慢性阻塞性肺疾病相关肺动脉高压早期诊断的研究进展
Research Progress in the Early Diagnosis of Pulmonary Hypertension Associated with Chronic Obstructive Pulmonary Disease
DOI: 10.12677/acm.2025.1541319, PDF, HTML, XML,   
作者: 张 娟:承德医学院第二临床学院,河北 承德;张秀义*, 许浩然:承德市中心医院呼吸与危重症医学科,河北 承德
关键词: 慢性阻塞性肺疾病肺动脉高压诊断研究进展Chronic Obstructive Pulmonary Disease Pulmonary Hypertension Diagnosis Research Progress
摘要: 慢性阻塞性肺疾病(Chronic Obstructive Pulmonary Disease, COPD)作为全球第三大死因,其病程中并发的肺动脉高压(Pulmonary Hypertension, PH)是患者预后不良的独立危险因素。本文综述了COPD相关肺动脉高压(Pulmonary Hypertension Associated with COPD, COPD-PH)的早期诊断研究进展,旨在梳理慢性阻塞性肺疾病相关肺动脉高压早期诊断领域的研究进展,通过整合循证证据与前沿探索,期望为临床实践提供决策参考,并指明未来研究方向。
Abstract: Chronic Obstructive Pulmonary Disease (COPD) is the third leading cause of death worldwide, and Pulmonary Hypertension (PH) complicating the course of the disease is an independent risk factor for poor prognosis of patients. This article reviews the research progress of early diagnosis of pulmonary hypertension associated with COPD (COPD-PH), aims to summarize the research progress in the field of early diagnosis of COPD-associated pulmonary hypertension, and expects to provide a reference for decision-making and indicate the direction of future research for the clinical practice by integrating the evidence-based evidence with the cutting-edge exploration. The aim is to summarize the research progress in the field of early diagnosis of COPD-PH.
文章引用:张娟, 张秀义, 许浩然. 慢性阻塞性肺疾病相关肺动脉高压早期诊断的研究进展[J]. 临床医学进展, 2025, 15(4): 3465-3471. https://doi.org/10.12677/acm.2025.1541319

1. 引言

慢性阻塞性肺疾病(简称慢阻肺)作为一种不可逆的慢性炎症性呼吸系统疾病,是全球第三大死因。在COPD病程中,肺动脉高压作为重要的并发症,是疾病进展至肺心病的核心病理生理环节。调查显示我国肺动脉高压患者出现症状后平均11个月才得以确诊[1]。研究表明,约20%~91%的COPD患者合并PH,且平均肺动脉压力大于25 mmHg的COPD患者5年生存率仅36% [2] [3]。早期识别PH、并给予积极处理,对于延缓COPD患者心肺功能恶化、改善预后具有关键意义。近年来,随着对COPD-PH病理机制的深入研究、超声心动图技术的优化、新型生物标志物的发现以及人工智能的不断迭代,PH早期诊断的敏感性和可及性显著提升,为临床提供了更高效的无创评估工具。

