LinkedIn/ https://www.linkedin.com/in/soufiane-ajana/https://spark.u-bordeaux.fr/en/
This thesis was funded by the European Union Horizon 2020 Research and Innovation Programme (www.eyerisk.eu) :
Objectives :
– Comparison of machine learning (ML) approaches to predict the risk of progression to a blinding disease called Age-related Macular Degeneration (AMD)
– Integration of the developed prediction model to a digital platform (www.macutest.com)
Main tasks :
– Deep understanding of various ML models: penalized regression, ensemble methods, neural networks, supervised dimension reduction and multi-state models
– Application of these models to retinal images and Omics data (genomics and metabolomics) to reach personalized predictions of AMD risk
– Interpret and explain the behavior of the best predictive models to the end users (clinicians, biologists …) to ensure that they understand and trust the functionality of these models
The European FRAILOMIC consortium (http://www.frailomic.org):
Implementing interpretable statistical models to explain and better predict the risk of frailty among elderly people, using classical biological markers and markers identified by omics approaches:
Generalized Linear Mixed models and Multi-state models
– Ajana, S., et al. Benefits of dimension reduction in penalized regression methods for high dimensional grouped data: a case study in low sample size. Bioinformatics (2019)
Link: https://academic.oup.com/bioinformatics/article-abstract/35/19/3628/5372340?redirectedFrom=fulltext
– Ajana S, et al. Predicting progression to advanced age-related macular degeneration from clinical, genetic and lifestyle factors using machine learning. Ophthalmology (2020)
Link: https://www.aaojournal.org/article/S0161-6420(20)30849-6/fulltext
– Acar N., BMJ M., Ajana S., et al. Predicting the retinal content in omega-3 fatty acids for age-related macular-degeneration. Clin Transl Med (2021)
Link: https://onlinelibrary.wiley.com/doi/full/10.1002/ctm2.404
