Un outil prédictif basé sur l’intelligence artificielle pour le dépistage précoce de l’amylose [...]

Organisation/Company ICube, Univ. de Strasbourg, CNRS Research Field Engineering Researcher Profile Recognised Researcher (R2) Leading Researcher (R4) First Stage Researcher (R1) Established Researcher (R3) Application Deadline 19 Apr 2026 - 22:00 (UTC) Country France Type of Contract Temporary Job Status Full-time Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Transthyretin amyloidosis (ATTR) is a progressive systemic disease caused by extracellular deposition of misfolded transthyretin protein fibrils. Once considered rare, it is now recognized as largely underdiagnosed, particularly in its wild-type form (ATTRwt), which mainly affects older individuals. Cardiac involvement is the most severe complication and is often diagnosed at an advanced stage, when irreversible damage has already occurred.

Clinical studies have shown that carpal tunnel syndrome (CTS) may precede cardiac involvement by 5 to 10 years, representing an early warning sign. However, routine screening for amyloidosis in patients undergoing CTS surgery is not currently performed due to cost, low diagnostic yield in unselected populations, and the absence of reliable risk stratification tools.

This project aims to develop an artificial intelligence–based predictive tool to identify, among patients with CTS, those at high risk of underlying amyloidosis. The approach will rely on building a multimodal database integrating clinical variables (age, sex, bilateral CTS), surgical findings, biological markers, electrophysiological data, and potentially histological results.

Machine learning models will be trained to detect complex patterns and combinations of risk factors that are difficult to identify using conventional statistical methods. Particular attention will be given to explainable artificial intelligence (XAI) to ensure transparency and clinical acceptability of predictions.

The ultimate goal is to provide a clinical decision-support system that guides hand surgeons toward targeted screening (synovial biopsy, cardiac scintigraphy, biomarkers) only in high-risk patients. By leveraging the early time window offered by CTS manifestations, this project seeks to transform a routine surgical procedure into an opportunity for early diagnosis of a severe systemic disease, with direct impact on patient survival and quality of life.

Formation requise

We are seeking a highly motivated candidate with a strong interest in interdisciplinary research at the interface of medicine and artificial intelligence.

Required background

• Master’s degree (MSc or equivalent) obtained or currently in preparation in Data Science, Artificial Intelligence, Computer Science, Applied Mathematics, or a related field.
• Solid knowledge of machine learning methods (supervised learning, model evaluation, cross-validation).
• Proficiency in Python (Scikit-learn, TensorFlow, PyTorch) and data engineering.
• Good understanding of statistics and data analysis.
• Knowledge of database management and structuring.