2. 慢性阻塞性肺疾病相关肺动脉高压的病理机制

COPD-PH的病理机制是多种机制交互作用的结果。COPD患者由于气道阻塞及血管破坏导致机体长期处于缺氧状态,慢性低氧血症是COPD-PH的核心因素。长期缺氧时通过激活缺氧诱导因子-1α (hypoxia inducible factor-1α, HIF-1α)上调内皮素-1 (endothelin-1, ET-1)的表达,抑制诱导型一氧化氮合酶,引起肺血管持续收缩。HIF-1α在肺动脉内皮细胞中表达增高,可促进该细胞的钙通道开放,引起血管收缩[4]。同时,研究发现ET-1可结合内皮素受体A促进钙离子内流,进一步收缩肺血管[5]。此外,HIF-1α能够启动下游信号通路,进而增强血管内皮生长因子-A的释放,加快肺血管生成与重塑[6]。大量研究发现,炎症反应在肺动脉高压的发展过程中起到关键作用[7]。肺血管周围出现炎症环境时,肺泡巨噬细胞和T淋巴细胞释放多种促炎因子如白介素-6 (Interleukin-6, IL-6)、肿瘤坏死因子-α (tumor necrosis factor-α, TNF-α)等激活NF-κB等多种信号通路,诱导肺血管内皮细胞凋亡和平滑肌细胞增殖[8] [9]。同时,炎症因子可抑制内皮型一氧化氮合成酶,减少一氧化氮生成,减弱血管舒张功能[4]。炎症因子还可促进血栓素A2释放,加剧血管收缩和血小板聚集[10]。长期低氧和炎症刺激可导致肺血管重构,表现为内皮损伤、平滑肌异常增殖及细胞外基质沉积。此外,COPD患者随着病情进展,肺泡过度充气和弹性回缩力进一步下降可导致通气/血流(V/Q)比例失调,进一步加重低氧血症和肺动脉压力。肺动脉压力持续升高导致右心室后负荷增加,初期右心室通过Frank-Starling机制可进行代偿,但长期负荷过重引发心肌纤维化、收缩功能下降,最终发展为右心衰竭。研究表明COPD患者一旦合并右心衰,其病死率高达50%,显著增加患者死亡风险[11]

3. 现有诊断方法

3.1. 金标准与侵入性方法

目前,肺动脉高压的诊断仍以右心导管检查(Right Heart Catheterization, RHC)为金标准,即在静息状态且处于海平面水平时,通过RHC测量平均肺动脉压力(mean pulmonary artery pressure, mPAP),当该指标 ≥ 25 mmHg时可确诊为肺动脉高压[12]。虽然该技术已较为成熟,严重并发症发生率低,但术后部分患者仍会出现穿刺点血肿、心律失常、肺动脉穿孔及迷走神经反射(血压下降、脉搏细弱等)等不良反应[13]。对于COPD患者,因常合并心肺功能不全,对RHC的耐受性较差,且对于非重度PH患者的靶向药物干预获益尚存争议,部分学者建议优先采用无创替代方案进行初筛。

CT肺动脉造影成像(Computed Tomography Pulmonary Angiography, CTPA)是一种造影技术,能够清晰显示肺组织与肺血管的解剖情况及其病理变化,从而为诊断肺动脉高压提供有力依据[14]。相关研究发现,CTPA中主肺动脉直径、升主动脉直径等指标对于评估肺动脉压力水平具有重要价值[15]。然而,COPD-PH的早期病理改变主要表现为缺氧诱导的肺小动脉痉挛和内膜增生,在 CTPA上难以显影。只有当病变发展至血管壁明显增厚或管腔出现狭窄时,CTPA才能识别,这可能导致错过早期干预的时机。此外,COPD患者由于高龄、长期缺氧、服用药物等因素,部分患者合并肾功能不全,而CTPA需要注射造影剂,这可能会加重肾损伤或者诱发过敏反应。

3.2. 无创筛查方法

肺动脉压力升高时可导致右心室后负荷增加,继发右心肥大,此时心电图即可出现相应变化。研究发现,QRS电轴右偏 > 87˚在诊断肺动脉高压方面的敏感度为86%,特异度为92% [16]。通常认为肺动脉压水平升高时可出现以下变化:肺性P波、右心室肥厚、额面QRS电轴右偏、右束支传导阻滞及QTc间期延长等[17]。在肺动脉高压的临床诊断中,心动图具备筛查优势以及动态监测价值,然而,部分肺动脉高压患者的心电图检查结果并未呈现异常表现。因此,为了进一步精准评估患者的肺动脉压水平,需将心电图检查与其他检查手段联合应用。

