RESUMO
BACKGROUND: Large language models (LLMs) have impacted advances in artificial intelligence. While LLMs have demonstrated high performance in general medical examinations, their performance in specialized areas such as nephrology is unclear. This study aimed to evaluate ChatGPT and Bard in their potential nephrology applications. METHODS: Ninety-nine questions from the Self-Assessment Questions for Nephrology Board Renewal from 2018 to 2022 were presented to two versions of ChatGPT (GPT-3.5 and GPT-4) and Bard. We calculated the correct answer rates for the five years, each year, and question categories and checked whether they exceeded the pass criterion. The correct answer rates were compared with those of the nephrology residents. RESULTS: The overall correct answer rates for GPT-3.5, GPT-4, and Bard were 31.3% (31/99), 54.5% (54/99), and 32.3% (32/99), respectively, thus GPT-4 significantly outperformed GPT-3.5 (p < 0.01) and Bard (p < 0.01). GPT-4 passed in three years, barely meeting the minimum threshold in two. GPT-4 demonstrated significantly higher performance in problem-solving, clinical, and non-image questions than GPT-3.5 and Bard. GPT-4's performance was between third- and fourth-year nephrology residents. CONCLUSIONS: GPT-4 outperformed GPT-3.5 and Bard and met the Nephrology Board renewal standards in specific years, albeit marginally. These results highlight LLMs' potential and limitations in nephrology. As LLMs advance, nephrologists should understand their performance for future applications.
Assuntos
Nefrologia , Autoavaliação (Psicologia) , Humanos , Avaliação Educacional , Conselhos de Especialidade Profissional , Competência Clínica , Inteligência ArtificialRESUMO
Pregnancy-onset thrombotic thrombocytopenic purpura (TTP) was reported by many obstetricians and hematologists, but less by nephrologists, and the detailed clinical course of its renal complication is not known. Here, we report a case of a 33-year-old pregnant woman who suffered from pregnancy-onset TTP with nephrotic syndrome which was controlled by the termination of pregnancy. On admission, she had periorbital and lower leg edema at 32 weeks of gestation. Her serum albumin level was 2.8 g/dL and the urine protein/creatinine ratio was 4.1 g/g Cr. Besides those, she had thrombocytopenia, hemolytic anemia, and severe deficiency of A Disintegrin-like and Metalloproteinase with Thrombospondin type 1 motifs 13 (ADAMTS-13) activity. Thus, she was diagnosed with nephrotic syndrome due to pregnancy-onset TTP. A cesarean section was performed without complications for the patient and her baby. Then, all her symptoms improved shortly. She was suspected of congenital TTP because of no ADAMTS-13 inhibitor results and the persistent deficiency of ADAMTS-13 activity even after her condition improved. Pregnancy-onset TTP can cause nephrotic syndrome. Termination of pregnancy should be considered in cases with pregnancy-onset TTP to protect kidney function.