人工智能辅助肺超声在资源有限重症监护病房中的临床获益
该前瞻性三阶段研究在资源有限的重症监护病房中评估了一种定制人工智能工具辅助肺超声判读的效果。第一阶段比较四组临床用户判读肺超声视频的性能;第二阶段在回顾性离线视频中比较57名非专家临床医生有无人工智能辅助的判读性能;第三阶段在重症监护病房对7名患者进行实时肺超声检查,14名临床医生在有无人工智能辅助下完成判读。结果显示,非专家临床医生在回顾性判读中准确率从68.9%提升至82.9%,在实时判读中从68.1%提升至93.4%;判读时间中位数从12.1秒缩短至5.0秒,置信度中位数从3分(满分4分)提升至4分(满分4分)。作者认为,人工智能辅助肺超声可帮助资源有限重症监护病房中的非专家临床医生更准确、更快速、更自信地判读肺超声特征。
要点
- 在资源有限的重症监护病房中,非专家临床医生实时判读肺超声的基线准确率为68.1% [95% CI 57.9-78.2%],使用人工智能工具后提升至93.4% [95% CI 89.0-97.8%](p < 0.001)。
- 在回顾性离线视频判读中,57名非专家临床医生的平均准确率从68.9% [95% CI 65.6-73.9%]提升至82.9% [95% CI 79.1-86.7%](p < 0.001)。
- 专家判读肺超声的平均准确率为95.0% [95% CI 88.2-100.0%],显著优于初学者、中级和高级用户(p < 0.001)。
- 使用人工智能工具后,判读时间中位数从12.1秒(IQR 8.5-20.6)缩短至5.0秒(IQR 3.5-8.8)(p < 0.001),临床医生置信度中位数从3分(满分4分)提升至4分(满分4分)。
- 作者认为,人工智能辅助肺超声可帮助资源有限的重症监护病房中的非专家临床医生更准确、更快速、更自信地判读肺超声特征。
适用人群与场景
- 资源有限的重症监护病房中的非专家临床医生(包括初学者、中级和高级用户)及接受肺超声检查的重症监护病房患者。
- 研究在低收入和中等收入国家的重症监护病房环境中进行。
研究设计与关键结果
- 研究为三阶段前瞻性研究:第一阶段评估四组临床用户判读肺超声视频的性能;第二阶段在回顾性离线视频中评估57名非专家临床医生有无定制人工智能工具辅助的判读性能;第三阶段在重症监护病房对7名患者进行实时肺超声检查,14名临床医生在有无人工智能工具辅助下完成判读,并访谈临床医生对人工智能工具可用性的评价。
- 初学者判读肺超声的平均准确率为68.7% [95% CI 66.8-70.7%],中级用户为72.2% [95% CI 70.0-75.6%],高级用户为73.4% [95% CI 62.2-87.8%],专家为95.0% [95% CI 88.2-100.0%];专家显著优于初学者、中级和高级用户(p < 0.001)。
- 非专家临床医生在回顾性离线视频判读中,无人工智能辅助的平均准确率为68.9% [95% CI 65.6-73.9%],有辅助时为82.9% [95% CI 79.1-86.7%](p < 0.001)。
- 非专家临床医生在实时前瞻性判读中,无人工智能辅助的基线准确率为68.1% [95% CI 57.9-78.2%],使用人工智能工具后为93.4% [95% CI 89.0-97.8%](p < 0.001)。
- 使用人工智能工具后,判读时间中位数从12.1秒(IQR 8.5-20.6)缩短至5.0秒(IQR 3.5-8.8)(p < 0.001),临床医生置信度中位数从3分(满分4分)提升至4分(满分4分)。
证据类型、等级与局限
- 证据类型:三阶段前瞻性研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,人工智能辅助肺超声可帮助资源有限的重症监护病房中的非专家临床医生更准确、更快速、更自信地判读肺超声特征。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
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.
参考来源
- Nhat PTH, Van Hao N, Tho PV, et al. Clinical benefit of AI-assisted lung ultrasound in a resource-limited intensive care unit. Crit Care. 2023. PMID: 37393330. doi:10.1186/s13054-023-04548-w
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。