超声心动图通过声波成像,无需侵入性操作或辐射暴露,该技术费用低廉、操作便捷,可用于重复检查和动态监测,在长期随访方面也具有显著优势。其对肺动脉压力水平的评估主要包括3种方法:三尖瓣反流速度法、肺动脉瓣反流法及心内分流法[18]。在临床实践中,三尖瓣反流速度法是最常用的方法之一,该方法应用伯努利方程,通过三尖瓣反流速度(tricuspid regurgitation velocity, TRV)估测肺动脉压力水平[12]。多项研究结果表明,TRV在诊断PH方面具有良好的准确性[19]-[21]。虽然目前最广泛应用三尖瓣反流速度法,但其受到患者呼吸、体位、右心室充盈情况等多种因素影响,可能导致高估或低估肺动脉压力实际水平。杜佩等发现,联合TRV和Tei指数诊断PH的敏感度为86%,特异度高达93% [21]。因此,Albani、Correale等多项研究进行进一步探索,研究结果表明多个超声指标联合应用可有助于筛查肺动脉高压[22]-[24]。然而,超声心动图只能间接估测肺动脉压力,当出现肺动脉狭窄或右心室流出道梗阻等病理改变时,其对肺动脉压力的估测出现误差的可能性增加。

胸部CT检查主要通过定量肺血管的测量和肺结构形态的评估,在临床中逐渐成为诊断肺动脉高压的简便、高效的方法。在CT影像中,COPD并发肺动脉高压的特征表现包括:第一、右下肺动脉横径 ≥ 15 mm,肺动脉段凸出程度≥3 mm,中央肺动脉呈扩张状态,外周肺血管纤细,由此形成“残根征”;第二、右心房及右心室扩大,致使出现右心影增大表现[25]。Corson等发现,当主肺动脉直径 > 29 mm时,诊断PH的敏感度为89%,特异度为84% [26]。目前认为胸部CT测量肺动脉直径与同水平升主动脉直径之比可以间接反映肺动脉压力,在慢阻肺患者中,当主肺动脉与同水平升主动脉直径的比值 > 1时,提示其继发肺动脉高压的可能性较大,其敏感度为89%,特异度为82% [26] [27]。胸部CT在PH的筛查中准确性良好,可作为超声检查提示可疑肺动脉高压患者的辅助筛查方法。相较于其他无创检查手段,其临床应用存在检查成本高、电离辐射暴露等局限性。

心脏磁共振(cardiovascular magnetic resonance, CMR)单次扫描即可同时获取心脏三维解剖结构、心脏功能、心肌组织特征以及血流动力学信息,为肺动脉高压的诊断和预后评估供应影像学指导[28] [29]。CMR通过钆对比剂延迟强化、纵向弛豫时间定量成像及心肌细胞外容积技术可评估肺动脉高压患者的心肌组织情况[30]。CMR通过显示心脏异常解剖、分析肺部血液分流情况及展现左心疾病的患病情况,以此揭示肺动脉高压患者潜在的致病因素[29] [31] [32]。张宝美等的研究发现CMR在诊断PH时敏感度为81%,特异度高达94% [33]。然而,CMR检查费用相对较高、检查时间较长,以及部分患者可能因身体状况难以耐受,这些因素在一定程度上限制了其在临床中的广泛应用。

生物标志物作为非侵入性检测手段,其操作简便、快捷易行,能够有效反映肺动脉高压的病理变化过程,目前指南推荐B型脑钠肽(Brain natriuretic peptide, BNP)和N末端B型脑钠肽前体(N-terminal pro-brain natriuretic peptide, NT-pro BNP)作为常规检测指标[12]。BNP主要在呼吸系统中代谢,研究发现在PH患者中BNP水平与PH不良结局相关[34]。此外,相关研究指出在第三组肺动脉高压中,BNP与世界卫生组织肺功能分级之间关系密切。多项研究结果均证实,BNP水平可作为独立的预测因子评估PH患者的死亡率风险[35]

