Mahdi Ebnali, Nima Ahmadi, Shiva Pourfalatoun, Abdullah Al-Taweel, Hamid Shokoohi
AI systems, particularly Large Language Models (LMMs), has the potential to improve telemedicine. However, there is a need for further investigation to understand the effectiveness of AI decision support and human-AI collaboration in this context. This study examines the impact of AI-only and clinician-AI support systems on trust, acceptance, usability, and cognitive load in telemedicine scenarios. Twenty non-medical participants were randomly assigned to receive instructions from an AI-only or clinician-AI decision support system during simulated cardiopulmonary resuscitation (CPR) scenarios. We used ChatGPT 3, a widely used LMM, as the AI system. Participants’ responses were measured using trust and acceptance questionnaires, as well as a wearable wristband to collect physiological data. The results show that the clinician-AI scenario was perceived as more useful compared to the ChatGPT-only scenario. The collaborative approach also led to higher heart rate variability (HRV) and lower LF/HF rating, indicating potentially lower mental effort compared to ChatGPT-only. No significant differences were found in System Usability Scale (SUS) and electrodermal activity (EDA) levels between the scenarios. These findings highlight the importance of involving clinicians in AI-supported telemedicine. Further research should explore real-world applications to validate the results.
Advanced AI, like ChatGPT 3, can improve telemedicine. We studied how AI helps decisions and teamwork with doctors. People tried AI-only and doctor-AI teamwork in emergencies. The results favored doctor-AI teamwork, showing better acceptance and less mental effort. This highlights the need for doctors in AI-supported telemedicine. More real-life research is needed to validate these findings.