Graph-guided Gaussian Process-based Diagnosis of CVD Severity with Uncertainty Measures.

The severity of coronary artery disease can be assessed invasively using the Fractional Flow Reserve (FFR) index which is a useful diagnostic tool for the clinicians to select the treatment approach. The present work capitalizes a Gaussian process (GP) framework over graphs for the prediction of FFR index using only non-invasive imaging and clinical features. More specifically, taking the per-node one-hop connectivity vector as input, we employed a regression-based task by applying an ensemble of graph-adapted Gaussian process experts, with a data-adaptive fashion via online training. The main novelty of the work lies in the fact that for the first time in a medical field the inference model considers only the similarity condition of the patients, instead of their features. Our results demonstrate the impressive merits of the proposed medical EGP (MedEGP) method, in comparison to the single GP, and Linear Regression (LR) models to predict the FFR index, with well-calibrated uncertainty.Clinical Relevance- This paper establishes an accurate non-invasive approach to predict the FFR for the diagnosis of coronary artery disease.

Predictive Models of Coronary Artery Disease Based on Computational Modeling: The SMARTool System.

SMARTool aims to the development of Decision Support Systems (DSS) for the risk stratification, diagnosis, prediction and treatment of coronary artery disease (CAD). In this work, we present the results of the prediction DSS, which utilizes clinical data, imaging morphological characteristics and computational modeling results. More specifically, 263 patients were recruited in the SMARTool clinical trial and 196 patients were selected for the DSS development. Traditional risk factors, blood examinations and computed coronary tomography angiography (CCTA) were performed at two different time points with an interscan period 6.22 ± 1.42 years. Computational modeling of blood flow and LDL transport was performed at the baseline. Predictive models are built for the prediction of CAD at the follow-up. The results show that CAD can be predicted with 83% accuracy, when low ESS, high accumulation of LDL and imaging data are included in the model.

A computational multi-level atherosclerotic plaque growth model for coronary arteries.

In this work, we present a novel computational approach for the prediction of atherosclerotic plaque growth. In particular, patient-specific coronary computed tomography angiography (CCTA) data were collected from 60 patients at two time points. Additionally, blood samples were collected for biochemical analysis. The CCTA data were used for 3D reconstruction of the coronary arteries, which were then used for computational modeling of plaque growth. The model of plaque growth is based on a multi-level approach: i) the blood flow is modeled in the lumen and the arterial wall, ii) the low and high density lipoprotein and monocytes transport is included, and iii) the major atherosclerotic processes are modeled including the foam cells formation, the proliferation of smooth muscle cells and the formation of atherosclerotic plaque. Validation of the model was performed using the follow-up CCTA. The results show a correlation of the simulated follow-up arterial wall area to be correlated with the corresponding realistic follow-up with r2=0.49, P<; 0.0001.

A Clinical Decision Support Platform for the Risk Stratification, Diagnosis, and Prediction of Coronary Artery Disease Evolution.

SMARTool aims to perform accurate risk stratification of coronary artery disease patients as well as to provide early diagnosis and prediction of disease progression. This is achieved by the acquisition of data from about 263 patients including computed tomography angiographic images, clinical, molecular, biohumoral, exposome, inflammatory and omics data. Data are collected in two time points with a followup period of approximately 5 years. In the first step, data mining techniques are implemented for the estimation of risk stratification. In the next step, patients, who are classified as medium to high risk are considered for coronary imaging and computational modelling of blood flow, plaque growth and stenosis severity assessment. Additionally, patients with increased stenosis are selected for stent deployment. All the above modules are integrated in a cloud-based platform for the clinical decision support (CDSS) of patients with coronary artery disease. The work presents preliminary results employing the SMARTool dataset as well as the concept and architecture of the under development platform.

SMARTool: A tool for clinical decision support for the management of patients with coronary artery disease based on modeling of atherosclerotic plaque process.

SMARTool aims to the development of a clinical decision support system (CDSS) for the management and stratification of patients with coronary artery disease (CAD). This will be achieved by performing computational modeling of the main processes of atherosclerotic plaque growth. More specifically, computed tomography coronary angiography (CTCA) is acquired and 3-dimensional (3D) reconstruction is performed for the arterial trees. Then, blood flow and plaque growth modeling is employed simulating the major processes of atherosclerosis, such as the estimation of endothelial shear stress (ESS), the lipids transportation, low density lipoprotein (LDL) oxidation, macrophages migration and plaque development. The plaque growth model integrates information from genetic and biological data of the patients. The SMARTool system enables also the calculation of the virtual functional assessment index (vFAI), an index equivalent to the invasively measured fractional flow reserve (FFR), to provide decision support for patients with stenosed arteries. Finally, it integrates modeling of stent deployment. In this work preliminary results are presented. More specifically, the reconstruction methodology has mean value of Dice Coefficient and Hausdorff Distance is 0.749 and 1.746, respectively, while low ESS and high LDL concentration can predict plaque progression.