Gonzalez Filipe André, Zawadka Mateusz, Varudo Rita, Messina Simone, Caruso Alessandro, Santonocito Cristina, Slama Michel, Sanfilippo Filippo
Intensive Care Department of Hospital Garcia de Orta, Almada, Portugal.
Intensive Care Unit of Hospital CUF Tejo, Lisbon, Portugal.
J Clin Monit Comput. 2025 Jun;39(3):505-515. doi: 10.1007/s10877-024-01259-7. Epub 2024 Dec 27.
Echocardiography is crucial for evaluating patients at risk of clinical deterioration. Left ventricular ejection fraction (LVEF) and velocity time integral (VTI) aid in diagnosing shock, but bedside calculations can be time-consuming and prone to variability. Artificial intelligence technology shows promise in providing assistance to clinicians performing point-of-care echocardiography. We conducted a systematic review, utilizing a comprehensive literature search on PubMed, to evaluate the interchangeability of LVEF and/or VTI measurements obtained through automated mode as compared to the echocardiographic reference methods in non-cardiology settings, e.g., Simpson´s method (LVEF) or manual trace (VTI). Eight studies were included, four studying automated-LVEF, three automated-VTI, and one both. When reported, the feasibility of automated measurements ranged from 78.4 to 93.3%. The automated-LVEF had a mean bias ranging from 0 to 2.9% for experienced operators and from 0% to -10.2% for non-experienced ones, but in both cases, with wide limits of agreement (LoA). For the automated-VTI, the mean bias ranged between - 1.7 cm and - 1.9 cm. The correlation between automated and reference methods for automated-LVEF ranged between 0.63 and 0.86 for experienced and between 0.56 and 0.81 for non-experienced operators. Only one study reported a correlation between automated-VTI and manual VTI (0.86 for experienced and 0.79 for non-experienced operators). We found limited studies reporting the interchangeability of automated LVEF or VTI measurements versus a reference approach. The accuracy and precision of these automated methods should be considered within the clinical context and decision-making. Such variability could be acceptable, especially in the hands of trained operators. PROSPERO number CRD42024564868.
超声心动图对于评估有临床病情恶化风险的患者至关重要。左心室射血分数（LVEF）和速度时间积分（VTI）有助于诊断休克，但床边计算可能耗时且容易出现差异。人工智能技术在为进行床旁超声心动图检查的临床医生提供协助方面显示出前景。我们进行了一项系统评价，利用在PubMed上进行的全面文献检索，以评估在非心脏病学环境中，例如辛普森法（LVEF）或手动描记法（VTI），通过自动模式获得的LVEF和/或VTI测量值与超声心动图参考方法的互换性。纳入了八项研究，四项研究自动LVEF，三项研究自动VTI，一项研究两者。当报告时，自动测量的可行性范围为78.4%至93.3%。对于有经验的操作者，自动LVEF的平均偏差范围为0至2.9%，对于无经验的操作者为0%至 -10.2%，但在两种情况下，一致性界限（LoA）都很宽。对于自动VTI，平均偏差在 -1.7厘米至 -1.9厘米之间。有经验的操作者自动LVEF的自动测量方法与参考方法之间的相关性在0.63至0.86之间，无经验的操作者在0.56至0.81之间。只有一项研究报告了自动VTI与手动VTI之间的相关性（有经验的操作者为0.86，无经验的操作者为0.79）。我们发现报告自动LVEF或VTI测量值与参考方法互换性的研究有限。这些自动方法的准确性和精密度应在临床背景和决策中加以考虑。这种变异性可能是可以接受的，尤其是在训练有素的操作者手中。国际前瞻性系统评价注册编号CRD42024564868。
