An Unsupervised Approach to Derive Right Ventricular Pressure–Volume Loop Phenotypes in Pulmonary Hypertension

ABSTRACT Although right ventricle (RV) dysfunction drives clinical worsening in pulmonary hypertension (PH), information about RV function has not been well integrated in PH risk assessment. The gold standard for assessing RV function and ventriculo‐arterial coupling is the construction of multi‐bea...

Full description

Saved in:
Bibliographic Details
Main Authors: Nikita Sivakumar, Cindy Zhang, Connie Chang‐Chien, Pan Gu, Yikun Li, Yi Yang, Darin Rosen, Tijana Tuhy, Ilton M. Cubero Salazar, Matthew Kauffman, Rachel L. Damico, Casey Overby Taylor, Joseph L. Greenstein, Steven Hsu, Paul M. Hassoun, Catherine E. Simpson
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Pulmonary Circulation
Subjects:
Online Access:https://doi.org/10.1002/pul2.70057
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063298469298176
author Nikita Sivakumar
Cindy Zhang
Connie Chang‐Chien
Pan Gu
Yikun Li
Yi Yang
Darin Rosen
Tijana Tuhy
Ilton M. Cubero Salazar
Matthew Kauffman
Rachel L. Damico
Casey Overby Taylor
Joseph L. Greenstein
Steven Hsu
Paul M. Hassoun
Catherine E. Simpson
author_facet Nikita Sivakumar
Cindy Zhang
Connie Chang‐Chien
Pan Gu
Yikun Li
Yi Yang
Darin Rosen
Tijana Tuhy
Ilton M. Cubero Salazar
Matthew Kauffman
Rachel L. Damico
Casey Overby Taylor
Joseph L. Greenstein
Steven Hsu
Paul M. Hassoun
Catherine E. Simpson
author_sort Nikita Sivakumar
collection DOAJ
description ABSTRACT Although right ventricle (RV) dysfunction drives clinical worsening in pulmonary hypertension (PH), information about RV function has not been well integrated in PH risk assessment. The gold standard for assessing RV function and ventriculo‐arterial coupling is the construction of multi‐beat pressure–volume (PV) loops. PV loops are technically challenging to acquire and not feasible for routine clinical use. Therefore, we aimed to map standard clinically available measurements to emergent PV loop phenotypes. One hundred and one patients with suspected PH underwent right heart catheterization (RHC) with exercise, multi‐beat PV loop measurement, and same‐day cardiac magnetic resonance imaging (CMR). We applied unsupervised k‐means clustering on 10 PV loop metrics to obtain three patient groups with unique RV functional phenotypes and times to clinical worsening. We integrated RHC and CMR measurements to train a random forest classifier that predicts the PV loop patient group with high discrimination (AUC = 0.93). The most informative variable for PV loop phenotype prediction was exercise mean pulmonary arterial pressure (mPAP). Distinct and clinically meaningful PV loop phenotypes exist that can be predicted using clinically accessible hemodynamic and RV‐centric measurements. Exercise mPAP may inform RV pressure–volume relationships.
format Article
id doaj-art-e69d11bfd41546ad9a82f3d6f92c902a
institution DOAJ
issn 2045-8940
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Pulmonary Circulation
spelling doaj-art-e69d11bfd41546ad9a82f3d6f92c902a2025-08-20T02:49:40ZengWileyPulmonary Circulation2045-89402025-01-01151n/an/a10.1002/pul2.70057An Unsupervised Approach to Derive Right Ventricular Pressure–Volume Loop Phenotypes in Pulmonary HypertensionNikita Sivakumar0Cindy Zhang1Connie Chang‐Chien2Pan Gu3Yikun Li4Yi Yang5Darin Rosen6Tijana Tuhy7Ilton M. Cubero Salazar8Matthew Kauffman9Rachel L. Damico10Casey Overby Taylor11Joseph L. Greenstein12Steven Hsu13Paul M. Hassoun14Catherine E. Simpson15Institute for Computational Medicine Johns Hopkins University Baltimore Maryland USAInstitute for Computational Medicine Johns Hopkins University Baltimore Maryland USAInstitute for Computational Medicine Johns Hopkins University Baltimore Maryland USAInstitute for Computational Medicine Johns Hopkins University Baltimore Maryland USAInstitute for Computational Medicine Johns Hopkins University Baltimore Maryland USAInstitute for Computational Medicine Johns Hopkins University Baltimore Maryland USADivision of Pulmonary and Critical Care Medicine Baltimore Maryland USADivision of Pulmonary and Critical Care Medicine Baltimore Maryland USADivision of Cardiology Johns Hopkins University School of Medicine Baltimore Maryland USADivision of Pulmonary and Critical Care Medicine Baltimore Maryland USADivision of Pulmonary and Critical Care Medicine Baltimore Maryland USAInstitute for Computational Medicine Johns Hopkins University Baltimore Maryland USAInstitute for Computational Medicine Johns Hopkins University Baltimore Maryland USADivision of Cardiology Johns Hopkins University School of Medicine Baltimore Maryland USADivision of Pulmonary and Critical Care Medicine Baltimore Maryland USADivision of Pulmonary and Critical Care Medicine Baltimore Maryland USAABSTRACT Although right ventricle (RV) dysfunction drives clinical worsening in pulmonary hypertension (PH), information about RV function has not been well integrated in PH risk assessment. The gold standard for assessing