文献速递肺栓塞与肺血管病

人工智能超声心动图评估肺动脉高压

Artificial Intelligence-Based Echocardiography in Pulmonary Arterial Hypertension.
PubMed 文献 · Chest · 2025-08-26

本研究评估全自动深度学习超声心动图流程评估肺动脉高压的可靠性与判别能力:在213名健康人和221例肺动脉高压患者中比较深度学习与核心实验室读数的偏倚和精度,并在196例转诊右心导管患者中评估其对轻度肺动脉高压的判别能力。结果显示多数参数无明显偏倚,但右心室面积变化分数存在显著偏倚;转诊队列中深度学习判别肺动脉高压的曲线下面积低于临床实验室读数,但差异无统计学意义。

要点

  • 三尖瓣反流峰值流速、右房面积和TAPSE的深度学习读数无明显偏倚,精度较好。
  • 右心室面积变化分数(RVFAC)深度学习读数存在显著偏倚,解读需谨慎。
  • 深度学习在转诊队列中判别肺动脉高压的AUC为0.75,低于临床实验室的0.79但差异无统计学意义。

核心结论

  • 全自动深度学习超声心动图流程在评估肺动脉高压方面具有前景,可能提高临床实践效率。
  • 多数超声参数无明显偏倚且精度可接受,但RVFAC存在显著偏倚。

研究设计与样本

  • 研究分两部分:第一部分以核心实验室读数为参考,评估Us2.ai软件版本1.4.5深度学习读数的偏倚与精度;第二部分评估深度学习对转诊右心导管患者中轻度肺动脉高压的判别能力。
  • 第一部分为病例对照队列,包括213名健康个体和221例肺动脉高压患者;第二部分转诊队列包括196例患者,其中171例有可测量的三尖瓣反流峰值信号。

主要发现

  • 肺动脉高压患者平均年龄48岁,78%为女性,平均肺动脉压52 mm Hg。
  • 三尖瓣反流峰值流速偏倚0.90%(95% CI,-0.17至1.57),右房面积偏倚1.71%(95% CI,0.59至3.34),TAPSE偏倚1.28%(95% CI,-0.51至3.18),均无显著偏倚。
  • RVFAC存在显著偏倚11.46%(95% CI,8.43至14.74)。
  • 除RVFAC外,所有测量的稳健百分位精度均低于15%。
  • 病例对照队列中,三尖瓣反流峰值流速的AUC在核心实验室读数为0.99,深度学习读数为0.98;转诊队列中肺动脉高压检测的AUC在临床实验室读数为0.79,深度学习读数为0.75(P = .068)。

关键数值与推荐

  • 三尖瓣反流峰值流速偏倚0.90%(95% CI,-0.17至1.57),右房面积偏倚1.71%(95% CI,0.59至3.34),TAPSE偏倚1.28%(95% CI,-0.51至3.18),RVFAC偏倚11.46%(95% CI,8.43至14.74)。
  • 除RVFAC外,所有测量的稳健百分位精度均低于15%。
  • 转诊队列肺动脉高压检测AUC:临床实验室读数0.79,深度学习读数0.75(P = .068)。

临床怎么用

  • 深度学习超声心动图可用于快速评估肺动脉高压相关参数,但RVFAC结果需人工复核。
  • 在临床应用中应结合临床实验室读数与深度学习结果,尤其对轻度肺动脉高压的判别需谨慎解读。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Echocardiography is central when assessing pulmonary hypertension (PH), but manual interpretation can be time-consuming and prone to error. RESEARCH QUESTION: Is a fully automated deep learning (DL) workflow in echocardiography reliable when assessing PH? STUDY DESIGN AND METHODS: This study had 2 parts: the first determined the bias and precision of DL reads by using Us2.ai software version 1.4.5 with core laboratory readers as the reference; the second part assessed the ability of DL to discriminate milder PH in patients referred for right heart catheterization (mean pulmonary artery pressure between 20 and 35 mm Hg). The first cohort (case-control) included 213 healthy individuals and 221 patients with pulmonary arterial hypertension. Parameters included peak tricuspid regurgitation velocity (TRV), right ventricular basal diameter, tricuspid annular plane systolic excursion, right atrial area, and right ventricular fractional area change (RVFAC). The referral cohort included 196 patients, with 171 patients having measurable peak TRV signals. Robust measures of bias and precision were reported, and area under the curve (AUC) analysis assessed discrimination. RESULTS: In patients with pulmonary arterial hypertension, mean age was 48 years, 78% were female, and mean pulmonary artery pressure was 52 mm Hg. No significant bias was observed for peak TRV (0.90%; 95% CI, -0.17 to 1.57), right atrial area (1.71%; 95% CI, 0.59 to 3.34), and tricuspid annular plane systolic excursion (1.28%; 95% CI, -0.51 to 3.18), while RVFAC exhibited a significant bias of 11.46% (95% CI, 8.43 to 14.74). For all measurements except RVFAC, robust percentile precision remained below 15%. In the case-control cohort, peak TRV had AUCs of 0.99 and 0.98 for core laboratory and DL reads, respectively. The AUC for PH detection in the referral cohort was 0.79 for clinical laboratory reads and 0.75 for DL reads (P = .068). INTERPRETATION: A fully automated DL workflow for echocardiography in PH is promising and likely to improve efficiency in clinical practice.

来源:Chest,查看原文。版权归原作者所有。

引用

  1. Celestin B, Bagherzadeh SP, Santana E, et al. Artificial Intelligence-Based Echocardiography in Pulmonary Arterial Hypertension. Chest. 2025. PMID: 40876740. doi:10.1016/j.chest.2025.06.052

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。