Machine learning cardiac-MRI features predict mortality in newly diagnosed pulmonary arterial hypertension

Samer Alabed; Johanna Uthoff; Shuo Zhou; Pankaj Garg; Krit Dwivedi; Faisal Alandejani; Rebecca Gosling; Lawrence Schobs; Martin Brook; Yousef Shahin; Dave Capener; Christopher S Johns; Jim M Wild; Alexander M K Rothman; Rob J van der Geest; Robin Condliffe; David G Kiely; Haiping Lu; Andrew J Swift

doi:10.1093/ehjdh/ztac022

Machine learning cardiac-MRI features predict mortality in newly diagnosed pulmonary arterial hypertension

Eur Heart J Digit Health. 2022 May 2;3(2):265-275. doi: 10.1093/ehjdh/ztac022. eCollection 2022 Jun.

Authors

Samer Alabed^{1

2

3}, Johanna Uthoff⁴, Shuo Zhou⁴, Pankaj Garg¹, Krit Dwivedi^{1

2}, Faisal Alandejani¹, Rebecca Gosling¹, Lawrence Schobs⁴, Martin Brook¹, Yousef Shahin¹, Dave Capener¹, Christopher S Johns^{1

2}, Jim M Wild^{1

3}, Alexander M K Rothman¹, Rob J van der Geest⁵, Robin Condliffe^{1

6}, David G Kiely^{1

3

6}, Haiping Lu^{3

4}, Andrew J Swift^{1

2

3}

Affiliations

¹ Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK.
² Department of Clinical Radiology, Sheffield Teaching Hospitals, Sheffield, UK.
³ INSIGNEO, Institute for in silico medicine, University of Sheffield, UK.
⁴ Department of Computer Science, University of Sheffield, Sheffield, UK.
⁵ Leiden University Medical Center, Leiden, The Netherlands.
⁶ Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield, UK.

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.

Keywords: Artificial Intelligence; Cardiac MRI; Machine learning; Mortality; Prognosis; Pulmonary hypertension.

Abstract

Grants and funding