This study discusses the integration of artificial intelligence (AI) and machine learning (ML) in medical reasoning and decision-making, with a focus on the challenges and opportunities associated with the massive consumption of data required for training AI systems, and contrasts this with the limited data typically available to medical practitioners. We advocate for a balanced approach that includes small data and emphasize the importance of maintaining the art of clinical reasoning amid technological advancements. Finally, we highlight the potential of multidisciplinary research in addressing the complexities of medical reasoning and suggest the necessity of careful abstraction and conceptual modeling in AI applications.

Cerebrotendinous xanthomatosis (CTX) is an inborn error of metabolism caused by recessive variants in the cytochrome P450 CYP27A1 gene. CTX is said to manifest with childhood-onset chronic diarrhea and the classic triad of juvenile-onset cataracts, Achilles tendons xanthomas, and progressive ataxia. It is currently one of the few inherited neurometabolic disorders amenable to a specific treatment. The diagnosis may be significantly delayed resulting in permanent neurological impairment. A retrospective review of the clinical characteristics and diagnostic findings in case series of six Polish patients with CTX. Additional retrospective review of symptoms and pathogenic variants of 568 CTX available cases and case series from the past 20 years. To the best of our knowledge, this is the widest review of CTX cases reported in years 2000-2021. We report the largest cohort of Polish patients ever published, with the identification of two hot-spot mutations. During the review of available 568 cases, we found significant differences in the clinical phenotypes and the localization of variants within the gene between Asian and non-Asian populations. These findings may facilitate molecular testing in the Polish and Asian populations. Invariably better screening for CTX and wider awareness is needed.