Derivation and external validation of a deep learning model to predict changes in coronary plaque burden.
Authors
Affiliations (14)
Affiliations (14)
- Interventional Cardiology Department, MedStar Washington Hospital Center, Washington, D.C., USA.
- Instituto Pladema, Universidad Nacional del Centro de la Provincia de Buenos Aires (UNICEN), Tandil, Argentina.
- Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Tandil, Argentina.
- Department of Cardiology, Rigshospitalet, Copenhagen University Hospital, Copenhagen, Denmark.
- Hospital Israelita Albert Einstein, São Paulo, Brazil.
- Faculty of Health Sciences, Universidad Autónoma de Chile, Providencia, Chile.
- Device and Innovation Centre, William Harvey Research Institute, Queen Mary University London, London, United Kingdom.
- Department of Cardiology, Geneva University Hospitals, Geneva, Switzerland.
- Department of Cardiology, Radboud UMC, Nijmegen, the Netherlands.
- Department of Cardiology, Medical University of Vienna, Vienna, Austria.
- Department of Pharmacology, Bern University Hospital, Bern, Switzerland.
- Sanofi, Geneva, Switzerland.
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
- National Laboratory for Scientific Computing, LNCC/ MCTI, Petrópolis, RJ, Brazil.
Abstract
Predicting the progression/regression of coronary plaque burden is challenging. We aimed to develop a deep learning model to forecast changes in percent atheroma volume (ΔPAV) using intravascular ultrasound (IVUS). We analysed data from IBIS-4 and PACMAN-AMI. Core lab measurements of plaque burden were available from IVUS pullbacks. Each model consists of a bidirectional Long Short-Term Memory (biLSTM) layer followed by two fully connected layers with one neuron each, resulting in both a classification for input progression/regression and an estimation of the ΔPAV. For the derivation and validation, a total of 1,960 regions of interest (ROIs) from the IBIS-4 dataset were used. The mean±standard deviation of the model accuracy was 0.85±0.02, the Matthews correlation coefficient was 0.70±0.04, and the F1 score was 0.85±0.02 for both progression and regression classes. In the testing (external validation) process with the PACMAN-AMI dataset, 5,283 ROIs were utilised. The mean ΔPAV was -0.31±5.63, for which 2,665 featured regression with a mean ΔPAV of -4.57±3.73, and 2,618 presented progression with a mean ΔPAV of 4.02±3.55, representing 49.6% of plaque progression prevalence. The predictive performance across the 100 trained models in the testing dataset showed an accuracy of 0.84, a Matthews correlation coefficient of 0.68, and an F1 score for the progression and regression classes of 0.84. This is the first deep learning model capable of detecting changes in plaque progression by analysing the rate of plaque burden change between adjacent frames.