A Fully Funded PhD in machine learning and data science

Contexte

The Lausanne University Hospital (CHUV) is one of five Swiss university hospitals. Through its collaboration with the Faculty of Biology and Medicine of the University of Lausanne and the EPFL, CHUV plays a leading role in the areas of medical care, medical research and training.

Dre Nazanin Sédille and Professor Oliver Y. Chén's teams develop new machine-learning and statistical methods and study large-scale data in health and disease. Our data are from diverse sources from the Service of Clinical Chemistry (Mission

The PhD student will primarily work on three interlinked projects in collaboration between CHUV and UNIL on data related to proteomic and metabolomic profilings in immunological and haematological diseases.

1. Automated biomarker discovery and disease prediction. We design machine learning methods to identify biomarkers associated with and predictive of disease outcomes (disease status, disease severity / clinical score, and longitudinal disease progression / fluctuation) in an automated way.

2. Discovering latent biomarkers to improve disease prediction and biological explanation. We design machine learning frameworks to identify, from multivariate, multimodal, and potentially high-dimensional data for latent, potentially nonlinear biomarkers that could better explain and predict the disease. We have data from metabolic diseases but the methods can be generalised to other diseases.

3. Longitudinal, personalised disease prediction. In addition to discovering population-level biomarkers (that are shared across subjects), we design methodological frameworks that incorporate, yet, distinguish, population-level and subject-specific information to capture not only the idiosyncratic information but also inform personalised assessment of individual longitudinal disease profiles. This may also potentially advance personalised medicine. We have data from immunological and haematological diseases; we also have data from wearable devices (digital health). The methods can be generalised to other disease territories.

Profil

• A master’s degree and an undergraduate degree in disciplines relevant to (applied) mathematics, computer science, engineering, machine learning, or statistics
• An interest in developing new methods and applications and employing them to address real-world healthcare-related problems
• An interest in data visualisation
• A team player
• The working language of the group is English. A good command of the french langage is mandatory
• Strong programming skills related to machine learning and longitudinal methods
• Experience in machine learning, statistical modelling, and version control.

Nous offrons