Research engineer Statistical analysis of longitudinal medical data

You will work in the context of the project REWIND (pRecision mEdecine WIth longitudinal Data), a multicentric project (Paris, Bordeaux, Lyon, Grenoble, Nice) granted via the “Investissement d’avenir” PEPR Santé Numérique. The project will focus on the development of new mathematical and statistical approaches for the analysis of multimodal multiscale longitudinal data. These models will be designed, implemented as prototypes and then transferred to an easy-used-well-documented platform where researchers from diverse communities, in particular physicians, will be able to analyze their own data set. The project will allow the development of a new generation of decision support systems, which will help clinicians at the bedside to make more informed decisions for the patient. They will contribute to the development of precision medicine in several key areas.

In this context, you will work in two Inria (the French National Institute for Research in Digital Science and Technology) teams: HeKA and ARAMIS lab (www.aramislab.fr). HeKA is located at the PariSanté Campus (https://parisantecampus.fr), while the ARAMIS lab is located at the Paris Brain Institute (https://institutducerveau-icm.org). While HeKA aims at developing methods, models, and tools to create, evaluate and validate learning health systems, ARAMIS lab is dedicated to the development of new computational approaches for the analysis of large neuroimaging and clinical datasets.

You will be strongly involved in scientific aspects of the work, such as discussion of methodological issues and interpretation of results. You will interact locally with the PhD students, postdoctoral fellows and engineers. You will take part in the communications and publications resulting from the use of the software.

The ARAMIS lab develops the open-source software Leaspy [1,2,3] (https://leaspy.readthedocs.io/en/stable/, https://gitlab.com/icm-institute/aramislab/leaspy), a Python library for the statistical analysis of longitudinal data, particularly medical data that comes in the form of repeated observations of patients at different time points. Leaspy allows users to easily fit various models to large-scale clinical studies consisting of clinical scores, cognitive assessments, physiological measurements, or imaging-derived data. Leaspy aims at recombining these series to reconstruct the long-term spatio-temporal trajectory of disease evolution. Each patient can then be positioned relative to the group-average timeline, in terms of both the temporal and spatial differences. Future observations as well as virtual patient trajectories can then be simulated. Leaspy is distributed freely to the scientific community and has users worldwide. It has been used to produce high impact medical publications that have advanced the understanding of neurodegenerative diseases such as Alzheimer’s disease, fronto-temporal dementia and amyotrophic lateral sclerosis [4,5,6,7].

• B. Schiratti, S. Allassonnière, O. Colliot, S. Durrleman: ‘A Bayesian mixed-effects model to learn trajectories of changes from repeated manifold-valued observations’, The Journal of Machine Learning Research, 18:1-33, 2017
• E. Poulet, S. Durrleman: ‘Multivariate disease progression modeling with longitudinal ordinal data’, Statistics in Medicine, 42(18), 3164-3183, 2023
• Fournier, S. Durrleman: ‘A Multimodal Disease Progression Model for Genetic Associations with Disease Progression Model for Genetic Associations with Disease Dynamics’, International Conference on Medical Image Computing and Computer-Assisted Intervention’, (pp. 601-610), Springer Nature Switzerland, 2023
• Maheux, I. Koval, J. Ortholand, C. Birkenbihl, D. Archetti, V. Bouteloup, …, S. Durrleman: ‘Forecasting individual progression trajectories in Alzheimer’s disease’, Nature Communications, 14(1), 761, 2023
• Ortholand, P.F. Pradat, S. Tezenas du Montcel, S. Durrleman : ‘Interaction of sex and onset site on the disease trajectory of amyotrophic lateral sclerosis’, Journal of Neurology, 270(12), 5903-5912, 2023
• Di Folco, R. Couronné, I. Arnulf, G. Mangone, S. Leu-Semenescu, P. Dodet, …, S. Durrleman : ‘Charting disease trajectories from isolated REM sleep behavior disorder to Parkinson’s disease’, Movement Disorders, 39(1), 64-75, 2024
• Moulaire, P.E. Poulet, E. Klockgether, …, S. Durrleman : ‘Temporal dynamics of the scale for the assessment and rating of ataxia in spinocerebellar ataxias’, Movement Disorders, 38(1), 35-44, 2023

You will be in charge of the:

• development of new features (implementation of new models, algorithms, metrics, visualizations),
• software maintenance,
• user support and animation of the community.

In addition, you will be presenting the software at international scientific conferences and other events (organized for instance by Inria, ICM, CNRS…). Finally, you will contribute to ambitious medical studies, by using Leaspy on large databases of patients, contributing to the interpretation of results and providing assistance to users (internal to the lab and external collaborators).

• PhD degree or master + experience in the field of statistical analysis
• Strong programming skills in Python
• Experience working with Git/GitHub on open-source projects would be a plus
• Excellent relational and communication skills to interact with users and lab members
• Good writing skills (documentation, website, scientific articles)

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking and flexible organization of working hours (after 12 months of employment)
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Social security coverage