Plant electrome corresponds to the emergent set of plant bioelectrical activity. The infection of plant tissues by different fungi alters this bioelectrical activity and can originate different electrical signatures, which can be used to identify the potential pathogenic agent. In this work, we evaluated the systemic variations of the electrome of barley triggered by the inoculation of Blumeria graminis and Bipolaris sorokiniana on the leaves. Therefore, approximately 50 days-old barley plants were placed within a Faraday cage under controlled conditions. A pair of needle electrodes was inserted in the culm for the recording of bioelectrical data. The plants were then inoculated with the pathogen in the last completely expanded leaf. Each pathogen was inoculated in different plants. Plants exposed to the same procedures as the inoculated ones, but without the fungi, served as controls. The electromes were recorded through 48 h, 24 h of which before the fungi inoculation or the control treatment. The bioelectrical data collected were analysed as time series through the following techniques: descriptive statistics, Bayesian change point (BCP) analysis, approximate entropy (ApEn), and autocorrelation. The results of these analyses were used as features, hence creating the dataset used in the machine learning (cluster analysis). The results indicate that the inoculation of pathogenic fungi culminated in a greater electrome variation (EV) when compared with the control (simulated inoculation). The pathogen inoculation generated peculiarities in the EV distribution for each pathogen. Therefore, the inoculation of B. graminis or B. sorokiniana created an electrical signature specific for each pathogen. This signature allows identifying the presence of pathogenic infection in the first minutes after contact with the host surface.