639
Ann Emerg Med. 2017 May;69(5):e27-e54
pubmed: 28442101
Anaesthesia. 2020 Mar;75(3):293-297
pubmed: 31268173
Lancet. 2016 Sep 10;388(10049):1067-1074
pubmed: 27492881
Adv Exp Med Biol. 2020;1235:19-34
pubmed: 32488634
Anaesthesia. 2021 May;76(5):602-607
pubmed: 32726498
Lancet Digit Health. 2020 Oct;2(10):e537-e548
pubmed: 33328048
Clin Anat. 2021 Jul;34(5):802-809
pubmed: 33904628
Anaesthesia. 2015 Sep;70(9):1084-91
pubmed: 25989611
Reg Anesth Pain Med. 2022 Jun;47(6):375-379
pubmed: 35091395
J Clin Epidemiol. 1989;42(12):1235-7
pubmed: 2585014
J Anesth. 2021 Aug;35(4):591-594
pubmed: 34008072
Psychon Bull Rev. 2021 Apr;28(2):503-511
pubmed: 33140228
Reg Anesth Pain Med. 2022 Feb;47(2):106-112
pubmed: 34552005
Clin Radiol. 2019 May;74(5):357-366
pubmed: 30898381
N Engl J Med. 2021 Oct 21;385(17):1593-1602
pubmed: 34670045
Br J Anaesth. 2019 May;122(5):e75-e77
pubmed: 30916020
Lancet Digit Health. 2021 Sep;3(9):e543-e554
pubmed: 34446265

Auteurs

James S Bowness (JS)

Oxford Simulation, Teaching and Research Centre, University of Oxford, Oxford, UK; Department of Anaesthesia, Aneurin Bevan University Health Board, Newport, UK. Electronic address: james.bowness@jesus.ox.ac.uk.

David Burckett-St Laurent (D)

Department of Anaesthesia, Royal Cornwall Hospitals NHS Trust, Truro, UK.

Nadia Hernandez (N)

Department of Anesthesiology, Memorial Hermann Hospital, Texas Medical Centre, Houston, TX, USA.

Pearse A Keane (PA)

Institute of Ophthalmology, Faculty of Brain Sciences, University College London, London, UK; National Institute for Health and Care Research Biomedical Research Centre, Moorfields Eye Hospital NHS Foundation Trust, London, UK.

Clara Lobo (C)

Anesthesiology Institute, Cleveland Clinic Abu Dhabi, Abu Dhabi, United Arab Emirates.

Steve Margetts (S)

Intelligent Ultrasound, Cardiff, UK.

Eleni Moka (E)

Anaesthesiology Department, Creta InterClinic Hospital, Hellenic Healthcare Group, Heraklion, Crete, Greece.

Amit Pawa (A)

Department of Anaesthesia, Guy's and St Thomas' Hospitals NHS Trust, London, UK; Faculty of Life Sciences and Medicine, King's College London, London, UK.

Meg Rosenblatt (M)

Department of Anesthesiology, Perioperative and Pain Medicine, Mount Sinai Morningside and West Hospitals, New York, NY, USA.

Nick Sleep (N)

Intelligent Ultrasound, Cardiff, UK.

Alasdair Taylor (A)

Department of Anaesthesia, NHS Tayside, Dundee, UK.

Glenn Woodworth (G)

Department of Anesthesiology and Perioperative Medicine, Oregon Health & Science University, Portland, OR, USA.

Asta Vasalauskaite (A)

Intelligent Ultrasound, Cardiff, UK.

J Alison Noble (JA)

Institute of Biomedical Engineering, University of Oxford, Oxford, UK.

Helen Higham (H)

Oxford Simulation, Teaching and Research Centre, University of Oxford, Oxford, UK; Department of Anaesthesia, Oxford University Hospitals NHS Foundation Trust, Oxford, UK.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female

Evaluation of Low-Value Services Across Major Medicare Advantage Insurers and Traditional Medicare.

Ciara Duggan, Adam L Beckman, Ishani Ganguli et al.
1.00
Humans United States Aged Cross-Sectional Studies Medicare Part C

Effectiveness of Virtual Yoga for Chronic Low Back Pain: A Randomized Clinical Trial.

Hallie Tankha, Devyn Gaskins, Amanda Shallcross et al.
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH

questionsmedicales.fr › Eucaryotes › Animaux › Chordés › Vertébrés › Mammifères › Eutheria › Primates › Haplorhini › Catarrhini › Hominidae › Humains › Assistive artificial intelligence for...
questionsmedicales.fr › Procédures de chirurgie opératoire › Procédures de neurochirurgie › Dénervation › Bloc nerveux › Assistive artificial intelligence for...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Assistive artificial intelligence for...
questionsmedicales.fr › Procédures de chirurgie opératoire › Interventions chirurgicales mini-invasives › Échographie interventionnelle › Assistive artificial intelligence for...
questionsmedicales.fr › Anesthésie et analgésie › Anesthésie › Anesthésie de conduction › Assistive artificial intelligence for...
questionsmedicales.fr › Diagnostic › Techniques et procédures diagnostiques › Imagerie diagnostique › Échographie › Assistive artificial intelligence for...