Post-Doctoral Fellow in Digital Epidemiology and Data Science / AI

Background: Personalisation of care is expected to improve short and long term outcomes of people living with diabetes. Precision health strategies can be defined as the right intervention/ treatment/ care for the right person at the right time. One way to achieve this ambitious objective is to rely on deep digital phenotyping methods leading to the development of a digital twin of a person with diabetes. Deep digital phenotyping is the combination of deep phenotyping (defined as the “precise and comprehensive analysis of phenotypic abnormalities in which the individual components of the phenotype are observed and described”), with digital phenotyping (defined as the moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices). A digital twin is a relatively recent concept in health research. It originally comes from the industrial world, where a digital replica of a physical entity is virtually recreated, with similar elements and dynamics, to perform real-time optimization and testing. The use of digital twins can be extended to the medical field, the elements being features from deep digital phenotyping and the dynamics being the evolution of health outcomes over time. Thus, a digital twin would be a virtual representation of a patient with similar or close characteristics as a new patient seen during a clinical visit, and for whom the health status, risks of complications, and disease evolutions are known. 

Objectives: This position is part of the Dataspace4Health project in Luxembourg. Dataspace4Health is a groundbreaking open ecosystem designed to revolutionise secure and compliant health data exchange in the country and in Europe. The objective is to transform healthcare by leveraging the power of data while fully adhering to EU regulations and Gaia-X standards. This collaborative project is led by NTT DATA, Hôpitaux Robert Schuman (HRS), Luxembourg Institute of Health (LIH), the University of Luxembourg, Agence eSanté, Luxembourg National Data Service (LNDS) and is co-financed by the Ministry of Economy of Luxembourg as part of Luxembourg’s national Gaia-X strategy. One work package is dedicated to the development of a digital twin of a person living with diabetes using data from the HRS hospital. A close collaboration between the LIH and the Interdisciplinary Centre for Security, Reliability and Trust of University of Luxembourg (Dr Sylvain Kubler) will boost the methodological development.

Training and research environment: The successful candidate will be fully embedded in the Deep Digital Phenotyping Lab led by Dr Guy Fagherazzi, Director of the Department of Precision Health at LIH and will work with epidemiologists, medical doctors, clinical research experts and data scientists. The candidate will have the opportunity to be trained on various topics ranging from epidemiology, diabetology, digital biomarkers, vocal biomarkers, digital health, mixed methods and many other soft skills (productivity, time management, grant writing, public speaking…).

Key Accountabilities

• Review and benchmark the ongoing initiatives related to the development of digital twins using epidemiological data at the international level.
• Develop a state-of-the-art proof of concept of a digital twin of a person with diabetes using large existing cohort datasets (from the All of Us Research Program, USA and/or UK Biobank, UK).
• Conduct interviews with stakeholders (diabetologists, clinicians, people with diabetes…) to ensure the relevance of the developed solution.
• Externally validate and fine-tune, if needed, the developed digital twin model on a large dataset of people with diabetes from a Luxembourg hospital.
• Conduct data analyses, publish first- and co-authored manuscripts, present findings at international conferences, and prepare and submit applications to national and international funding agencies in order to establish research independence.
• Organize and lead meetings with project partners.

Key Skills, Experience and Qualifications

• PhD in Health Data Science, Bioinformatics, Epidemiology, Biostatistics or a related field. Candidates will have an advantage if they also have research experience in the field of diabetes or digital health.
• Strong analytical and writing skills are required as evidenced by publications in international peer-reviewed journals.
• Strong quantitative skills including data analysis and management.
• Ability to work independently and to take initiatives.
• Excellent time management skills and ability to prioritize tasks.
• The ideal candidate will have significant experience in the use of data analysis packages, preferably Python and R.
• Excellent English proficiency. French proficiency or willingness to learn French would be an asset.
• Ability to work in an interdisciplinary team.     

Gender Equality  

The LIH is an equal opportunities employer. We are fully committed to removing any discriminatory barrier related to gender, and not only, in recruitment and career progression of our staff. The LIH is attentive to gender representation among its leadership staff and aims to eliminate obstacles to the recruitment and promotion of female leaders and their career development.