Prediction of incident cardiovascular events using machine learning and CMR radiomics
Prediction of incident cardiovascular events using machine learning and CMR radiomics
Objectives: evaluation of the feasibility of using cardiovascular magnetic resonance (CMR) radiomics in the prediction of incident atrial fibrillation (AF), heart failure (HF), myocardial infarction (MI), and stroke using machine learning techniques.
Methods: we identified participants from the UK Biobank who experienced incident AF, HF, MI, or stroke during the continuous longitudinal follow-up. The CMR indices and the vascular risk factors (VRFs) as well as the CMR images were obtained for each participant. Three-segmented regions of interest (ROIs) were computed: right ventricle cavity, left ventricle (LV) cavity, and LV myocardium in end-systole and end-diastole phases. Radiomics features were extracted from the 3D volumes of the ROIs. Seven integrative models were built for each incident cardiovascular disease (CVD) as an outcome. Each model was built with VRF, CMR indices, and radiomics features and a combination of them. Support vector machine was used for classification. To assess the model performance, the accuracy, sensitivity, specificity, and AUC were reported.
Results: AF prediction model using the VRF+CMR+Rad model (accuracy: 0.71, AUC 0.76) obtained the best result. However, the AUC was similar to the VRF+Rad model. HF showed the most significant improvement with the inclusion of CMR metrics (VRF+CMR+Rad: 0.79, AUC 0.84). Moreover, adding only the radiomics features to the VRF reached an almost similarly good performance (VRF+Rad: accuracy 0.77, AUC 0.83). Prediction models looking into incident MI and stroke reached slightly smaller improvement.
Conclusions: radiomics features may provide incremental predictive value over VRF and CMR indices in the prediction of incident CVDs.
Key points: • Prediction of incident atrial fibrillation, heart failure, stroke, and myocardial infarction using machine learning techniques. • CMR radiomics, vascular risk factors, and standard CMR indices will be considered in the machine learning models. • The experiments show that radiomics features can provide incremental predictive value over VRF and CMR indices in the prediction of incident cardiovascular diseases.
Atrial fibrillation, Heart failure, Machine learning, Preventive medicine, Radiomics
Pujadas, Esmeralda Ruiz
e716562c-2efd-4392-881a-e79fedb85724
Raisi-Estabragh, Zahra
43c85c5e-4574-476b-80d6-8fb1cdb3df0a
Szabo, Liliana
a5da4e9d-450f-43e5-b2de-1b1cabde6a6c
McCracken, Celeste
5d772e9e-3aaa-41da-a5ef-3943b1631fd9
Morcillo, Cristian Izquierdo
86bf8888-9722-49fc-afff-9df2de43a13f
Campello, Víctor M.
5ae7579f-cbea-4aa9-94fe-6c309603d889
Martín-Isla, Carlos
c383e3b5-6a84-460d-b31e-1c01c023c359
Atehortua, Angelica M
8ce54e99-c4b9-480a-ab2f-f145f0682d56
Vago, Hajnalka
00802f4a-87e9-45b0-9fd1-7703390370f6
Merkely, Bela
e00fa145-1c09-496d-b62b-c1fe1ba5b037
Maurovich-Horvat, Pal
b6df9ecf-1a85-498d-85a8-31a9240f83bc
Harvey, Nicholas C.
ce487fb4-d360-4aac-9d17-9466d6cba145
Neubauer, Stefan
c8a34156-a4ed-4dfe-97cb-4f47627d927d
Petersen, Steffen E.
04f2ce88-790d-48dc-baac-cbe0946dd928
Lekadir, Karim
b8de558a-869c-4574-b0d3-005dc52c3106
Pujadas, Esmeralda Ruiz
e716562c-2efd-4392-881a-e79fedb85724
Raisi-Estabragh, Zahra
43c85c5e-4574-476b-80d6-8fb1cdb3df0a
Szabo, Liliana
a5da4e9d-450f-43e5-b2de-1b1cabde6a6c
McCracken, Celeste
5d772e9e-3aaa-41da-a5ef-3943b1631fd9
Morcillo, Cristian Izquierdo
86bf8888-9722-49fc-afff-9df2de43a13f
Campello, Víctor M.
5ae7579f-cbea-4aa9-94fe-6c309603d889
Martín-Isla, Carlos
c383e3b5-6a84-460d-b31e-1c01c023c359
Atehortua, Angelica M
8ce54e99-c4b9-480a-ab2f-f145f0682d56
Vago, Hajnalka
00802f4a-87e9-45b0-9fd1-7703390370f6
Merkely, Bela
e00fa145-1c09-496d-b62b-c1fe1ba5b037
Maurovich-Horvat, Pal
b6df9ecf-1a85-498d-85a8-31a9240f83bc
Harvey, Nicholas C.
ce487fb4-d360-4aac-9d17-9466d6cba145
Neubauer, Stefan
c8a34156-a4ed-4dfe-97cb-4f47627d927d
Petersen, Steffen E.
