Development of Machine Learning Copilot to Assist Novices in Learning Flexible Laryngoscopy.

IF 2.2 3区医学 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Laryngoscope Pub Date : 2024-10-03 DOI:10.1002/lary.31812

Mattea E Miller, Dan Witte, Ioan Lina, Jonathan Walsh, Anaïs Rameau, Nasir I Bhatti

{"title":"Development of Machine Learning Copilot to Assist Novices in Learning Flexible Laryngoscopy.","authors":"Mattea E Miller, Dan Witte, Ioan Lina, Jonathan Walsh, Anaïs Rameau, Nasir I Bhatti","doi":"10.1002/lary.31812","DOIUrl":null,"url":null,"abstract":"Objectives: Here we describe the development and pilot testing of the first artificial intelligence (AI) software \"copilot\" to help train novices to competently perform flexible fiberoptic laryngoscopy (FFL) on a mannikin and improve their uptake of FFL skills.Methods: Supervised machine learning was used to develop an image classifier model, dubbed the \"anatomical region classifier,\" responsible for predicting the location of camera in the upper aerodigestive tract and an object detection model, dubbed the \"anatomical structure detector,\" responsible for locating and identifying key anatomical structures in images. Training data were collected by performing FFL on an AirSim Combo Bronchi X mannikin (United Kingdom, TruCorp Ltd) using an Ambu aScope 4 RhinoLaryngo Slim connected to an Ambu® aView™ 2 Advance Displaying Unit (Ballerup, Ambu A/S). Medical students were prospectively recruited to try the FFL copilot and rate its ease of use and self-rate their skills with and without the copilot.Results: This model classified anatomical regions with an overall accuracy of 91.9% on the validation set and 80.1% on the test set. The model detected anatomical structures with overall mean average precision of 0.642. Through various optimizations, we were able to run the AI copilot at approximately 28 frames per second (FPS), which is imperceptible from real time and nearly matches the video frame rate of 30 FPS. Sixty-four novice medical students were recruited for feedback on the copilot. Although 90.9% strongly agreed/agreed that the AI copilot was easy to use, their self-rating of FFL skills following use of the copilot were overall equivocal to their self-rating without the copilot.Conclusions: The AI copilot tracked successful capture of diagnosable views of key anatomical structures effectively guiding users through FFL to ensure all anatomical structures are sufficiently captured. This tool has the potential to assist novices in efficiently gaining competence in FFL.Level of evidence: NA Laryngoscope, 2024.","PeriodicalId":49921,"journal":{"name":"Laryngoscope","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Laryngoscope","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/lary.31812","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}

引用次数: 0

Abstract

Objectives: Here we describe the development and pilot testing of the first artificial intelligence (AI) software "copilot" to help train novices to competently perform flexible fiberoptic laryngoscopy (FFL) on a mannikin and improve their uptake of FFL skills.

Methods: Supervised machine learning was used to develop an image classifier model, dubbed the "anatomical region classifier," responsible for predicting the location of camera in the upper aerodigestive tract and an object detection model, dubbed the "anatomical structure detector," responsible for locating and identifying key anatomical structures in images. Training data were collected by performing FFL on an AirSim Combo Bronchi X mannikin (United Kingdom, TruCorp Ltd) using an Ambu aScope 4 RhinoLaryngo Slim connected to an Ambu® aView™ 2 Advance Displaying Unit (Ballerup, Ambu A/S). Medical students were prospectively recruited to try the FFL copilot and rate its ease of use and self-rate their skills with and without the copilot.

Results: This model classified anatomical regions with an overall accuracy of 91.9% on the validation set and 80.1% on the test set. The model detected anatomical structures with overall mean average precision of 0.642. Through various optimizations, we were able to run the AI copilot at approximately 28 frames per second (FPS), which is imperceptible from real time and nearly matches the video frame rate of 30 FPS. Sixty-four novice medical students were recruited for feedback on the copilot. Although 90.9% strongly agreed/agreed that the AI copilot was easy to use, their self-rating of FFL skills following use of the copilot were overall equivocal to their self-rating without the copilot.

Conclusions: The AI copilot tracked successful capture of diagnosable views of key anatomical structures effectively guiding users through FFL to ensure all anatomical structures are sufficiently captured. This tool has the potential to assist novices in efficiently gaining competence in FFL.

Level of evidence: NA Laryngoscope, 2024.

查看原文本刊更多论文

开发辅助新手学习柔性喉镜的机器学习驾驶仪。

目的：我们在此介绍首个人工智能（AI）软件 "copilot "的开发和试点测试，该软件可帮助培训新手在人体模型上熟练进行柔性纤维喉镜检查（FFL），并提高他们对FFL技能的掌握程度：方法：利用监督机器学习技术开发了一个图像分类器模型（称为 "解剖区域分类器"）和一个物体检测模型（称为 "解剖结构检测器"），前者负责预测上气道摄像头的位置，后者负责定位和识别图像中的关键解剖结构。通过使用连接到 Ambu® aView™ 2 高级显示单元（Ballerup，Ambu A/S）的 Ambu aScope 4 RhinoLaryngo Slim，在 AirSim Combo Bronchi X 人形机器人（英国，TruCorp Ltd）上执行 FFL，收集训练数据。医学专业学生被招募试用 FFL 副驾驶，并对其易用性进行评分，同时对使用和不使用副驾驶的技能进行自我评分：该模型在验证集上对解剖区域进行分类的总体准确率为 91.9%，在测试集上为 80.1%。该模型检测解剖结构的总体平均精度为 0.642。通过各种优化，我们能够以大约每秒 28 帧（FPS）的速度运行人工智能副驾驶，这与实时速度相比不易察觉，几乎与 30 FPS 的视频帧率相匹配。我们招募了 64 名医学专业的新手学生，以获得他们对副驾驶的反馈意见。尽管90.9%的人非常同意/同意人工智能副驾驶软件易于使用，但他们在使用副驾驶软件后对FFL技能的自我评分总体上与未使用副驾驶软件时的自我评分相当：结论：人工智能辅助驾驶仪可跟踪关键解剖结构的可诊断视图的成功捕获，有效地指导用户完成 FFL，以确保充分捕获所有解剖结构。该工具有可能帮助新手有效地获得 FFL 的能力：NA 《喉镜》，2024 年。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Laryngoscope 医学-耳鼻喉科学

CiteScore

6.50

自引率

7.70%

发文量

500

审稿时长

2-4 weeks

期刊介绍： The Laryngoscope has been the leading source of information on advances in the diagnosis and treatment of head and neck disorders since 1890. The Laryngoscope is the first choice among otolaryngologists for publication of their important findings and techniques. Each monthly issue of The Laryngoscope features peer-reviewed medical, clinical, and research contributions in general otolaryngology, allergy/rhinology, otology/neurotology, laryngology/bronchoesophagology, head and neck surgery, sleep medicine, pediatric otolaryngology, facial plastics and reconstructive surgery, oncology, and communicative disorders. Contributions include papers and posters presented at the Annual and Section Meetings of the Triological Society, as well as independent papers, "How I Do It", "Triological Best Practice" articles, and contemporary reviews. Theses authored by the Triological Society’s new Fellows as well as papers presented at meetings of the American Laryngological Association are published in The Laryngoscope. • Broncho-esophagology • Communicative disorders • Head and neck surgery • Plastic and reconstructive facial surgery • Oncology • Speech and hearing defects