随着医疗信息化技术的发展,人工智能(artificial intelligence, AI)现已广泛应用于肺部疾病、心血管疾病等多种医学领域[36]。Tison等通过深度学习构建的神经网络结果显示,AI联合心电图对诊断肺动脉高压具有极高的辨别力[37]。此外,Aras等通过对24470例患者进行深度学习心电图算法研究,最终发现其检测PH的敏感度和特异度均为81%,检测毛细血管前PH的敏感度和特异度分别为83%和84% [38]。Diller等在肺动脉高压患者的大队列中评估了机器学习算法在估计预后和指导治疗方面的效用,研究发现准确率高达90%以上[39]。研究发现,通过三维卷积神经网络(3D Convolutional Neural Network, 3D CNN)这种深度学习模型,在无需进行血管造影的情况下即可自动区分动脉和静脉,在COPD队列中敏感度高达97% [40]。研究发现,基于CT构建的随机森林模型在预测肺动脉压力时表现出最佳性能,基于该模型对肺动脉高压的诊断可减少对侵入性RHC的依赖,其诊断mPAP > 15 mmHg的灵敏度高达77.8%,特异度为74.6% [41]。在肺动脉造影中,AI自动测量的右心室与左心室直径比值相较于手动测量的比值对诊断肺动脉高压具有更高的敏感性[42]。相关研究表明,机器学习方法可以根据超声心动图数据在无创环境中有效区分毛细血管前肺动脉高压和毛细血管后肺动脉高压[43]。因此,深度开发机器自动化辨识系统具有广阔的实践前景,扩大其应用范围,能够进一步推动对肺动脉高压的筛查、分类与诊断工作。

4. 总结与展望

右心导管检查虽然对于诊断COPD-PH准确性高,但其侵入性风险限制了临床应用范围。无创技术联合生物标志物可提高诊断的敏感度。PH疾病具备复杂性、多样性及高风险性,AI在肺动脉高压的诊断中也表现出很强的辨别力,对于发现PH高危人群、早期筛查PH患者、明确PH诊断及评估患者预后都有巨大的应用前景[44] [45]。未来,需建立大规模、多中心、规范化医疗数据库,提供高质量、标准化的医疗数据,提高AI技术水平,促进AI和PH的数据契合度,更好地在临床实践中落实此应用性技术,最终实现最佳医疗保健的管理。

