LLM-supported self-diagnosis and self-treatment of familial Mediterranean fever: a case report.

Large language models (LLMs) are increasingly being used by patients to seek explanations for persistent or unexplained symptoms. However, their impact on real-world diagnostic pathways and patient behavior remains poorly understood. We report the case of a 34-year-old male of Egyptian origin with recurrent episodes of fever, severe migratory abdominal pain, arthralgia, myalgia, and intermittent erythematous skin lesions since early childhood. Despite almost 3 decades of extensive investigations, no unifying diagnosis had been established. During an iterative dialogue with the LLM DeepSeek in June 2025, the differential diagnosis was progressively refined toward familial Mediterranean fever (FMF). Although the model repeatedly recommended specialist assessment, it also provided specific information regarding genetic testing and colchicine treatment. The patient subsequently arranged genetic testing independently and obtained colchicine in Egypt, initiating treatment without prior specialist assessment at 0.5 mg twice daily. His inflammatory attacks ceased completely. However, liver enzymes increased, prompting temporary treatment discontinuation and dose reduction. FMF was thereafter confirmed by specialist assessment based on the characteristic clinical phenotype, family history, genotype, and response to colchicine. This case illustrates how patient-facing LLMs may facilitate recognition of rare autoinflammatory diseases. However, confident diagnostic language combined with actionable treatment advice may also encourage unsupervised testing and self-medication, underscoring the need for clear safety boundaries and specialist confirmation.