Purpose: Artificial intelligence has been applied across various fields of medicine, with large language models (LLMs) demonstrating potential to assist in clinical decision-making for rare diseases. This study assessed the performance of LLMs in aiding the phenotyping process and guiding the identification of correct genetic conditions. Materials and Methods: Clinical images from 10 Korean individuals with genetically confirmed rare diseases were collected through a literature review. Using identical prompts, the top 10 Human Phenotype Ontology (HPO) terms and suspected genetic conditions were queried across three LLMs: generative pre-trained transformers (GPTs) models GPT-4o and GPT o1, and Claude 3.5 Sonnet. Concordance between 5 manually curated key HPO terms and the top 10 predicted terms were assessed, and the accuracy of genetic diagnoses among the LLMs was analyzed. Results: Clinical images, ranging from 3 to 9 per case, were used as input for 10 Korean rare disease cases. The average number of key HPO terms correctly matched among the top 10 predictions was 3.0 (1.99-4.01) for GPT-4o, 2.8 (2.06-3.54) for GPT o1, and 1.7 (0.80-2.60) for Claude 3.5 (mean, [95% confidence interval]). GPT models provided more specific HPO terms than Claude in these cases. The accuracy of genetic diagnosis within the top 10 predictions was 2/10 for GPT-4o, 3/10 for GPT o1, and 0/10 for Claude 3.5, with frequent hallucination events observed. Conclusion LLMs demonstrate potential as a supportive tool for image-based rare disease phenotyping, while the frequent hallucinations highlight the need for further investigation and caution in clinical application.

Purpose: Rare diseases necessitate consistent access to specialized health services. In Korea, despite the growing socioeconomic burden, insufficient comprehensive research is available on patients with rare diseases and their families, particularly concerning factors influencing the length of time to diagnosis. The aim of this study was to thoroughly characterize rare pediatric diseases and explore factors impacting the diagnostic odyssey. Methods: The study enrolled patients under 15 years old seeking medical care at the Seoul National University Children’s Hospital Rare Disease Center between January 2022 and December 2023. Participating patients were required to have been diagnosed with one of the 1,248 rare diseases recognized in Korea. A 33-question survey was developed to assess clinical features of the patients, characteristics of their primary caregivers, and their perceptions of ongoing medical care. Results: The study included 101 patients and their families. Regarding perceived cognitive and motor functions, most families indicated moderate or severe limitations (cognitive, 62.4%; motor, 57.4%). Over half of the families (53.5%) reported discontinuing employment to provide patient care. Neurological symptoms represented the most common initial chief concern, with dermatologic symptoms and laboratory test abnormalities also noted. Three factors were associated with time to diagnosis: the number of hospitals visited, whether the districts of residence and diagnosis aligned, and the age at symptom onset. Conclusion The comprehensive characterization of patients with rare diseases and their families in Korea, along with the identification of factors impacting the diagnostic odyssey, provides key insights for the development of a tailored support system.