Liane S. Canas

Self-reported symptoms during the SARS-CoV-2 pandemic have shown to be effective in training artificial intelligence (AI) models to identify possible foci of infections. Such models can be further used to early identify SARS-CoV-2 infected individuals, helping to contain the spread of the pandemic and efficiently allocate medical resources. These studies rapidly increased our understanding of SARS-CoV-2 during the pandemic and enabled the monitoring of long-term effects of COVID-19 outside the hospital setting. 

In this talk, I present our Hierarchical Gaussian Process model designed for the specific task of early detection of COVID-19, which outperforms the symptoms-based criteria considered in clinical practice for test referencing. 

Secondly, I focused on the description and phenotyping of post-COVID symptom profiles, which we have achieved using unsupervised machine-learning techniques.

Anticipating the progression of TBM and predicting patients’ outcomes can help to understand their prognosis and response to treatment. Also, the prediction of severe neurological events, which might lead to high morbidity and mortality, can improve the clinical outcome and the timely treatment. We developed a longitudinal model aiming at (1) predicting the changes in clinical scores, precursors of health decline and severe neurological events, and (2) identifying the patients’ clinical and demographic features that can explain the development of such events. Our model relies on imaging data, MRI, and clinical assessments of OUCRU trial patients. To our knowledge, this is the first attempt to combine multi-modal data using AI tools, aiming at the TBM prognosis. 

Prion diseases are a group of progressive neurodegenerative conditions which cause cognitive impairment and neurological deficits. To date, there is no accurate measure that can be used to diagnose this illness, or to quantify the evolution of symptoms over time. Prion disease, due to its rarity, is in fact commonly mistaken for other types of dementia. A robust tool to diagnose and quantify the progression of the disease is key as it would lead to more appropriately timed clinical trials, and thereby improve patients’ quality of life. The approaches used to study other types of neurodegenerative diseases are not satisfactory to capture the progression of human form of Prion disease. This is due to the large heterogeneity of phenotypes of Prion disease and to the lack of consistent geometrical pattern of disease progression. In this paper, we aim to identify and select imaging biomarkers that are relevant for the diagnostic on Prion disease. We extract features from magnetic resonance imaging data and use genetic and demographic information from a cohort affected by genetic forms of the disease. The proposed framework consists of a multi-modal subjectspecific feature extraction step, followed by a Gaussian Process classifier used to calculate the probability of a subject to be diagnosed with Prion disease. We show that the proposed method improves the characterisation of Prion disease. 

Gaussian Processes (GP) are a powerful tool to capture the complex time-variations of a dataset. In the context of medical imaging analysis, they allow robust modelling even in case of highly uncertain or incomplete datasets. Predictions from GP are dependent of the covariance kernel function selected to explain the data variance. To overcome this limitation, we propose a framework to identify the optimal covariance kernel function to model the data.The optimal kernel is defined as a composition of base kernel functions used to identify correlation patterns between data points. Our approach includes a modified version of the Compositional Kernel Learning (CKL) algorithm, in which we score the kernel families using a new energy function that depends on both the Bayesian Information Criterion (BIC) and the explained variance score. We applied the proposed framework to model the progression of neurodegenerative diseases over time, in particular the progression of autosomal dominantly-inherited Alzheimer's disease, and use it to predict the time to clinical onset of subjects carrying the genetic mutation.