NOTES

*通讯作者。

参考文献

[1] Quan, R., Zhang, G., Yu, Z., Zhang, C., Yang, Z., Tian, H., et al. (2022) Characteristics, Goal‐oriented Treatments and Survival of Pulmonary Arterial Hypertension in China: Insights from a National Multi-Centre Prospective Registry. Respirology, 27, 517-528.
https://doi.org/10.1111/resp.14247
[2] Beyhan Sagmen, S. and Fidan, A. (2022) Can FVC/DLCO Predict Pulmonary Hypertension in Patients with Chronic Obstructive Pulmonary Disease? European Review for Medical and Pharmacological Sciences, 26, 6658-6664.
[3] Gonzalez-Garcia, M., Aguirre-Franco, C.E., Vargas-Ramirez, L., Barrero, M. and Torres-Duque, C.A. (2022) Effect of Pulmonary Hypertension on Exercise Capacity and Gas Exchange in Patients with Chronic Obstructive Pulmonary Disease Living at High Altitude. Chronic Respiratory Disease, 19, Article 14799731221104095.
https://doi.org/10.1177/14799731221104095
[4] 王建美, 袁天翊, 高丽, 等. 低氧性肺动脉高压病理机制与治疗药物研究进展[J]. 中国药理学通报, 2022, 38(9): 1281-1288.
[5] Liu, G., Fu, D., Tian, H. and Dai, A. (2021) The Mechanism of Ions in Pulmonary Hypertension. Pulmonary Circulation, 11, 1-20.
https://doi.org/10.1177/2045894020987948
[6] Liu, J., Wang, W., Wang, L., Chen, S., Tian, B., Huang, K., et al. (2018) IL-33 Initiates Vascular Remodelling in Hypoxic Pulmonary Hypertension by Up-Regulating Hif-1α and VEGF Expression in Vascular Endothelial Cells. eBioMedicine, 33, 196-210.
https://doi.org/10.1016/j.ebiom.2018.06.003
[7] Evans, C.E., Cober, N.D., Dai, Z., Stewart, D.J. and Zhao, Y. (2021) Endothelial Cells in the Pathogenesis of Pulmonary Arterial Hypertension. European Respiratory Journal, 58, Article 2003957.
https://doi.org/10.1183/13993003.03957-2020
[8] Mao, J. and Ma, L. (2022) Research Progress on the Mechanism of Phenotypic Transformation of Pulmonary Artery Smooth Muscle Cells Induced by Hypoxia. Journal of Zhejiang University (Medical Sciences), 51, 750-757.
https://doi.org/10.3724/zdxbyxb-2022-0282
[9] Xue, J., Zhang, Z., Sun, Y., Jin, D., Guo, L., Li, X., et al. (2023) Research Progress and Molecular Mechanisms of Endothelial Cells Inflammation in Vascular-Related Diseases. Journal of Inflammation Research, 16, 3593-3617.
https://doi.org/10.2147/jir.s418166
[10] Wang, X. and He, B. (2024) Endothelial Dysfunction: Molecular Mechanisms and Clinical Implications. MedComm, 5, e651.
https://doi.org/10.1002/mco2.651
[11] Pellicori, P., Cleland, J.G.F. and Clark, A.L. (2022) Chronic Obstructive Pulmonary Disease and Heart Failure. Cardiology Clinics, 40, 171-182.
https://doi.org/10.1016/j.ccl.2021.12.005
[12] Humbert, M., Kovacs, G., Hoeper, M.M., Badagliacca, R., Berger, R.M.F., Brida, M., et al. (2022) 2022 ESC/ERS Guidelines for the Diagnosis and Treatment of Pulmonary Hypertension. European Heart Journal, 43, 3618-3731.
https://doi.org/10.1093/eurheartj/ehac237
[13] 罗勤, 熊长明. 肺血管病右心导管术操作指南[J]. 中国循环杂志, 2022, 37(12): 1186-1194.
[14] 郭华, 李扬, 孙继锋. CT肺动脉成像在评价慢性阻塞性肺疾病合并肺动脉高压的应用[J]. 医学影像学杂志, 2022, 32(6): 1054-1056.
[15] 王大伟, 杨飞, 杨智翔, 等. 回顾性心电门控CTPA在评估肺动脉高压患者肺动脉弹性及心功能的应用价值[J]. 中国医药导报, 2022, 19(19): 156-159.
[16] 赵勤华, 王岚, 何晶, 等. 心电图对肺动脉高压的诊断价值探讨[C]//中国心脏大会2014论文汇编: 2014年卷. 2014: 376-377.
