Abstract
<jats:p>Medical competency is one of the key outcomes from learning in medical schools; however, it presents challenges to neurodivergent students in sensory demanding environments. High cognitive loads, multi-sensory stimuli, and strict procedural steps limit learners' capabilities, decrease their task accuracy, and exacerbate the cognitive load problem. Although the neurodiversity movement has grown considerably in recent years, existing medical training programs have not been adapted to eliminate those obstacles. Therefore, there is a pressing need for inclusive solutions to optimize and maximize performance in medical environments. In this case study, an engineering and technological methodology is employed to assess structural and systematic barriers faced in clinical learning processes. The creation of sensory-adjustable simulation environments has been performed, including customizable interface layout, haptic and visual feedback system, and controllable environment (lighting, sounds, task difficulty). Controlled simulation scenarios have been carried out under both traditional and adaptive settings, where reaction times, error percentages, task completion percentage, and measures of cognitive load are assessed. Further analysis is applied using regression and cluster methods to measure the contribution of engineering factors to clinical performance. Stratified analysis and performance variability indicated that individuals who initially possessed higher sensory sensitivities gained the most from adaptive solutions. Effect sizes were very high (d>0.8) and performance differences were all significant (p<0.01), indicating a clear improvement due to engineered environment. These results confirm the positive impact that engineering interventions have on minimizing structural challenges for neurodiverse people. With the application of adaptive principles, simulation of human systems and performance metrics, it is possible to create more accessible and efficient learning environments within medical training systems. This paper contributes to the existing knowledge base by providing a framework for the development of intelligent and sensory-responsive medical learning systems.</jats:p>