VR-Based Neurophysiological Measurement Analysis and AI-Supported Design Integration in Biophilic Hospital Interiors: Neuroarchitectural Method Proposal

Abstract

Future healthcare structures will be intelligent spaces that adapt not only to aesthetic, technical, and functional aspects but also to measurable responses from the human brain and body, thereby contributing to recovery processes. The aim of this study is to establish a methodological basis for an evidence-based optimisation approach and design guide using artificial intelligence technology. This involves evaluating user responses through simultaneous neurophysiological measurements while experiencing the interior components of hospital rooms designed with biophilic parameters within a neuroarchitectural framework in a VR environment. To achieve this goal, inpatient rooms were scenario-based in a virtual environment with different biophilic elements, and the neurophysiological methods/techniques used during the user's VR experience were comparatively analysed within the framework of predefined accessibility, VR compatibility, data sensitivity, ethical compliance, and cost criteria. Subsequently, the framework for an artificial intelligence-based evaluation/recommendation approach was defined by considering the selected measurement set and biophilic design parameters together. The findings indicate that the most functional set of measurements in terms of applicability, portability, and data meaningfulness, capable of reliably capturing stress/mood/cognitive load indicators while working synchronously with VR, is Electroencephalography (EEG), Heart Rate Variability (HRV), and Galvanic Skin Response (GSR). These results demonstrate that biophilic design decisions can be optimised using artificial intelligence technology based on measurable neurophysiological responses. This study is unique in that it proposes a holistic approach to biofilic hospital rooms through VR-based neurophysiological data collection and AI-supported design optimisation, and provides a systematic framework that can transform this approach into an evidence-based design guide, thereby making significant contributions to both the literature and practice.