While generative AI is revolutionary, experts have acknowledged that deep learning alone can’t achieve true human-like intelligence. Issues like hallucinations (fabricated results) make it difficult to adopt standard LLMs for areas like medicine, where reasoning can be a matter of life and death. So a team of AI scientists and clinical experts decided to rethink the playbook, combining deep learning with symbolic AI — a set of techniques that treats clinical thinking like a type of algebra. The results? Actual, measurable clinician-like reasoning that understands patient data like a physician.