RV function and ventriculo‐arterial coupling is the construction of multi‐beat pressure–volume (PV) loops. PV loops are technically challenging to acquire and not feasible for routine clinical use. Therefore, we aimed to map standard clinically available measurements to emergent PV loop phenotypes. One hundred and one patients with suspected PH underwent right heart catheterization (RHC) with exercise, multi‐beat PV loop measurement, and same‐day cardiac magnetic resonance imaging (CMR). We applied unsupervised k‐means clustering on 10 PV loop metrics to obtain three patient groups with unique RV functional phenotypes and times to clinical worsening. We integrated RHC and CMR measurements to train a random forest classifier that predicts the PV loop patient group with high discrimination (AUC = 0.93). The most informative variable for PV loop phenotype prediction was exercise mean pulmonary arterial pressure (mPAP). Distinct and clinically meaningful PV loop phenotypes exist that can be predicted using clinically accessible hemodynamic and RV‐centric measurements. Exercise mPAP may inform RV pressure–volume relationships.https://doi.org/10.1002/pul2.70057cardiac resonance imagingright heart catheterizationright ventricular‐pulmonary arterial couplingunsupervised clustering
spellingShingle Nikita Sivakumar
Cindy Zhang
Connie Chang‐Chien
Pan Gu
Yikun Li
Yi Yang
Darin Rosen
Tijana Tuhy
Ilton M. Cubero Salazar
Matthew Kauffman
Rachel L. Damico
Casey Overby Taylor
Joseph L. Greenstein
Steven Hsu
Paul M. Hassoun
Catherine E. Simpson
An Unsupervised Approach to Derive Right Ventricular Pressure–Volume Loop Phenotypes in Pulmonary Hypertension
Pulmonary Circulation
cardiac resonance imaging
right heart catheterization
right ventricular‐pulmonary arterial coupling
unsupervised clustering
title An Unsupervised Approach to Derive Right Ventricular Pressure–Volume Loop Phenotypes in Pulmonary Hypertension
title_full An Unsupervised Approach to Derive Right Ventricular Pressure–Volume Loop Phenotypes in Pulmonary Hypertension
title_fullStr An Unsupervised Approach to Derive Right Ventricular Pressure–Volume Loop Phenotypes in Pulmonary Hypertension
title_full_unstemmed An Unsupervised Approach to Derive Right Ventricular Pressure–Volume Loop Phenotypes in Pulmonary Hypertension
title_short An Unsupervised Approach to Derive Right Ventricular Pressure–Volume Loop Phenotypes in Pulmonary Hypertension
title_sort unsupervised approach to derive right ventricular pressure volume loop phenotypes in pulmonary hypertension
topic cardiac resonance imaging
right heart catheterization
right ventricular‐pulmonary arterial coupling
unsupervised clustering
url https://doi.org/10.1002/pul2.70057
work_keys_str_mv AT nikitasivakumar anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT cindyzhang anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT conniechangchien anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT pangu anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT yikunli anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT yiyang anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT darinrosen anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT tijanatuhy anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT iltonmcuberosalazar anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT matthewkauffman anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT rachelldamico anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT caseyoverbytaylor anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT josephlgreenstein anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT stevenhsu anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT paulmhassoun anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT catherineesimpson anunsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT nikitasivakumar unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT cindyzhang unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT conniechangchien unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT pangu unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT yikunli unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT yiyang unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT darinrosen unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT tijanatuhy unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT iltonmcuberosalazar unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT matthewkauffman unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT rachelldamico unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT caseyoverbytaylor unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT josephlgreenstein unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT stevenhsu unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT paulmhassoun unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension
AT catherineesimpson unsupervisedapproachtoderiverightventricularpressurevolumeloopphenotypesinpulmonaryhypertension