Health, Signal and ML
joint work with S. Allassonnière, R. Besson, F. Logé-Munerel, C. Marini, M. Brigham, P. Clavier, F. Gaudfernau, A. Pierangelo, I. Kamal, J. Stirnemann and I. Ben M’Barek
With S. Allassonnière, R. Besson and Necker obstetrician, we have worked on an optimization of a decision tree to accelerate foetal abnomalies detection. This tools combines an expert model with data assimilation and a reinforcement learning procedure on trees. It is now used by Sonio.
With F. Logé-Munerel and Air Liquide, we have used a similar idea to optimize health questionnaire and applied reinforcement learning to control insulin pumps.
With C. Marini and M. Brigham, we have worked working on the use of a blockchain within a machine learning framework in a sleep study context. We have also developped some sleep representation learning tools.
With S. Allassonnière and P. Clavier, we are working on robust versions of reinforcement learning and their application to patient trajectories.
With S. Allassonnière and F. Gaudfernau, we are working on image registration and atlas construction in medical imaging.
With A. Pierangelo and I. Kamal, we are developping ML tools to study the images produced by a new imaging device base on Mueller polarimetry.
With J. Stirnemann and I. Ben M’Barek, we are analysing cardiotocometric signals to help live diagnosis during labour.