整合超声心动图与临床特征的心力衰竭患者肺动脉高压多模态预测模型构建及验证

赖宇星; 邹春峰; 苏津自; 卢卓强; 庄伟; 高彦伟; 余盛彬; 李家缙; 曾勇军; 方周菲; 蔡瀚

doi:10.16439/j.issn.1673-7245.2025-0207

中华高血压杂志（中英文） ›› 2026, Vol. 34 ›› Issue (7) : 656 -670. DOI: 10.16439/j.issn.1673-7245.2025-0207

论著

整合超声心动图与临床特征的心力衰竭患者肺动脉高压多模态预测模型构建及验证

赖宇星 ¹^,²^,³^,⁴^,⁵ ,
邹春峰 ⁶ ,
苏津自 ¹^,²^,³^,⁴^,⁵ ,
卢卓强 ¹^,²^,³^,⁴^,⁵ ,
庄伟 ¹^,²^,³^,⁴^,⁵ ,
高彦伟 ¹^,²^,³^,⁴^,⁵ ,
余盛彬 ¹^,²^,³^,⁴^,⁵ ,
李家缙 ⁷ ,
曾勇军 ¹^,²^,³^,⁴^,⁵ ,
方周菲 ⁸^,⁹ ,
蔡瀚 ¹^,²^,³^,⁴^,⁵

作者信息 +

Construction and validation of a multimodal predictive model for pulmonary hypertension in heart failure patients integrating echocardiographic and clinical features

Yuxing LAI ¹^,²^,³^,⁴^,⁵ ,
Chunfeng ZOU ⁶ ,
Jinzi SU ¹^,²^,³^,⁴^,⁵ ,
Zhuoqiang LU ¹^,²^,³^,⁴^,⁵ ,
Wei ZHUANG ¹^,²^,³^,⁴^,⁵ ,
Yanwei GAO ¹^,²^,³^,⁴^,⁵ ,
Shengbin YU ¹^,²^,³^,⁴^,⁵ ,
Jiajin LI ⁷ ,
Yongjun ZENG ¹^,²^,³^,⁴^,⁵ ,
Zhoufei FANG ⁸^,⁹ ,
Han CAI ¹^,²^,³^,⁴^,⁵

Author information +

文章历史 +

PDF (2610K)

摘要

目的系统整合心力衰竭患者的超声心动图参数（包括右心结构、功能相关指标）与临床特征（生物标志物、心功能分级、基础疾病），构建肺动脉高压（PH）多模态预测模型并验证其检验效能。方法本研究共纳入146例心力衰竭患者。经右心导管检查（RHC）确诊为心力衰竭合并PH者共105例，包括单纯毛细血管前PH（pre-capillary PH）18例、单纯毛细血管后PH（Ipc-PH）56例，以及毛细血管前与毛细血管后混合性PH（Cpc-PH）31例。以RHC为金标准，评估超声心动图诊断PH的准确性。在此基础上，整合临床特征、生物标志物及超声心动图参数，构建多模态预测模型，通过Cox比例风险模型评估模型预测值与主要临床不良事件（包括心力衰竭再住院、呼吸衰竭、肺性脑病及死亡）的相关性。验证队列的50例心力衰竭患者（36例确诊为PH）通过受试者操作特征（ROC）曲线评估该模型的诊断效能。结果本研究纳入的心力衰竭患者中，根据新指南标准[平均肺动脉压（mPAP）＞20 mmHg]诊断的PH比例为71.92%（105/146）。超声心动图肺动脉收缩压诊断PH的效能有限（最佳截断值46.5 mmHg，灵敏度为53.3%）。基于二元logistic回归分析结果，构建多模态预测模型，其评分公式为：PH评分=0.185 × I（脑利尿钠肽＞358 ng/L） + 1.243 × I（左室射血分数＜54.5%） + 3.580 × I（右心房收缩末期面积＞ 20.5 cm²） + 4.180 × I（右心室舒张末期内径＞3.26 cm） + 2.883 × I（三尖瓣环收缩期位移/ 肺动脉收缩压＜0.325） + 1.965 × I（心房颤动）–6.865[其中I（·）为示性函数，条件满足时取值为1，否则为0]。该评分对应的概率为：P = e^PH评分/（1 + e^PH评分）。该预测模型的诊断效能显著优于单一超声心动图指标[曲线下面积（AUC）=0.955，单一指标AUC最大值为0.792（三尖瓣环收缩期位移/肺动脉收缩压），ΔAUC=0.163，95%CI: 0.078～0.242， P＜0.001]。模型预测值P值与主要临床不良事件有一定相关性（HR = 14.985）。验证队列AUC=0.960（95%CI：0.912～0.999），灵敏度为77.78%，特异度为92.86%。结论本研究成功整合超声心动图核心参数与临床特征变量，构建了心力衰竭患者PH多模态预测模型，能够较准确地无创筛查心力衰竭患者是否合并PH，且其预测值与不良预后相关。

