Exploring the potential of artificial intelligence in pediatric echocardiography. Preliminary results from the first pediatric study using AI software developed for adults

IF 18 Q4 Medicine
C. Vasile , X. Bouteiller , M. Avesani , C. Velly , C. Chan , J.B. Thambo , X. Iriart
{"title":"Exploring the potential of artificial intelligence in pediatric echocardiography. Preliminary results from the first pediatric study using AI software developed for adults","authors":"C. Vasile ,&nbsp;X. Bouteiller ,&nbsp;M. Avesani ,&nbsp;C. Velly ,&nbsp;C. Chan ,&nbsp;J.B. Thambo ,&nbsp;X. Iriart","doi":"10.1016/j.acvdsp.2023.07.038","DOIUrl":null,"url":null,"abstract":"<div><h3>Introduction</h3><p>Transthoracic echocardiography<span> is the first-line non-invasive investigation for assessing pediatric patients. Sometimes performing echocardiography in pediatric patients can be challenging for physicians and sonographers due to factors such as patient cooperation and time constraints.</span></p></div><div><h3>Objective</h3><p>Our primary purpose was to establish whether the Ligence Heart software validated for analyzing adult echocardiography could be transposed to pediatric patients.</p></div><div><h3>Methods</h3><p>The study was conducted at the University Hospital of Bordeaux between August and September 2022 and included 45 patients with normal or near-normal heart architecture who underwent a 2D TTE. The ultrasound scans were performed manually by two medical practitioners, a senior, a junior and the AI software provided by Ligence Heart Company. Twenty-three features were assessed through echocardiography for each patient. We compared the agreement between methods and observers.</p></div><div><h3>Results/Expected results</h3><p>The mean age of our patients at the time of evaluation was 8.2 years<!--> <!-->±<!--> <span>5.7, and the main reason for referral to our service was the presence of a heart murmur. Bland-Altman analysis showed good agreement between AI and the senior physician for two parameters (aortic annulus and E wave) regardless of the age of the children included in the study. A good agreement between AI and physicians was also achieved for two other features (STJ and EF) but only for patients older than 9 years. For other features, a good agreement was found between physicians but not with the AI, or a poor agreement was established. In the first case, maybe proper training of the AI could improve the measurement, but in the latter case, for now, it seems unrealistic to expect to reach a satisfactory accuracy.</span></p></div><div><h3>Conclusion/Perspectives</h3><p>Based on this preliminary study on a small cohort group of pediatric patients, the AI soft originally developed for the adult population had provided promising results in evaluating aortic annulus, STJ, and E wave.</p></div>","PeriodicalId":8140,"journal":{"name":"Archives of Cardiovascular Diseases Supplements","volume":null,"pages":null},"PeriodicalIF":18.0000,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Archives of Cardiovascular Diseases Supplements","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1878648023002598","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction

Transthoracic echocardiography is the first-line non-invasive investigation for assessing pediatric patients. Sometimes performing echocardiography in pediatric patients can be challenging for physicians and sonographers due to factors such as patient cooperation and time constraints.

Objective

Our primary purpose was to establish whether the Ligence Heart software validated for analyzing adult echocardiography could be transposed to pediatric patients.

Methods

The study was conducted at the University Hospital of Bordeaux between August and September 2022 and included 45 patients with normal or near-normal heart architecture who underwent a 2D TTE. The ultrasound scans were performed manually by two medical practitioners, a senior, a junior and the AI software provided by Ligence Heart Company. Twenty-three features were assessed through echocardiography for each patient. We compared the agreement between methods and observers.

Results/Expected results

The mean age of our patients at the time of evaluation was 8.2 years ± 5.7, and the main reason for referral to our service was the presence of a heart murmur. Bland-Altman analysis showed good agreement between AI and the senior physician for two parameters (aortic annulus and E wave) regardless of the age of the children included in the study. A good agreement between AI and physicians was also achieved for two other features (STJ and EF) but only for patients older than 9 years. For other features, a good agreement was found between physicians but not with the AI, or a poor agreement was established. In the first case, maybe proper training of the AI could improve the measurement, but in the latter case, for now, it seems unrealistic to expect to reach a satisfactory accuracy.

Conclusion/Perspectives

Based on this preliminary study on a small cohort group of pediatric patients, the AI soft originally developed for the adult population had provided promising results in evaluating aortic annulus, STJ, and E wave.

探索人工智能在儿童超声心动图中的潜力。这是首个使用为成人开发的人工智能软件的儿科研究的初步结果
引言经胸超声心动图是评估儿科患者的一线非侵入性研究。有时,由于患者合作和时间限制等因素,在儿科患者中进行超声心动图检查对医生和超声学家来说可能是一项挑战。目的我们的主要目的是确定用于分析成人超声心动图的Ligence Heart软件是否可以用于儿科患者。方法该研究于2022年8月至9月在波尔多大学医院进行,包括45名心脏结构正常或接近正常的患者,他们接受了二维经胸超声心动图检查。超声波扫描由两名医生手动进行,一名大四,一名小三,人工智能软件由Ligence心脏公司提供。通过超声心动图对每位患者的23个特征进行评估。我们比较了方法和观察者之间的一致性。结果/预期结果在评估时,我们患者的平均年龄为8.2岁±5.7岁,转诊到我们服务的主要原因是存在心脏杂音。Bland-Altman分析显示,无论研究中儿童的年龄如何,AI和高级医生在两个参数(主动脉瓣环和E波)方面都有很好的一致性。AI和医生在其他两个特征(STJ和EF)方面也达成了良好的一致,但仅适用于9岁以上的患者。对于其他特征,医生之间达成了良好的协议,但与人工智能没有达成,或者达成了较差的协议。在第一种情况下,也许人工智能的适当训练可以改善测量,但在后一种情况下——就目前而言,期望达到令人满意的精度似乎是不现实的。结论/展望基于这项针对儿童患者小队列的初步研究,最初为成年人群开发的AI软件在评估主动脉瓣环、STJ和E波方面提供了有希望的结果。
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
Archives of Cardiovascular Diseases Supplements
Archives of Cardiovascular Diseases Supplements CARDIAC & CARDIOVASCULAR SYSTEMS-
自引率
0.00%
发文量
508
期刊介绍: Archives of Cardiovascular Diseases Supplements is the official journal of the French Society of Cardiology. The journal publishes original peer-reviewed clinical and research articles, epidemiological studies, new methodological clinical approaches, review articles, editorials, and Images in cardiovascular medicine. The topics covered include coronary artery and valve diseases, interventional and pediatric cardiology, cardiovascular surgery, cardiomyopathy and heart failure, arrhythmias and stimulation, cardiovascular imaging, vascular medicine and hypertension, epidemiology and risk factors, and large multicenter studies. Additionally, Archives of Cardiovascular Diseases also publishes abstracts of papers presented at the annual sessions of the Journées Européennes de la Société Française de Cardiologie and the guidelines edited by the French Society of Cardiology.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信