[17] 中华医学会呼吸病学分会肺栓塞与肺血管病学组, 中国医师协会呼吸医师分会肺栓塞与肺血管病工作委员会, 全国肺栓塞与肺血管病防治协作组, 等. 中国肺动脉高压诊断与治疗指南(2021版) [J]. 中华医学杂志, 2021, 101(1): 11-51.
[18] 靳文英, 王之龙, 朱天刚. 肺动脉高压的心脏超声评估[J]. 中华全科医师杂志, 2019, 18(12): 1196-1198.
[19] Montané, B.E., Fiore, A.M., Reznicek, E.C., Jain, V., Jellis, C., Rokadia, H., et al. (2021) Optimal Tricuspid Regurgitation Velocity to Screen for Pulmonary Hypertension in Tertiary Referral Centers. Chest, 160, 2209-2219.
https://doi.org/10.1016/j.chest.2021.06.046
[20] Sumimoto, K., Tanaka, H., Mukai, J., Yamashita, K., Tanaka, Y., Shono, A., et al. (2020) Optimal Cut-Off of Tricuspid Regurgitation Velocity According to the New Definition of Pulmonary Hypertension―Its Use in Predicting Pulmonary Hypertension. Circulation Reports, 2, 625-629.
https://doi.org/10.1253/circrep.cr-20-0094
[21] 杜佩, 范小明, 张健, 等. 多普勒技术评估房间隔缺损合并肺动脉高压的应用价值[J]. 临床超声医学杂志, 2018, 20(6): 370-373.
[22] Albani, S., Stolfo, D., Venkateshvaran, A., Chubuchny, V., Biondi, F., De Luca, A., et al. (2022) Echocardiographic Biventricular Coupling Index to Predict Precapillary Pulmonary Hypertension. Journal of the American Society of Echocardiography, 35, 715-726.
https://doi.org/10.1016/j.echo.2022.02.003
[23] Li, M., Wang, Y., Li, H., Huang, Y., Huang, T., Zhang, C., et al. (2021) A Prediction Model of Simple Echocardiographic Variables to Screen for Potentially Correctable Shunts in Adult Patients with Pulmonary Arterial Hypertension Associated with Atrial Septal Defects: A Cross-Sectional Study. The International Journal of Cardiovascular Imaging, 37, 1551-1562.
https://doi.org/10.1007/s10554-020-02128-5
[24] Correale, M., Tricarico, L., Padovano, G., Ferraretti, A., Monaco, I., Musci, R.L., et al. (2019) Echocardiographic Score for Prediction of Pulmonary Hypertension at Catheterization: The Daunia Heart Failure Registry. Journal of Cardiovascular Medicine, 20, 809-815.
https://doi.org/10.2459/jcm.0000000000000853
[25] 周拓. CT肺动脉成像对COPD合并肺动脉高压的诊断价值[J]. 中国CT和MRI杂志, 2019, 17(5): 79-82.
[26] Corson, N., Armato, S.G., Labby, Z.E., Straus, C., Starkey, A. and Gomberg-Maitland, M. (2014) CT-Based Pulmonary Artery Measurements for the Assessment of Pulmonary Hypertension. Academic Radiology, 21, 523-530.
https://doi.org/10.1016/j.acra.2013.12.015
[27] 中华医学会放射学分会心胸学组. 慢性阻塞性肺疾病胸部CT检查及评价中国专家共识[J]. 中华放射学杂志, 2023, 57(6): 600-607.
[28] Lungu, A., Swift, A.J., Capener, D., Kiely, D., Hose, R. and Wild, J.M. (2016) Diagnosis of Pulmonary Hypertension from Magnetic Resonance Imaging-Based Computational Models and Decision Tree Analysis. Pulmonary Circulation, 6, 181-190.
https://doi.org/10.1086/686020
[29] Wang, Y., Zhao, S. and Lu, M. (2024) State-of-the Art Cardiac Magnetic Resonance in Pulmonary Hypertension—An Update on Diagnosis, Risk Stratification and Treatment. Trends in Cardiovascular Medicine, 34, 161-171.
https://doi.org/10.1016/j.tcm.2022.12.005
[30] 谢洪燕, 刘东婷, 刘家祎, 等. 心脏磁共振在肺动脉高压的应用与研究进展[J]. 心肺血管病杂志, 2023, 42(9): 974-978.
[31] 高杨, 谢江, 王增智, 等. 支气管扩张症合并肺动脉高压患者的临床特征分析[J]. 中国医药, 2022, 17(8): 1159-1163.
[32] 程子超, 李海威, 彭红玉, 等. 射血分数保留型心力衰竭相关性肺动脉高压研究进展[J]. 中国医药, 2023, 18(1): 119-122.
[33] 张宝美, 胡春峰, 程守全, 等. 心脏磁共振室间隔曲率对成人房间隔缺损肺动脉高压的诊断价值[J]. 徐州医科大学学报, 2021, 41(4): 261-266.