Abstract

Objective To systematically integrate echocardiographic parameters （including right heart structural and functional indicators） and clinical features （biomarkers, heart function classification, and underlying diseases） in heart failure （HF） patients, and to construct a multimodal predictive model for pulmonary hypertension （PH） and validate its diagnostic efficacy. Methods A total of 146 HF patients were included in this study. Among them, 105 patients were diagnosed with HF combined with PH by right heart catheterization （RHC）, including 18 cases of isolated pre-capillary PH （pre-capillary PH）, 56 cases of isolated post-capillary PH （Ipc-PH）, and 31 cases of combined pre-capillary and postcapillary PH （Cpc-PH）. The accuracy of echocardiography （ECHO） in diagnosing PH was evaluated with RHC as the gold standard. Based on this, a multimodal predictive model was developed by integrating clinical features, biomarkers, and ECHO parameters. The model's predicted values were assessed for correlation with major clinical adverse events （including HF rehospitalization, respiratory failure, pulmonary encephalopathy, and death） using the Cox proportional hazards model. In the validation cohort, 50 HF patients （36 diagnosed with PH） were assessed using the receiver operating characteristic （ROC） curve to evaluate the model's diagnostic performance. Results In this study, 71.92% （105/146） patients with heart failure were diagnosed with PH according to the new guideline criteria （mean pulmonary artery pressure, mPAP＞ 20 mmHg）. The efficacy of echocardiography assessed pulmonary arterial systolic pressure （PASP） was limited for diagnosing PH, with a sensitivity of 53.3% at the optimal cutoff of 46.5 mmHg. Based on the results of the binary logistic regression analysis, we constructed a multimodal predictive model with the following scoring formula: PH score = 0.185 × I （brain natriuretic peptide＞ 358 ng/L） + 1.243 × I （left ventricular ejection fraction＜ 54.5%） + 3.580 × I （end-systolic right atrial area＞20.5 cm2） + 4.180 × I （right ventricular end-diastolic diameter＞3.26 cm） + 2.883 × I （tricuspid annular plane systolic excursion/PASP ratio＜0.325） + 1.965 × I （atrial fibrillation） −6.865; where I（·） is the indicator function, taking a value of 1 when the condition is satisfied, otherwise 0. The corresponding probability for this score is: P = e^{PH score} / （1 + e^{PH score}）. The predictive performance of this model was significantly superior to that of any single ECHO indicators (AUC = 0.955 vs. 0.792 [the highest AUC for a single indicator, achieved by tricuspid annular plane systolic excursion/ PASP ratio], ΔAUC = 0.163, 95%CI: 0.078 to 0.242, P＜ 0.001). The model's predicted values were also significantly correlated with major clinical adverse events （HR = 14.985）. In the validation cohort, AUC = 0.960 （95%CI: 0.912 to 0.999）, with a sensitivity of 77.78% and specificity of 92.86%. Conclusions This study successfully integrated core echocardiographic parameters and clinical feature variables to construct a multimodal predictive model for PH in HF patients. The model can accurately screen for the presence of pulmonary hypertension in heart failure patients non-invasively and its predicted values are associated with adverse prognosis.

关键词

超声心动图 / 心力衰竭 / 肺动脉高压 / 多模态模型

Key words

echocardiography / heart failure / pulmonary hypertension / multimodal model

引用本文

引用格式 ▾

赖宇星,邹春峰,苏津自,卢卓强,庄伟,高彦伟,余盛彬,李家缙,曾勇军,方周菲,蔡瀚. 整合超声心动图与临床特征的心力衰竭患者肺动脉高压多模态预测模型构建及验证[J]. 中华高血压杂志（中英文）, 2026, 34(7): 656-670 DOI:10.16439/j.issn.1673-7245.2025-0207

登录浏览全文

4963

注册一个新账户忘记密码

参考文献

原文顺序 | 出版日期 | 本文引用

[1]	Johnson S, Sommer N, Cox—Flaherty K, et al. Pulmonary hypertension: a contemporary review[J]. Am J Respir Crit Care Med, 2023, 208(5): 528-548.

[2]	Ruopp NF, Cockrill BA . Diagnosis and treatment of pulmonary arterial hypertension: a review[J]. JAMA, 2022, 327(14): 1379-1391.

[3]	Perros F, Humbert M, Dorfmüller P . Smouldering fire or conflagration? An illustrated update on the concept of inflammation in pulmonary arterial hypertension[J]. Eur Respir Rev, 2021, 30(162): 210161.

[4]	Kurakula K, Smolders VFED, Tura—Ceide O, et al. Endothelial dysfunction in pulmonary hypertension: cause or consequence?[J]. Biomedicines, 2021, 9(1): 57.

[5]	Riley JM, Fradin JJ, Russ DH, et al. Post—capillary pulmonary hypertension: clinical review[J]. J Clin Med, 2024, 13(2): 625.

