In the paper a technique for qualitative assessment of fatigue crack growth monitoring is presented, utilizing guided elastic waves generated by sparse PZT piezoelectric transducers network in the pitch catch configuration. The Damage Indices used for the inference carries marginal signal information content in order to decrease their sensitivity with respect to undesired non-controllable factors. The reason for that is to limit the false calls ratio which besides the damage detection capability of a system, plays a crucial role in applications. However even such simplified damage indices can be altered over a long term, leading to the misclassification problem. Considering single sensing path, it is very difficult to distinguish whether the resultant change of DIs is caused by a damage or due to such DIs decoherence. Therefore assessment approaches based on threshold levels fixed separately for DIs obtained on each of the sensing paths, would eventually lead to a false call. In order to decrease such misclassification risk a method to compensate the DIs drift is proposed utilizing the information from all of the network sensing paths. The proposed approach has been verified on a real structure during a Full Scale Fatigue Test (FSFT).