From neurotechnology to the classroom: the promise of brain-computer interfaces for training systems engineers

This perspective article explores the transformative potential of brain-Computer Interfaces (BCI) in undergraduate systems engineering programs, a domain characterized by high attrition and a widening gap between rapid technological innovation and slower pedagogical change. I argue that BCI, by enabling real-time detection of cognitive states such as mental workload, attention, and frustration, can evolve from laboratory tools to central pedagogical instruments for adaptive, student-centered education. I review the state-of-the-art methods, which demonstrate the technical feasibility of low-cost electroencephalography (EEG) devices and machine learning algorithms that classify cognitive states with high accuracy in controlled settings. Building on this evidence, I outline concrete applications in three dimensions: formative assessment, dynamic curricular adaptation, and cognitive inclusion, with a specific emphasis on preventing dropout in foundational courses such as algorithms. I also examine ethical, technical, and pedagogical challenges, and propose a scalable, ethically grounded pilot model tailored for universities, particularly in Latin America. This study reports no empirical results. It synthesizes the existing evidence and proposes a roadmap for research and educational action.