Imperial College London
Portrait Picture

DrChristopherRhodes

Faculty of Medicine, National Heart & Lung Institute

Reader in Pulmonary Vascular Disease
 
 
 
//

Contact

 

+44 (0)20 7594 7638c.rhodes07

 
 
//

Location

 

535ICTEM buildingHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Dawes:2017:10.1148/radiol.2016161315,
author = {Dawes, T and Simoes, monteiro de marvao A and Shi, W and Fletcher, T and Watson, G and Wharton, J and Rhodes, C and Howard, L and Gibbs, J and Rueckert, D and Cook, S and Wilkins, M and O'Regan, DP},
doi = {10.1148/radiol.2016161315},
journal = {Radiology},
pages = {381--390},
title = {Machine learning of three-dimensional right ventricular motion enables outcome prediction in pulmonary hypertension: a cardiac MR imaging study},
url = {http://dx.doi.org/10.1148/radiol.2016161315},
volume = {283},
year = {2017}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Purpose: To determine if patient survival and mechanisms of right ventricular (RV) failure in pulmonary hypertension (PH) could be predicted using supervised machine learning of three dimensional patterns of systolic cardiac motion. Materials and methods: The study was approved by a research ethics committee and participants gave written informed consent. 256 patients (143 females, mean age 63 ± 17) with newly diagnosed PH underwent cardiac MR imaging, right heart catheterization (RHC) and six minute walk testing (6MWT) with a median follow up of 4.0 years. Semi automated segmentation of short axis cine images was used to create a three dimensional model of right ventricular motion. Supervised principal components analysis identified patterns of systolic motion which were most strongly predictive of survival. Survival prediction was assessed by the difference in median survival time and the area under the curve (AUC) using time dependent receiver operator characteristic for one year survival. Results: At the end of follow up 33% (93/256) died and one underwent lung transplantation. Poor outcome was predicted by a loss of effective contraction in the septum and freewall coupled with reduced basal longitudinal motion. When added to conventional imaging, hemodynamic, functional and clinical markers, three dimensional cardiac motion improved survival prediction (area under the curve 0.73 vs 0.60, p<0.001) and provided greater differentiation by difference in median survival time between high  and low  risk groups (13.8 vs 10.7 years, p<0.001). Conclusion:Three dimensional motion modeling with machine learning approaches reveal the adaptations in function that occur early in right heart failure and independently predict outcomes in newly diagnosed PH patients.
AU  - Dawes,T
AU  - Simoes,monteiro de marvao A
AU  - Shi,W
AU  - Fletcher,T
AU  - Watson,G
AU  - Wharton,J
AU  - Rhodes,C
AU  - Howard,L
AU  - Gibbs,J
AU  - Rueckert,D
AU  - Cook,S
AU  - Wilkins,M
AU  - O'Regan,DP
DO  - 10.1148/radiol.2016161315
EP  - 390
PY  - 2017///
SN  - 1527-1315
SP  - 381
TI  - Machine learning of three-dimensional right ventricular motion enables outcome prediction in pulmonary hypertension: a cardiac MR imaging study
T2  - Radiology
UR  - http://dx.doi.org/10.1148/radiol.2016161315
UR  - http://hdl.handle.net/10044/1/42689
VL  - 283
ER  -
Download