Engineer F - M Prodromal Trajectories Of Neurodegenerative Diseases Linking Ap-Hp Clinical Data Warehouse And National Health Data H/F - 75

A propos d'Inria

Inria est l'institut national de recherche dédié aux sciences et technologies du numérique. Il emploie 2600 personnes. Ses 215 équipes-projets agiles, en général communes avec des partenaires académiques, impliquent plus de 3900 scientifiques pour relever les défis du numérique, souvent à l'interface d'autres disciplines. L'institut fait appel à de nombreux talents dans plus d'une quarantaine de métiers différents. 900 personnels d'appui à la recherche et à l'innovation contribuent à faire émerger et grandir des projets scientifiques ou entrepreneuriaux qui impactent le monde. Inria travaille avec de nombreuses entreprises et a accompagné la création de plus de 200 start-up. L'institut s'eorce ainsi de répondre aux enjeux de la transformation numérique de la science, de la société et de l'économie.Engineer F/M Prodromal Trajectories of Neurodegenerative Diseases: Linking AP-HP Clinical Data Warehouse and National Health Data
Le descriptif de l'offre ci-dessous est en Anglais
Type de contrat : CDD

Contrat renouvelable : Oui

Niveau de diplôme exigé : Bac +5 ou équivalent

Fonction : Ingénieur scientifique contractuel

Niveau d'expérience souhaité : Jeune diplômé

Contexte et atouts du poste

The ARAMIS team (Algorithms, Models and Methods for Images and Signals in Medical Research) is an INRIA team based at the Paris Brain Institute that develops computational methods for studying neurodegenerative diseases.

Within the framework of the PRAIRIE-PSAI initiative, we are looking for aResearch Engineer to model longitudinal care trajectories and identify predictive patterns of neurodegenerative disease progression using large EHR/EMR data sets.

We have established a linkage between two major health data infrastructures:

- The AP-HP Clinical Data Warehouse (EDS-APHP): over 11 million patients, detailed clinical data (medical notes, laboratory results, imaging).
- The French National Health Data System (SNDS): 99% population coverage, longitudinal data on prescriptions, hospitalizations, and consultations since 2009.

This linkage encompasses over 150,000 patients with neurological diseases presenting motor symptoms: Parkinson's disease, multiple sclerosis, amyotrophic lateral sclerosis (ALS).

The central objective of this project is tocorrelate what happens before diagnosis (care trajectories, prescriptions, symptoms) with what happens after (evolution, prognosis) to understand:

- How long before diagnosis does the disease actually begin?
- What are the first detectable signals in health data?
- Which factors (medications, comorbidities, care) modify disease risk or progression?

Mission confiée

Theengineer will work on analyzing longitudinal care trajectories and identifying predictive patterns of neurodegenerative disease progression.

1. Extraction and Feature Engineering

- Build features from trajectories of prescriptions, hospitalizations, and medical procedures 5-10 years pre-diagnosis.
- Integrate heterogeneous data (ICD-10 codes, ATC codes, biological results, clinical notes via NLP).
- Handle temporal irregularity of observations (data collected during opportunistic consultations).

2. Statistical Modeling and Machine Learning

Method selection will be adapted to the intern's profile and interests. Several approaches are possible.

Classical methods:

- Survival models (Cox, Fine-Gray) to predict time to diagnosis or clinical events.
- Mixed-effects models to model longitudinal biomarker trajectories.
- Joint models combining longitudinal evolution and survival.

Exploratory methods (deep learning):

- DeepSurv: neural networks for survival analysis with non-linear relationships.
- Transformers / BERT: sequence models to capture complex temporal patterns in care trajectories.
- Trajectory embeddings: vector representations of care pathways for clustering or prediction.
- Recurrent Neural Networks (RNN / LSTM).

The project encourages methodological innovation while maintaining strong grounding in clinical questions. The goal is to do both: answer important clinical questions and explore new statistical/ML approaches.

Principales activités

Main activities:

- bibliographical work, literature review
- data management of large data sets of medical records
- design, implementation and conduct of complex analysis plans
- critical analysis results in light of the current literature
- present results at scientific conferences and in peer-reviewed scientific journals.

Compétences

Required:

- advanced statistics and/or machine learning (master level)
- scientific computing including data management in Python and/or R (master level)
- able to propose andimplement complex data analysis plans

Understanding the key challenges of real-world data analysis would be a plus.

Languages : fluent in scientific english (oral and written)

Relational skills : able to work in multidisciplinary teams at the interface between statistics, medicine and epidemiology.

Other valued appreciated : interest in neurodegenerative diseases

Avantages

- 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
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage