Artificial Intelligence improves novices' bronchoscopy performance - a randomized controlled trial in a simulated setting

Kristoffer Mazanti Cold; Sujun Xie; Anne Orholm Nielsen; Paul Frost Clementsen; Lars Konge

doi:10.1016/j.chest.2023.08.015

Artificial Intelligence improves novices' bronchoscopy performance - a randomized controlled trial in a simulated setting

Kristoffer Mazanti Cold^*, Sujun Xie, Anne Orholm Nielsen, Paul Frost Clementsen, Lars Konge

^*Corresponding author for this work

12 Citations (Scopus)

Abstract

BACKGROUND: Navigating through the bronchial tree and visualizing all bronchial segments is the initial step toward learning flexible bronchoscopy. A novel bronchial segment identification system based on artificial intelligence (AI) has been developed to help guide trainees toward more effective training.

RESEARCH QUESTION: Does feedback from an AI-based automatic bronchial segment identification system improve novice bronchoscopists' end-of-training performance?

STUDY DESIGN AND METHODS: The study was conducted as a randomized controlled trial in a standardized simulated setting. Novices without former bronchoscopy experience practiced on a mannequin. The feedback group (n = 10) received feedback from the AI, and the control group (n = 10) trained according to written instructions. Each participant decided when to end training and proceed to performing a full bronchoscopy without any aids.

RESULTS: The feedback group performed significantly better on all three outcome measures (median difference, P value): diagnostic completeness (3.5 segments, P < .001), structured progress (13.5 correct progressions, P < .001), and procedure time (-214 seconds, P = .002).

INTERPRETATION: Training guided by this novel AI makes novices perform more complete, more systematic, and faster bronchoscopies. Future studies should examine its use in a clinical setting and its effects on more advanced learners.

Original language	English
Journal	Chest
Volume	165
Issue number	2
Pages (from-to)	405-413
Number of pages	9
ISSN	0012-3692
DOIs	https://doi.org/10.1016/j.chest.2023.08.015
Publication status	Published - Feb 2024

Keywords

artificial intelligence
assessment
feedback
flexible bronchoscopy
simulation

Access to Document

10.1016/j.chest.2023.08.015

Cite this

@article{d9b77e7ccc314601b44ed91ef1c6d7f9,

title = "Artificial Intelligence improves novices' bronchoscopy performance - a randomized controlled trial in a simulated setting",

abstract = "BACKGROUND: Navigating through the bronchial tree and visualizing all bronchial segments is the initial step toward learning flexible bronchoscopy. A novel bronchial segment identification system based on artificial intelligence (AI) has been developed to help guide trainees toward more effective training.RESEARCH QUESTION: Does feedback from an AI-based automatic bronchial segment identification system improve novice bronchoscopists' end-of-training performance?STUDY DESIGN AND METHODS: The study was conducted as a randomized controlled trial in a standardized simulated setting. Novices without former bronchoscopy experience practiced on a mannequin. The feedback group (n = 10) received feedback from the AI, and the control group (n = 10) trained according to written instructions. Each participant decided when to end training and proceed to performing a full bronchoscopy without any aids.RESULTS: The feedback group performed significantly better on all three outcome measures (median difference, P value): diagnostic completeness (3.5 segments, P < .001), structured progress (13.5 correct progressions, P < .001), and procedure time (-214 seconds, P = .002).INTERPRETATION: Training guided by this novel AI makes novices perform more complete, more systematic, and faster bronchoscopies. Future studies should examine its use in a clinical setting and its effects on more advanced learners.",

keywords = "artificial intelligence, assessment, feedback, flexible bronchoscopy, simulation",

author = "Cold, {Kristoffer Mazanti} and Sujun Xie and Nielsen, {Anne Orholm} and Clementsen, {Paul Frost} and Lars Konge",

note = "Copyright {\textcopyright} 2023. Published by Elsevier Inc.",

year = "2024",

month = feb,

doi = "10.1016/j.chest.2023.08.015",

language = "English",

volume = "165",

pages = "405--413",

journal = "Chest",

issn = "0012-3692",

publisher = "American College of Chest Physicians",

number = "2",

}

TY - JOUR

T1 - Artificial Intelligence improves novices' bronchoscopy performance - a randomized controlled trial in a simulated setting

AU - Cold, Kristoffer Mazanti

AU - Xie, Sujun

AU - Nielsen, Anne Orholm

AU - Clementsen, Paul Frost

AU - Konge, Lars

PY - 2024/2

Y1 - 2024/2

N2 - BACKGROUND: Navigating through the bronchial tree and visualizing all bronchial segments is the initial step toward learning flexible bronchoscopy. A novel bronchial segment identification system based on artificial intelligence (AI) has been developed to help guide trainees toward more effective training.RESEARCH QUESTION: Does feedback from an AI-based automatic bronchial segment identification system improve novice bronchoscopists' end-of-training performance?STUDY DESIGN AND METHODS: The study was conducted as a randomized controlled trial in a standardized simulated setting. Novices without former bronchoscopy experience practiced on a mannequin. The feedback group (n = 10) received feedback from the AI, and the control group (n = 10) trained according to written instructions. Each participant decided when to end training and proceed to performing a full bronchoscopy without any aids.RESULTS: The feedback group performed significantly better on all three outcome measures (median difference, P value): diagnostic completeness (3.5 segments, P < .001), structured progress (13.5 correct progressions, P < .001), and procedure time (-214 seconds, P = .002).INTERPRETATION: Training guided by this novel AI makes novices perform more complete, more systematic, and faster bronchoscopies. Future studies should examine its use in a clinical setting and its effects on more advanced learners.

AB - BACKGROUND: Navigating through the bronchial tree and visualizing all bronchial segments is the initial step toward learning flexible bronchoscopy. A novel bronchial segment identification system based on artificial intelligence (AI) has been developed to help guide trainees toward more effective training.RESEARCH QUESTION: Does feedback from an AI-based automatic bronchial segment identification system improve novice bronchoscopists' end-of-training performance?STUDY DESIGN AND METHODS: The study was conducted as a randomized controlled trial in a standardized simulated setting. Novices without former bronchoscopy experience practiced on a mannequin. The feedback group (n = 10) received feedback from the AI, and the control group (n = 10) trained according to written instructions. Each participant decided when to end training and proceed to performing a full bronchoscopy without any aids.RESULTS: The feedback group performed significantly better on all three outcome measures (median difference, P value): diagnostic completeness (3.5 segments, P < .001), structured progress (13.5 correct progressions, P < .001), and procedure time (-214 seconds, P = .002).INTERPRETATION: Training guided by this novel AI makes novices perform more complete, more systematic, and faster bronchoscopies. Future studies should examine its use in a clinical setting and its effects on more advanced learners.

KW - artificial intelligence

KW - assessment

KW - feedback

KW - flexible bronchoscopy

KW - simulation

UR - http://www.scopus.com/inward/record.url?scp=85179170064&partnerID=8YFLogxK

U2 - 10.1016/j.chest.2023.08.015

DO - 10.1016/j.chest.2023.08.015

M3 - Journal article

C2 - 37619664

SN - 0012-3692

VL - 165

SP - 405

EP - 413

JO - Chest

JF - Chest

IS - 2

ER -

Artificial Intelligence improves novices' bronchoscopy performance - a randomized controlled trial in a simulated setting

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this