Context

Real-world evidence on the pathophysiological mechanisms and natural history of diseases can be effectively generated by applying diverse data science methods to real-world data (RWD). Specifically, these methods include advanced algorithms capable of estimating treatment effects, predicting time-to-event, and identifying patient subgroups or prognostic factors.

Such algorithms can be leveraged to develop ‘disease and care models’, which can in turn be used to generate synthetic patient cohorts.

Such cohorts can then be used to simulate in silico efficacy and safety of drugs, making them invaluable for answering research questions in the pharmaceutical industry, particularly in the design and development of clinical trials.

In this context, our aim is to develop innovative and cutting-edge methods to create valuable ‘disease and care models’ and synthetic patient simulators. At the crossroads of various scientific areas (e.g., causal inference, predictive modeling, Bayesian modeling, machine/deep learning, generative AI), our research topics may encompass e.g. individualized treatment effect estimation (1) , synthetic data generation (2), (3), sequence analysis and modeling (4), (longitudinal) predictive modeling (5), federated learning (6).

Objectives

You will be expected to:

1. Conduct a comprehensive methodological literature review on a specific topic (such as the ones cited above).

2. Identify methods of interest, the hypotheses on which they rely on, and their pros and cons.

3. Implement these methods via a simulation study or on RWD (EHRs, patient registries…) to compare them under several scenarios and give recommendations on which method to use in which scenario.

• You’re coming from a master’s degree (engineering school in Data Science or equivalent) and you are currently looking for either an end-of-study internship or a gap year internship

• You’ve demonstrated a strong knowledge of mathematics/ machine learning/ data science (Engineering school, Master program in such specialties)

• You’ve an excellent working knowledge in statistical programming (Python and/or R)

• You’re interested in medical research

• You’re fluent both in written and oral scientific English

1. One meeting with Camille, our HR Manager

2. Technical use case with one of our Senior Data Scientist

3. Meeting with Antoine and Mathilde, our managers in Quinten Health