深度学习增强胸片无创检测肺动脉高压及其亚型并经导管验证
该回顾性队列纳入4576例患者(2288例肺动脉高压),开发深度学习模型CXR-PH-Net和CXR-CHD-PAH-Net用于胸片检测肺动脉高压及先天性心脏病相关肺动脉高压。内部测试集中CXR-PH-Net检测PH的敏感度为0.902、AUC为0.964;经右心导管确认的队列中内部敏感度0.902(AUC 0.872)、外部敏感度0.803(AUC 0.811)。CXR-CHD-PAH-Net在内部和外部数据集中检测CHD-PAH的敏感度分别为0.859和0.870,AUC分别为0.908和0.860。
要点
- CXR-PH-Net在内部测试集检测PH的敏感度0.902、AUC 0.964。
- 经右心导管确认队列中CXR-PH-Net外部验证敏感度0.803、AUC 0.811。
- CXR-CHD-PAH-Net检测CHD-PAH内部和外部AUC分别为0.908和0.860。
核心结论
- CXR-PH-Net和CXR-CHD-PAH-Net作为PH和CHD-PAH的筛查工具表现出高敏感度,可能有助于早期发现和分诊进一步评估。
研究设计与样本
- 回顾性队列研究纳入4576例患者,其中2288例为肺动脉高压患者,均接受胸片检查后行右心导管或经胸超声心动图。
- 开发并验证了检测PH的CXR-PH-Net模型和检测CHD-PAH的CXR-CHD-PAH-Net模型。
- 内部测试集2140例(1070例PH),另设经右心导管确认的内部队列1158例和来自2家独立医院的外部右心导管队列90例进行验证。
主要发现
- CXR-PH-Net在内部测试集检测PH的敏感度为0.902,AUC为0.964。
- 在经右心导管确认的队列中,CXR-PH-Net内部敏感度0.902(AUC 0.872),外部敏感度0.803(AUC 0.811)。
- CXR-CHD-PAH-Net在内部和外部数据集检测CHD-PAH的敏感度分别为0.859和0.870,AUC分别为0.908和0.860。
- CXR-CHD-PAH-Net在轻度PH患者中检测CHD-PAH的内部和外部敏感度分别为0.813和0.846。
临床怎么用
- 模型可作为PH和CHD-PAH的筛查工具,高敏感度有助于早期发现和分诊进一步评估,尤其在资源有限环境中。
局限性
- 需要在多样化人群中进一步验证以提高临床通用性。
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: Pulmonary hypertension (PH) is a complex, life-threatening condition requiring noninvasive, accessible, and accurate diagnostic tools, particularly in resource-limited settings. Early and precise identification of PH and its subtypes is critical for effective management and timely intervention. RESEARCH QUESTION: Can deep learning (DL) methods applied to chest radiography (CXR) accurately detect PH and its subtype, congenital heart disease-associated pulmonary arterial hypertension (CHD-PAH)? STUDY DESIGN AND METHODS: A retrospective cohort study was conducted with 4,576 patients, including 2,288 patients with PH, who underwent CXR followed by right heart catheterization (RHC) or transthoracic echocardiography. DL models were developed and validated for detecting PH (CXR-PH-Net model) and CHD-PAH (CXR-CHD-PAH-Net model). Internal testing used a data set of 2,140 patients (1,070 patients with PH), and additional validation included an RHC-confirmed internal cohort (1,158 patients) and an external RHC cohort (90 patients) from 2 independent hospitals. Model performance was evaluated primarily using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. RESULTS: The CXR-PH-Net model achieved a sensitivity of 0.902 and an AUC of 0.964 for PH detection in the internal test set. In the RHC-confirmed cohort, sensitivity was 0.902 (AUC, 0.872) internally and 0.803 (AUC, 0.811) externally. The CXR-CHD-PAH-Net model demonstrated sensitivities of 0.859 and 0.870 with AUCs of 0.908 and 0.860 in the internal and external data sets, respectively. Meanwhile, the CXR-CHD-PAH-Net model showed favorable sensitivity in detecting CHD-PAH among patients with mild PH, with values of 0.813 and 0.846 in the internal and external datasets, respectively. INTERPRETATION: The CXR-PH-Net and CXR-CHD-PAH-Net models demonstrated high sensitivity as screening tools for PH and CHD-PAH, potentially facilitating early detection and triage for further evaluation, particularly in resource-limited settings. Further validation in diverse populations is warranted to enhance clinical generalizability. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov; No.: NCT05566002; URL: www. CLINICALTRIALS: gov.
引用
- Huang Z, Diao X, Huo Y, et al. Deep Learning-Enhanced Noninvasive Detection of Pulmonary Hypertension and Subtypes via Chest Radiographs, Validated by Catheterization. Chest. 2025. PMID: 40541737. doi:10.1016/j.chest.2025.06.008
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。