[6]	Gerges C, Pistritto AM, Gerges M, et al. Left ventricular filling pressure in chronic thromboembolic pulmonary hypertension[J]. J Am Coll Cardiol, 2023, 81(7): 653-664.

[7]	Jang AY, Park SJ, Chung WJ . Pulmonary hypertension in heart failure[J]. Int J Heart Fail, 2021, 3(3): 147-159.

[8]	Alamri AK, Ma CL, Ryan JJ . Left heart disease—related pulmonary hypertension[J]. Cardiol Clin, 2022, 40(1): 69-76.

[9]	Garry JD, Kundu S, Annis J, et al. Incidence of pulmonary hypertension in the echocardiography referral population[J]. Ann Am Thorac Soc, 2025, 22(5): 679-688.

[10]	Kadoglou NPE, Khattab E, Velidakis N, et al. The role of echocardiography in the diagnosis and prognosis of pulmonary hypertension[J]. J Pers Med, 2024, 14(5): 474.

[11]	Fisher MR, Criner GJ, Fishman AP, et al. Estimating pulmonary artery pressures by echocardiography in patients with emphysema[J]. Eur Respir J, 2007, 30(5): 914-921.

[12]	Chen ZW, Chung YW, Cheng JF, et al. Right ventricular—vascular uncoupling predicts pulmonary hypertension in clinically diagnosed heart failure with preserved ejection fraction[J]. J Am Heart Assoc, 2024, 13(1): e030025.

[13]	Wang D, Fan G, Zhang X, et al. Prevalence of long—term right ventricular dysfunction after acute pulmonary embolism: a systematic review and meta—analysis[J]. EClinicalMedicine, 2023, 62: 102153.

[14]	Johns CS, Rajaram S, Capener DA, et al. Non—invasive methods for estimating mPAP in COPD using cardiovascular magnetic resonance imaging[J]. Eur Radiol, 2018, 28(4): 1438-1448.

[15]	Humbert M, Kovacs G, Hoeper MM, et al. 2022 ESC/ERS guidelines for the diagnosis and treatment of pulmonary hypertension[J]. Eur Heart J, 2022, 43(38): 3618-3731.

[16]	Jone PN, Ivy DD, Hauck A, et al. Pulmonary hypertension in congenital heart disease: a scientific statement from the American Heart Association[J]. Circ Heart Fail, 2023, 16(7): e00080.

[17]	Hoeper MM, Lee SH, Voswinckel R, et al. Complications of right heart catheterization procedures in patients with pulmonary hypertension in experienced centers[J]. J Am Coll Cardiol, 2006, 48(12): 2546-2552.

[18]	Chen Y, Shlofmitz E, Khalid N, et al. Right heart catheterization—related complications: a review of the literature and best practices[J]. Cardiol Rev, 2020, 28(1): 36-41.

[19]	Alenezi F, Covington TA, Mukherjee M, et al. Novel approaches to imaging the pulmonary vasculature and right heart[J]. Circ Res, 2022, 130(9): 1445-1465.

[20]	Maron BA, Kovacs G, Vaidya A, et al. Cardiopulmonary hemodynamics in pulmonary hypertension and heart failure: JACC review topic of the week[J]. J Am Coll Cardiol, 2020, 76(22): 2671-2681.

[21]	Maron BA, Hess E, Maddox TM, et al. Association of borderline pulmonary hypertension with mortality and hospitalization in a large patient cohort: insights from the veterans affairs clinical assessment, reporting, and tracking program[J]. Circulation, 2016, 133(13): 1240-1248.

[22]	Brusca SB, Zou Y, Elinoff JM . How low should we go? Potential benefits and ramifications of the pulmonary hypertension hemodynamic definitions proposed by the 6th World Symposium[J]. Curr Opin Pulm Med, 2020, 26(5): 384-390.

[23]	Atagün Güney P, Çardak ME . Effectiveness of echocardiographic evaluation of lung transplant candidates: could it be an alternative to right heart catheterization?[J]. Turk Gogus Kalp Damar Cerrahisi Derg, 2022, 30(4): 584-592.

[24]	Albani S, Stolfo D, Venkateshvaran A, et al. Echocardiographic biventricular coupling index to predict precapillary pulmonary hypertension[J]. J Am Soc Echocardiogr, 2022, 35(7): 715-726.

[25]

Li M, Wang Y, Li H, et al. 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[J]. Int J Cardiovasc Imaging, 2021, 37(5): 1551-1562.

[26]	Latimer K, Layne M, Payne M . Pulmonary hypertension[J]. Am Fam Physician, 2024, 110(2): 183-191.

[27]	Correale M, Tricarico L, Padovano G, et al. Echocardiographic score for prediction of pulmonary hypertension at catheterization: the Daunia heart failure registry[J]. J Cardiovasc Med (Hagerstown), 2019, 20(12): 809-815.