Skip to main content
Aurélien Vannieuwenhuyze

Applied AI Research Engineer · Explainable & Neuro-Symbolic AI · Healthcare & Industrial R&D

Model patient trajectories. Explain clinical predictions.

I design and evaluate artificial intelligence approaches to analyze changes in patient condition, anticipate clinical events, and produce results that healthcare professionals can understand and assess.

Based in Lille, France · Available for focused R&D assignments, scientific collaborations, and international opportunities compatible with completing my PhD.

Positioning

Expertise at the intersection of AI, time, and medicine

My work combines applied research, engineering, and an understanding of critical clinical environments. I focus on problems where temporal dynamics, explainability, and expert knowledge are essential.

Expertise and engagements

Turning complex clinical questions into structured R&D work

Scientific framing and applied R&D

Feasibility assessment, scientific and technical framing, data exploration, prototyping, and model evaluation for healthcare artificial intelligence projects.

Discuss a project →

Temporal clinical AI

Modeling medical time series, longitudinal events, and patient trajectories to identify dynamics, early signals, and clinically meaningful changes.

Explore the research →

Explainable and neuro-symbolic AI

Combining machine learning, knowledge graphs, temporal reasoning, and domain expertise to produce interpretable, explainable, and reviewable results.

Explore the approach →

Professional and scientific credentials

Experience

Nearly 20 years across technology, data, and digital transformation

Doctoral research

PhD candidate in artificial intelligence at CNAM, CEDRIC Laboratory — ISID team

Clinical knowledge

University Diploma in Critical Care, University of Lille — awarded in 2026

Publication

International Conference on Conceptual Modeling, ER 2025 — Springer

Research problems

Systems that are useful because they understand time and remain explainable

Clinical data is not simply a collection of measurements. It describes changes, interventions, disruptions, and uncertainties that a model must represent without losing their medical meaning.

  • Represent heterogeneous and irregularly sampled patient trajectories.
  • Identify early temporal signals in complex clinical data.
  • Integrate medical knowledge and expert constraints into learning systems.
  • Produce predictions that are understandable, challengeable, and useful for clinical decision-making.

Collaborate

Do you have a clinical challenge, data, or a healthcare AI project to structure?

I am open to applied research assignments, R&D project support, collaborations with medical or industry teams, and international opportunities in AI Research Engineering.