Brain-computer interfaces (BCIs) have revolutionized the way humans interact with machines, particularly for patients with severe motor impairments. EEG-based BCIs have limited functionality due to the restricted pool of stimuli that they can distinguish, while those elaborating event-related potentials up to now employ paradigms that require the patient’s perception of the eliciting stimulus. In this work, we propose MIRACLE: a novel BCI system that combines functional data analysis and machine-learning techniques to decode patients’ minds from the elicited potentials. MIRACLE relies on a hierarchical ensemble classifier recognizing 10 different semantic categories of imagined stimuli. We validated MIRACLE on an extensive dataset collected from 20 volunteers, with both imagined and perceived stimuli, to compare the system performance on the two. Furthermore, we quantify the importance of each EEG channel in the decision-making process of the classifier, which can help reduce the number of electrodes required for data acquisition, enhancing patients’ comfort.

Introduction: Vascular access devices (VADs), namely peripheral VADs (PVADs) and central venous VADs (CVADs), are crucial in both intensive care unit (ICU) and non-ICU settings. However, VAD placement carries risks, notably catheter-related bloodstream infections (CRBSIs). Candida spp. is a common pathogen in CRBSIs, yet its clinical and microbiological characteristics, especially in non-ICU settings, are underexplored. Methods: We conducted a monocentric, retrospective observational study at Luigi Sacco Hospital from 1 May 2021 to 1 September 2023. We reviewed medical records of non-ICU adult patients with CVADs and PVADs. Data on demographics, clinical and laboratory results, VAD placement, and CRBSI occurrences were collected. Statistical analysis compared Candida spp. CRBSI and bacterial CRBSI groups. Results: Out of 1802 VAD placements in 1518 patients, 54 cases of CRBSI were identified, and Candida spp. was isolated in 30.9% of episodes. The prevalence of CRBSI was 3.05%, with Candida spp. accounting for 0.94%. Incidence rates were 2.35 per 1000 catheter days for CRBSI, with Candida albicans and Candida non-albicans at 0.47 and 0.26 per 1000 catheter days, respectively—patients with Candida spp. CRBSI had more frequent SARS-CoV-2 infection, COVID-19 pneumonia, and hypoalbuminemia. Conclusions: During the COVID-19 pandemic, Candida spp. was a notable cause of CRBSIs in our center, underscoring the importance of considering Candida spp. in suspected CRBSI cases, including those in non-ICU settings and in those with PVADs.