Probabilistic model definition for physiological state monitoring

Laure Amate (1) , Florence Forbes (2) , Julie Fontecave-Jallon (3) , Benoît Vettier (1) , Catherine Garbay (1)

1 AMA - Analyse de données, Modélisation et Apprentissage automatique [Grenoble]
2 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
3 TIMC-IMAG-PRETA - Physiologie cardio-Respiratoire Expérimentale Théorique et Appliquée

Assessing the global situation of a person from physiological data is a well-known difficult problem. In previous work, we propose a system that does not produce a diagnosis but instead follows a set of hypotheses and decides of an alarming situation with this information. In this paper we focus on data processing part of the system taking into account the complexity and the ambiguity of the data. We propose a statistical approach with a global model based on Hidden Markov Model and we present data models that rely on classical physiological parameters and expert's knowledge. We then learn a model that depends on the person and its environment, and we define and compute confidence values to assess the plausibility of hypotheses.

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]

Laure Amate, Florence Forbes, Julie Fontecave-Jallon, Benoît Vettier, Catherine Garbay. Probabilistic model definition for physiological state monitoring. SSP 2011 - Statistical Signal Processing Workshop, Jun 2011, Nice, France. pp.457-460, ⟨10.1109/SSP.2011.5967730⟩. ⟨hal-00742161⟩