04f2ce88-790d-48dc-baac-cbe0946dd928
Lekadir, Karim
b8de558a-869c-4574-b0d3-005dc52c3106
Pujadas, Esmeralda Ruiz, Raisi-Estabragh, Zahra, Szabo, Liliana, McCracken, Celeste, Morcillo, Cristian Izquierdo, Campello, Víctor M., Martín-Isla, Carlos, Atehortua, Angelica M, Vago, Hajnalka, Merkely, Bela, Maurovich-Horvat, Pal, Harvey, Nicholas C., Neubauer, Stefan, Petersen, Steffen E. and Lekadir, Karim
(2022)
Prediction of incident cardiovascular events using machine learning and CMR radiomics.
European radiology.
(doi:10.1007/s00330-022-09323-z).
Abstract
Objectives: evaluation of the feasibility of using cardiovascular magnetic resonance (CMR) radiomics in the prediction of incident atrial fibrillation (AF), heart failure (HF), myocardial infarction (MI), and stroke using machine learning techniques.
Methods: we identified participants from the UK Biobank who experienced incident AF, HF, MI, or stroke during the continuous longitudinal follow-up. The CMR indices and the vascular risk factors (VRFs) as well as the CMR images were obtained for each participant. Three-segmented regions of interest (ROIs) were computed: right ventricle cavity, left ventricle (LV) cavity, and LV myocardium in end-systole and end-diastole phases. Radiomics features were extracted from the 3D volumes of the ROIs. Seven integrative models were built for each incident cardiovascular disease (CVD) as an outcome. Each model was built with VRF, CMR indices, and radiomics features and a combination of them. Support vector machine was used for classification. To assess the model performance, the accuracy, sensitivity, specificity, and AUC were reported.
Results: AF prediction model using the VRF+CMR+Rad model (accuracy: 0.71, AUC 0.76) obtained the best result. However, the AUC was similar to the VRF+Rad model. HF showed the most significant improvement with the inclusion of CMR metrics (VRF+CMR+Rad: 0.79, AUC 0.84). Moreover, adding only the radiomics features to the VRF reached an almost similarly good performance (VRF+Rad: accuracy 0.77, AUC 0.83). Prediction models looking into incident MI and stroke reached slightly smaller improvement.
Conclusions: radiomics features may provide incremental predictive value over VRF and CMR indices in the prediction of incident CVDs.
Key points: • Prediction of incident atrial fibrillation, heart failure, stroke, and myocardial infarction using machine learning techniques. • CMR radiomics, vascular risk factors, and standard CMR indices will be considered in the machine learning models. • The experiments show that radiomics features can provide incremental predictive value over VRF and CMR indices in the prediction of incident cardiovascular diseases.
Text
s00330-022-09323-z
- Version of Record
More information
Accepted/In Press date: 28 November 2022
e-pub ahead of print date: 13 December 2022
Additional Information:
Funding Information:
Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work was partly funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement no. 825903 (euCanSHare project) and grant agreement no. 965345 (HealthyCloud project). ZR-E recognises the National Institute for Health Research (NIHR) Integrated Academic Training programme which supports her Academic Clinical Lectureship post and was also supported by British Heart Foundation Clinical Research Training Fellowship No. FS/17/81/33318. LS received funding from the European Association of Cardiovascular Imaging (EACVI Research Grant App000076437). CM was supported by the Oxford NIHR Biomedical Research Centre. SEP acknowledges support from the “SmartHeart” EPSRC programme grant (www. nihr.ac.uk; EP/P001009/1) and also from the CAP-AI programme, London’s first AI-enabling programme focused on stimulating growth in the capital’s AI sector. CAP-AI is led by Capital Enterprise in partnership with Barts Health NHS Trust and Digital Catapult and is funded by the European Regional Development Fund and Barts Charity. HV and BM received funding from the Ministry of Innovation and Technology NRDI Office within the framework of the Artificial Intelligence National Laboratory Program. SEP has also received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement no. 825903 (euCanSHare project). SEP acknowledges the British Heart Foundation for funding the manual analysis to create a cardiovascular magnetic resonance imaging reference standard for the UK Biobank imaging-resource in 5000 CMR scans ( www.bhf.org.uk ; PG/14/89/31194). This project was enabled through access to the MRC eMedLab Medical Bioinformatics infrastructure, supported by the Medical Research Council ( www.mrc.ac.uk ; MR/L016311/1). The funders provided support in the form of salaries for authors as detailed above but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Publisher Copyright:
© 2022, The Author(s).
Keywords:
Atrial fibrillation, Heart failure, Machine learning, Preventive medicine, Radiomics
Identifiers
Local EPrints ID: 473669
URI: http://eprints.soton.ac.uk/id/eprint/473669
ISSN: 0938-7994
PURE UUID: 9e1260fe-5ce0-4ef6-af23-23f9282ba728
Catalogue record
Date deposited: 27 Jan 2023 17:34
Last modified: 17 Mar 2024 02:59
Export record
Altmetrics
Contributors
Author:
Esmeralda Ruiz Pujadas
Author:
Zahra Raisi-Estabragh
Author:
Liliana Szabo
Author:
Celeste McCracken
Author:
Cristian Izquierdo Morcillo
Author:
Víctor M. Campello
Author:
Carlos Martín-Isla
Author:
Angelica M Atehortua
Author:
Hajnalka Vago
Author:
Bela Merkely
Author:
Pal Maurovich-Horvat
Author:
Stefan Neubauer
Author:
Steffen E. Petersen
Author:
Karim Lekadir
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
