Phobia Pulse: A Virtual Reality and Machine Learning Framework for Objective Phobia Assessment in Adventure Sports Medical Clearance

Accurate psychological evaluation for adventure sports participation is an increasingly critical requirement within modern occupational and sports medicine. Conventional assessment methodologies, predominantly reliant on self-reported questionnaires and structured clinical interviews, are inherently susceptible to subjective bias, social desirability effects, and an inability to capture real-time physiological reactions under authentic fear-inducing conditions. This paper presents the Neuro-Adaptive Phobia Diagnostic System (NPDS), a comprehensive and integrated framework that synergistically combines immersive Virtual Reality (VR) simulation, continuous physiological signal acquisition, and unsupervised machine learning for objective and reproducible phobia detection. The proposed system immerses candidates in photorealistic, scenario-specific VR environments engineered to evoke common phobic responses—including acrophobia (heights), claustrophobia (confined spaces), aquaphobia (deep water), nyctophobia (darkness), and hylophobia (dense forests). Concurrently, cardiac activity, specifically heart rate, is monitored via wearable biosensors and transmitted in real time through the Lab Streaming Layer (LSL) protocol. Anomaly detection is performed using the Isolation Forest algorithm, which constructs a personalized physiological baseline during an initial calibration phase, thereby enabling precise differentiation between transient stress elevations and genuine phobic autonomic responses. To bridge the translational gap between raw anomaly scores and actionable clinical intelligence, NPDS incorporates a Retrieval-Augmented Generation (RAG) module that retrieves contextually relevant medical literature from a curated vector database and synthesises structured, human-readable diagnostic reports. A dual-interface web platform—built on Next.js and FastAPI—facilitates real-time monitoring for clinicians and accessible summary reports for patients. Experimental evaluation conducted across multiple simulated phobia scenarios demonstrates that NPDS achieves reliable anomaly detection, seamless VR-physiological synchronization, and clinically interpretable outputs. The system represents a significant step toward objective, scalable, and bias-free phobia screening in adventure sports medical clearance contexts.