The electrochemical impedance spectrometry (EIS) measurement coupled with equivalentcircuit (EC) model is widely used to monitor the health status of proton exchange membrane fuel cell (PEMFC). However, limited studies are available to investigate the impact of measurement uncertainty on the evaluation of EC parameters. To fill this gap, this study aims at establishing a machine learning-based method to improve identification of EC parameters based on EIS measurement for PEMFC health monitoring. This computational method was employed to estimate the uncertainty of EC parameters with regard to oxygenstoichiometry that could be quantified by means of charge transfer resistance and limited current density. Gaussian process classification and combined sampling methods together with theoretical calculation were adopted to generate the synthetic data with an R2 of 0.991 to determine the measurement uncertainty of EC parameters. The effectiveness of this computational approach was validated against high-level noisy experimental data. The result shows that this approach can effectively reduce the variances of EC parameters from over 400% to less than 30% and satisfactorily quantify the measurement uncertainty within 35 s. The introduction of synthetic data allows Gaussian process regression to predict the most reliable EIS spectra in the absence of measured oxygen stoichiometry with the computational time optimized. This study expands our capacity in improving the PEMFC health management via machine learning-based computational methods