1
|
Alabed S, Uthoff J, Zhou S, Garg P, Dwivedi K, Alandejani F, Gosling R, Schobs L, Brook M, Shahin Y, Capener D, Johns CS, Wild JM, Rothman AMK, van der Geest RJ, Condliffe R, Kiely DG, Lu H, Swift AJ. Machine learning cardiac-MRI features predict mortality in newly diagnosed pulmonary arterial hypertension. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2022; 3:265-275. [PMID: 36713008 PMCID: PMC9708011 DOI: 10.1093/ehjdh/ztac022] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/29/2021] [Revised: 02/19/2022] [Indexed: 02/01/2023]
Abstract
Aims Pulmonary arterial hypertension (PAH) is a rare but serious disease associated with high mortality if left untreated. This study aims to assess the prognostic cardiac magnetic resonance (CMR) features in PAH using machine learning. Methods and results Seven hundred and twenty-three consecutive treatment-naive PAH patients were identified from the ASPIRE registry; 516 were included in the training, and 207 in the validation cohort. A multilinear principal component analysis (MPCA)-based machine learning approach was used to extract mortality and survival features throughout the cardiac cycle. The features were overlaid on the original imaging using thresholding and clustering of high- and low-risk of mortality prediction values. The 1-year mortality rate in the validation cohort was 10%. Univariable Cox regression analysis of the combined short-axis and four-chamber MPCA-based predictions was statistically significant (hazard ratios: 2.1, 95% CI: 1.3, 3.4, c-index = 0.70, P = 0.002). The MPCA features improved the 1-year mortality prediction of REVEAL from c-index = 0.71 to 0.76 (P ≤ 0.001). Abnormalities in the end-systolic interventricular septum and end-diastolic left ventricle indicated the highest risk of mortality. Conclusion The MPCA-based machine learning is an explainable time-resolved approach that allows visualization of prognostic cardiac features throughout the cardiac cycle at the population level, making this approach transparent and clinically interpretable. In addition, the added prognostic value over the REVEAL risk score and CMR volumetric measurements allows for a more accurate prediction of 1-year mortality risk in PAH.
Collapse
Affiliation(s)
| | - Johanna Uthoff
- Department of Computer Science, University of Sheffield, Sheffield, UK
| | - Shuo Zhou
- Department of Computer Science, University of Sheffield, Sheffield, UK
| | - Pankaj Garg
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Krit Dwivedi
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK,Department of Clinical Radiology, Sheffield Teaching Hospitals, Sheffield, UK
| | - Faisal Alandejani
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Rebecca Gosling
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Lawrence Schobs
- Department of Computer Science, University of Sheffield, Sheffield, UK
| | - Martin Brook
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Yousef Shahin
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Dave Capener
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Christopher S Johns
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK,Department of Clinical Radiology, Sheffield Teaching Hospitals, Sheffield, UK
| | - Jim M Wild
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK,INSIGNEO, Institute for in silico medicine, University of Sheffield, UK
| | - Alexander M K Rothman
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | | | - Robin Condliffe
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK,Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield, UK
| | - David G Kiely
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK,INSIGNEO, Institute for in silico medicine, University of Sheffield, UK,Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield, UK
| | | | | |
Collapse
|
2
|
Zaky A, Zafar I, Masjoan-Juncos JX, Husain M, Mariappan N, Morgan CJ, Hamid T, Frölich MA, Ahmad S, Ahmad A. Echocardiographic, Biochemical, and Electrocardiographic Correlates Associated With Progressive Pulmonary Arterial Hypertension. Front Cardiovasc Med 2021; 8:705666. [PMID: 34355033 PMCID: PMC8329095 DOI: 10.3389/fcvm.2021.705666] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2021] [Accepted: 06/09/2021] [Indexed: 12/15/2022] Open
Abstract
Background: Pulmonary arterial hypertension (PAH) is a progressive proliferative vasculopathy associated with mechanical and electrical changes, culminating in increased vascular resistance, right ventricular (RV) failure, and death. With a main focus on invasive tools, there has been an underutilization of echocardiography, electrocardiography, and biomarkers to non-invasively assess the changes in myocardial and pulmonary vascular structure and function during the course of PAH. Methods: A SU5416-hypoxia rat model was used for inducing PAH. Biventricular functions were measured using transthoracic two-dimensional (2D) echocardiography/Doppler (echo/Doppler) at disease onset (0 week), during progression (3 weeks), and establishment (5 weeks). Similarly, electrocardiography was performed at 0, 3, and 5 weeks. Invasive hemodynamic measurements and markers of cardiac injury in plasma were assessed at 0, 3, and 5 weeks. Results: Increased RV systolic pressure (RVSP) and rate of isovolumic pressure rise and decline were observed at 0, 3, and 5 weeks in PAH animals. EKG showed a steady increase in QT-interval with progression of PAH, whereas P-wave height and RS width were increased only during the initial stages of PAH progression. Echocardiographic markers of PAH progression and severity were also identified. Three echocardiographic patterns were observed: a steady pattern (0-5 weeks) in which echo parameter changed progressively with severity [inferior vena cava (IVC) expiratory diameter and pulmonary artery acceleration time (PAAT)], an early pattern (0-3 weeks) where there is an early change in parameters [RV fractional area change (RV-FAC), transmitral flow, left ventricle (LV) output, estimated mean PA pressure, RV performance index, and LV systolic eccentricity index], and a late pattern (3-5 weeks) in which there is only a late rise at advanced stages of PAH (LV diastolic eccentricity index). RVSP correlated with PAAT, PAAT/PA ejection times, IVC diameters, RV-FAC, tricuspid systolic excursion, LV systolic eccentricity and output, and transmitral flow. Plasma myosin light chain (Myl-3) and cardiac troponin I (cTnI) increased progressively across the three time points. Cardiac troponin T (cTnT) and fatty acid-binding protein-3 (FABP-3) were significantly elevated only at the 5-week time point. Conclusion: Distinct electrocardiographic and echocardiographic patterns along with plasma biomarkers were identified as useful non-invasive tools for monitoring PAH progression.
Collapse
Affiliation(s)
- Ahmed Zaky
- Department of Anesthesiology and Perioperative Medicine, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Iram Zafar
- Department of Anesthesiology and Perioperative Medicine, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Juan Xavier Masjoan-Juncos
- Department of Anesthesiology and Perioperative Medicine, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Maroof Husain
- Department of Anesthesiology and Perioperative Medicine, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Nithya Mariappan
- Department of Anesthesiology and Perioperative Medicine, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Charity J. Morgan
- Department of Biostatistics, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Tariq Hamid
- Division of Cardiovascular Disease, Department of Medicine, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Michael A. Frölich
- Department of Anesthesiology and Perioperative Medicine, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Shama Ahmad
- Department of Anesthesiology and Perioperative Medicine, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Aftab Ahmad
- Department of Anesthesiology and Perioperative Medicine, University of Alabama at Birmingham, Birmingham, AL, United States
| |
Collapse
|