PhD student in Diabetes Epidemiology and Health Data Science

Background

Cardiovascular disease (CVD) remains the leading cause of death worldwide and exerts a disproportionate burden on individuals living with type 1 diabetes (T1D). Despite advances in care, traditional risk prediction models like the Steno Type 1 Risk Engine fail to account for the immunological dysregulation inherent in T1D.

Project Objective

The PhD candidate will primarily focus on the clinical and epidemiological characterisation of cardiovascular risk among people living with T1D, using multimodal data in the large SFDT1 cohort study. This work will lay the groundwork for developing novel patient clusters and digital phenotypes, leveraging machine learning approaches to identify individuals at high CV risk based on clinical and biochemical markers, immune markers, digital health data (e.g., CGM metrics), and routine laboratory tests.

Key Responsibilities

• Conduct advanced clinical epidemiological analyses using large cohort data (SFDT1, but also REVADIAB, ANGIOSAFE2);
• Apply unsupervised machine learning techniques to derive clinically meaningful clusters based on CV risk factors and digital biomarkers;
• Identify phenotypic extremes to guide downstream immunological analyses;
• Collaborate closely with bioinformaticians, immunologists, and diabetologists to ensure integrated analysis and interpretation;
• Prepare scientific manuscripts for publication and present findings at national and international conferences;
• Participate in strategic planning and dissemination activities in coordination with other partners.

Key Skills, Experience and Qualifications

• MSc (or equivalent) in Data Science, Bioinformatics, Epidemiology, Biostatistics, Biomedical Sciences, or related disciplines;
• Strong background in statistical modeling, and/or machine learning (any experience in multimodal AI is an asset);
• Previous experience working with cohort data or electronic health records is an asset;
• Interest in digital health and diabetes research;
• Proficiency in R and/or Python;
• Excellent writing and communication skills in English. French is an asset.

Training & Environment

The selected candidate will be fully embedded in the Deep Digital Phenotyping Research Unit at the Department of Precision Health of the Luxembourg Institute of Health. This multidisciplinary environment provides a unique platform to acquire and deepen knowledge in diabetes epidemiology, digital biomarkers, and precision medicine. The candidate will benefit from internal training opportunities and collaborations across LIH, Inserm, AP-HP, and international academic partners. The PhD will be supervised by Dr Guy Fagherazzi, and co-supervised by Pr Jean-Pierre Riveline and Dr Fawaz Alzaid. 

Applications including a detailed CV, a motivation letter describing your research interests and alignment with the project goals and the contact details of 2 academic referees should be sent before 30 June 2025 via our website www.LIH.lu/jobs with the ref: MC/PhD525/GF/DDP

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 recruitment and promotion of female leaders and their career development.

In Short

• Contract type :  Fixed-term contract (CDD)
• Contract duration :  36 months
• Work hours :  40h/week
• Location :  rue Thomas Edison 1 A-B - 1445 LUXEMBOURG
• Start date :  ASAP

The Deep Digital Phenotyping Lab aims to leverage digital health technologies to identify digital biomarkers for enhanced disease monitoring.

https://www.lih.lu/en/research-scope/research-department/department-of-precision-health/deep-digital-phenotyping-research-unit/

• MSc (or equivalent) in Data Science, Bioinformatics, Epidemiology, Biostatistics, Biomedical Sciences, or related disciplines;
• Strong background in statistical modeling, and/or machine learning (any experience in multimodal AI is an asset);
• Previous experience working with cohort data or electronic health records is an asset;
• Interest in digital health and diabetes research;
• Proficiency in R and/or Python;
• Excellent writing and communication skills in English. French is an asset.