Fuel cells, especially the proton exchange membrane fuel cell, are promising energy converters that can be used for various applications (transportation, mobile and stationary applications ). Although, they have a limited lifespan due to degradation mechanisms (chemical and mechanical stresses) that are not completely understood. Consequently, researches have been conducted to estimate the Remaining Useful Life of such devices, in order to take mitigation actions, extending the life of this electrochemical converter. The aim of the presented work is to propose an observer based method for prognostic of Proton Exchange Membrane Fuel Cell. An Extended Kalman Filter estimates the State of Health and its derivative using a single empirical degradation model, in any operating conditions. Those estimations are used to predict the future State of Health. Once the prediction equalizes a defined threshold, the fuel cell is considered out of use and the Remaining Useful Life is given. This method is validated by simulation and then used on a set of experimental data resulting from a long term test on a 5-cell stack operated under a constant current solicitation.