[34] Galiè, N., Humbert, M., Vachiery, J., Gibbs, S., Lang, I., Torbicki, A., et al. (2015) 2015 ESC/ERS Guidelines for the Diagnosis and Treatment of Pulmonary Hypertension. European Heart Journal, 37, 67-119.
https://doi.org/10.1093/eurheartj/ehv317
[35] Yogeswaran, A., Tello, K., Faber, M., Sommer, N., Kuhnert, S., Seeger, W., et al. (2020) Risk Assessment in Severe Pulmonary Hypertension Due to Interstitial Lung Disease. The Journal of Heart and Lung Transplantation, 39, 1118-1125.
https://doi.org/10.1016/j.healun.2020.06.014
[36] 倪炯, 王培军. 医学影像人工智能的现状与未来[J]. 中华医学杂志, 2021, 101(7): 455-457.
[37] Tison, G.H., Zhang, J., Delling, F.N. and Deo, R.C. (2019) Automated and Interpretable Patient ECG Profiles for Disease Detection, Tracking, and Discovery. Circulation: Cardiovascular Quality and Outcomes, 12, e005289.
https://doi.org/10.1161/circoutcomes.118.005289
[38] Aras, M.A., Abreau, S., Mills, H., Radhakrishnan, L., Klein, L., Mantri, N., et al. (2023) Electrocardiogram Detection of Pulmonary Hypertension Using Deep Learning. Journal of Cardiac Failure, 29, 1017-1028.
https://doi.org/10.1016/j.cardfail.2022.12.016
[39] Diller, G., Kempny, A., Babu-Narayan, S.V., Henrichs, M., Brida, M., Uebing, A., et al. (2019) Machine Learning Algorithms Estimating Prognosis and Guiding Therapy in Adult Congenital Heart Disease: Data from a Single Tertiary Centre Including 10 019 Patients. European Heart Journal, 40, 1069-1077.
https://doi.org/10.1093/eurheartj/ehy915
[40] Nardelli, P., Jimenez-Carretero, D., Bermejo-Pelaez, D., Washko, G.R., Rahaghi, F.N., Ledesma-Carbayo, M.J., et al. (2018) Pulmonary Artery–Vein Classification in CT Images Using Deep Learning. IEEE Transactions on Medical Imaging, 37, 2428-2440.
https://doi.org/10.1109/tmi.2018.2833385
[41] Huang, L., Li, J., Huang, M., Zhuang, J., Yuan, H., Jia, Q., et al. (2019) Prediction of Pulmonary Pressure after Glenn Shunts by Computed Tomography–based Machine Learning Models. European Radiology, 30, 1369-1377.
https://doi.org/10.1007/s00330-019-06502-3
[42] Charters, P.F.P., Rossdale, J., Brown, W., Burnett, T.A., Komber, H.M.E.I., Thompson, C., et al. (2022) Diagnostic Accuracy of an Automated Artificial Intelligence Derived Right Ventricular to Left Ventricular Diameter Ratio Tool on CT Pulmonary Angiography to Predict Pulmonary Hypertension at Right Heart Catheterisation. Clinical Radiology, 77, e500-e508.
https://doi.org/10.1016/j.crad.2022.03.009
[43] ЧЖУ, Ф., ХУ, Д., ЛЮ, Я., et al. (2020) Машинное обучение для диагностики легочной гипертензии (Machine Learning for the Diagnosis of Pulmonary Hypertension). Кардиология, 60, 96.
https://lib.ossn.ru/jour/article/view/953
[44] Kiely, D.G., Doyle, O., Drage, E., Jenner, H., Salvatelli, V., Daniels, F.A., et al. (2019) Utilising Artificial Intelligence to Determine Patients at Risk of a Rare Disease: Idiopathic Pulmonary Arterial Hypertension. Pulmonary Circulation, 9, 1-9.
https://doi.org/10.1177/2045894019890549
[45] Ong, M., Klann, J.G., Lin, K.J., Maron, B.A., Murphy, S.N., Natter, M.D., et al. (2020) Claims-Based Algorithms for Identifying Patients with Pulmonary Hypertension: A Comparison of Decision Rules and Machine-Learning Approaches. Journal of the American Heart Association, 9, e016648.
https://doi.org/10.1161/jaha.120.016648