Clinical benefit of AI-assisted lung ultrasound in a resource-limited intensive care unit

Author:

Nhat Phung Tran Huy,Van Hao Nguyen,Tho Phan Vinh,Kerdegari Hamideh,Pisani Luigi,Thu Le Ngoc Minh,Phuong Le Thanh,Duong Ha Thi Hai,Thuy Duong Bich,McBride Angela,Xochicale Miguel,Schultz Marcus J.,Razavi Reza,King Andrew P.,Thwaites Louise,Van Vinh Chau Nguyen,Yacoub Sophie,Thao Dang Phuong,Kien Dang Trung,Thy Doan Bui Xuan,Trinh Dong Huu Khanh,Duc Du Hong,Geskus Ronald,Hai Ho Bich,Chanh Ho Quang,Van Hien Ho,Trieu Huynh Trung,Kestelyn Evelyne,Yen Lam Minh,Van Khoa Le Dinh,Phuong Le Thanh,Khanh Le Thuy Thuy,Tran Luu Hoai Bao,An Luu Phuoc,Mcbride Angela,Vuong Nguyen Lam,Huy Nguyen Quang,Quyen Nguyen Than Ha,Ngoc Nguyen Thanh,Giang Nguyen Thi,Trinh Nguyen Thi Diem,Le Thanh Nguyen Thi,Dung Nguyen Thi Phuong,Thao Nguyen Thi Phuong,Van Ninh Thi Thanh,Kieu Pham Tieu,Khanh Phan Nguyen Quoc,Lam Phung Khanh,Nhat Phung Tran Huy,Thwaites Guy,Thwaites Louise,Duc Tran Minh,Hung Trinh Manh,Turner Hugo,Van Nuil Jennifer Ilo,Hoang Vo Tan,Huyen Vu Ngo Thanh,Yacoub Sophie,Tam Cao Thi,Thuy Duong Bich,Duong Ha Thi Hai,Nghia Ho Dang Trung,Chau Le Buu,Toan Le Mau,Thu Le Ngoc Minh,Thao Le Thi Mai,Tai Luong Thi Hue,Phu Nguyen Hoan,Viet Nguyen Quoc,Dung Nguyen Thanh,Nguyen Nguyen Thanh,Phong Nguyen Thanh,Anh Nguyen Thi Kim,Van Hao Nguyen,Van Thanh Duoc Nguyen,Oanh Pham Kieu Nguyet,Van Phan Thi Hong,Qui Phan Tu,Tho Phan Vinh,Thao Truong Thi Phuong,Ali Natasha,Clifton David,English Mike,Hagenah Jannis,Lu Ping,McKnight Jacob,Paton Chris,Zhu Tingting,Georgiou Pantelis,Perez Bernard Hernandez,Hill-Cawthorne Kerri,Holmes Alison,Karolcik Stefan,Ming Damien,Moser Nicolas,Manzano Jesus Rodriguez,Canas Liane,Gomez Alberto,Kerdegari Hamideh,King Andrew,Modat Marc,Razavi Reza,Xochicale Miguel,Karlen Walter,Denehy Linda,Rollinson Thomas,Pisani Luigi,Schultz Marcus,Gomez Alberto,

Abstract

Abstract Background Interpreting point-of-care lung ultrasound (LUS) images from intensive care unit (ICU) patients can be challenging, especially in low- and middle- income countries (LMICs) where there is limited training available. Despite recent advances in the use of Artificial Intelligence (AI) to automate many ultrasound imaging analysis tasks, no AI-enabled LUS solutions have been proven to be clinically useful in ICUs, and specifically in LMICs. Therefore, we developed an AI solution that assists LUS practitioners and assessed its usefulness in  a low resource ICU. Methods This was a three-phase prospective study. In the first phase, the performance of four different clinical user groups in interpreting LUS clips was assessed. In the second phase, the performance of 57 non-expert clinicians with and without the aid of a bespoke AI tool for LUS interpretation was assessed in retrospective offline clips. In the third phase, we conducted a prospective study in the ICU where 14 clinicians were asked to carry out LUS examinations in 7 patients with and without our AI tool and we interviewed the clinicians regarding the usability of the AI tool. Results The average accuracy of beginners’ LUS interpretation was 68.7% [95% CI 66.8–70.7%] compared to 72.2% [95% CI 70.0–75.6%] in intermediate, and 73.4% [95% CI 62.2–87.8%] in advanced users. Experts had an average accuracy of 95.0% [95% CI 88.2–100.0%], which was significantly better than beginners, intermediate and advanced users (p < 0.001). When supported by our AI tool for interpreting retrospectively acquired clips, the non-expert clinicians improved their performance from an average of 68.9% [95% CI 65.6–73.9%] to 82.9% [95% CI 79.1–86.7%], (p < 0.001). In prospective real-time testing, non-expert clinicians improved their baseline performance from 68.1% [95% CI 57.9–78.2%] to 93.4% [95% CI 89.0–97.8%], (p < 0.001) when using our AI tool. The time-to-interpret clips improved from a median of 12.1 s (IQR 8.5–20.6) to 5.0 s (IQR 3.5–8.8), (p < 0.001) and clinicians’ median confidence level improved from 3 out of 4 to 4 out of 4 when using our AI tool. Conclusions AI-assisted LUS can help non-expert clinicians in an LMIC ICU improve their performance in interpreting LUS features more accurately, more quickly and more confidently.

Publisher

Springer Science and Business Media LLC

Subject

Critical Care and Intensive Care Medicine

Cited by 14 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3