Skip to Main content Skip to Navigation
New interface

Heart & Brain. Linking cardiovascular pathologies and neurodegeneration with a combined biophysical and statistical methodology

Abstract : Clinical studies have identified several cardiovascular risk factors associated to dementia and cardiac pathologies, but their pathological interaction remains poorly understood. Classically, the investigation of the heart-brain relationship is mostly carried out through statistical analysis exploring the association between cardiac indicators and cognitive biomarkers. This kind of investigations are usually performed in large-scale epidemiological datasets, for which joint measurements of both brain and heart are available. For this reason, most of these analyses are performed on cohorts representing the general population. Therefore, the generalisation of these findings to dementia studies is generally difficult, since extensive assessments of cardiac and cardiovascular function in currently available dementia dataset is usually lacking. Another limiting factor of current studies is the limited interpretability of the complex pathophysiological relations between heart and brain allowed by standard correlation analyses. Improving our understanding of the implications of cardiovascular function in dementia ultimately requires the development of more refined mechanistic models of cardiac physiology, as well as the development of novel approaches allowing to integrate these models with image-based brain biomarkers. To address these challenges, in this thesis we developed new computational tools based on the integration of mechanistic models within a statistical learning framework. First, we studied the association between non-observable physiological indicators, such as cardiac contractility, and brain-derived imaging features. To this end, the parameter-space of a mechanistic model of the cardiac function was constrained during the personalisation stage based on the relationships between the parameters of the cardiac model and brain information. This allows to tackle the ill-posedness of the inverse problem associated to model personalisation, and obtain patient-specific solutions that are comparable population-wise.Second, we developed a probabilistic imputation model that allows to impute missing cardiac information in datasets with limited data. The imputation leverages on the cardiac-brain dynamics learned in a large-scale population analysis, and uses this knowledge to obtain plausible solutions in datasets with partial data. The generative nature of the approach allows to simulate the evolution of cardiac model parameters as brain features change. The framework is based on a conditional variational autoencoder (CVAE) combined with Gaussian process (GP) regression. Third, we analysed the potential role of cardiac model parameters as early biomarkers for dementia, which could help to identify individuals at risk. To this end, we imputed missing cardiac information in an Alzheimer's disease (AD) longitudinal cohort. Next, via disease progression modelling we estimated the disease stage for each individual based on the evolution of biomarkers. This allowed to obtain a model of the disease evolution, to analyse the role of cardiac function in AD, and to identify cardiac model parameters as potential early-stage biomarkers of dementia. These results demonstrate the importance of the developed tools by providing clinically plausible associations between cardiac model parameters and brain imaging features in an epidemiological dataset, as well as highlighting insights about the physiological relationship between cardiac function and dementia biomarkers. The obtained results open new research directions, such as the use of more complex mechanistic models that allow to better characterise the heart-brain relationship, or the use of biophysical cardiac models to derive in-silico biomarkers for identifying individuals at risk of dementia in clinical routine, and/or for their inclusion in neuroprotective trials.
Complete list of metadata
Contributor : Jaume Banus Connect in order to contact the contributor
Submitted on : Monday, May 31, 2021 - 11:50:30 AM
Last modification on : Saturday, June 25, 2022 - 11:50:48 PM


Version validated by the jury (STAR)


  • HAL Id : tel-03242796, version 2



Jaume Banus. Heart & Brain. Linking cardiovascular pathologies and neurodegeneration with a combined biophysical and statistical methodology. Modeling and Simulation. Université Côte d'Azur, 2021. English. ⟨NNT : 2021COAZ4030⟩. ⟨tel-03242796v2⟩



Record views


Files downloads