The objective of the research discussed in this paper is to create damage detection methods based on universal parameters that are applicable to a large number and large variety of structures. Such methods, if successful, streamline the data analysis across large bridge networks and provide a basis for bridge managers to reach efficient, effective, yet safe and sustainable maintenance decisions. The first step towards this goal is to identify an appropriate parameter and validate that it can be used to detect damage in real-life settings. The centroid of stiffness is a universal parameter and its position in a cross-section can be evaluated for any load-carrying beam structure as the position of the neutral axis under conveniently chosen loads. Thus, a change in the position of the neutral axis within a cross-section can indicate change in the position of the centroid of stiffness, i.e., unusual structural behaviors. This research focuses on the neutral axis because of its universal applicability to beam-like structures and its direct correlation with unusual structural behaviors (e.g., damage). In this paper two examples of successful damage detection in real-life settings using the neutral axis are presented. In both cases the neutral axis is evaluated with long-gauge fiber-optic strain sensors installed on the structure in a parallel topology. The results show that the neutral axis is sensitive to damage and can be used to detect cracking and delamination in real-life settings, even years after the damage occurred.