AI vs. Doctors: Human Judgment Wins (for time being) in Complex Medical Contexts

Our host Iman Mossavat invites Dr. Artin Entezarjou, a board-certified specialist in general medicine, to debate the role AI in medicine. He discusses AI’s advancements in healthcare and its challenges in complex clinical scenarios. “Humans can outperform AI when questions aren’t multiple choice, especially when psychosocial factors are involved,” Dr. Entezarjou says. His research comparing GPT-4 with human doctors shows that AI struggles with the complexity and context of real-world medicine. “When we want to make decisions in clinical practice, we need to consider more than just symptoms. We need to understand the patient's preferences and context,” he adds. Dr. Entezarjou emphasizes the importance of human judgment in healthcare, stating, “We’re still the masters of knowing when we need more context. But this is rapidly changing.” He calls for AI systems that are robust, trustworthy, and intuitive, to support physicians rather than replace them. “AI can be superhuman in specific areas, but in general, we still need human judgment,” Dr. Entezarjou concludes. Dr. Entezarjou holds a Ph.D. from Lund University and is a postdoctoral researcher at the University of Gothenburg. He works at Tandem Health, a startup using large language models to automate administrative tasks for clinicians. Dr. Entezarjou has worked on eVisits in Swedish primary care, focusing on telemedicine, automated patient histories, and machine learning. Podcasts for Brainport featured by Radio 4 Brainport, 2025