JMIR Publications

ABSTRACT

Background:

Recent studies have demonstrated that large language models (LLMs) exhibit exceptional performance in medical examinations. However, there is a lack of reports assessing their capabilities in specific domains or their application in practical data analysis using code interpreters. Furthermore, comparative analyses across different LLMs have not been extensively conducted.

Objective:

The purpose of this study was to evaluate whether advanced AI models can analyze data from template-based input and can demonstrate basic knowledge of reproductive medicine. The three AI models (Chat GPT, Claude, and Gemini) were evaluated for their data analytical capabilities through numerical calculations and graph rendering. Their knowledge of infertility treatment was assessed by solving ten examination questions from experts.

Methods:

First, we uploaded data to the AI models and furnished instruction templates using the chat interface. The study investigated whether the AI models could perform pregnancy rate analysis and graph rendering, based on blastocyst grades according to Gardner criteria. Second, we assessed model diagnostic capabilities based on specialized knowledge. This evaluation utilized ten questions derived from the Japanese Fertility Specialist Examination and the Embryologist Certification Exam, along with chromosome imaging. These materials were curated under the supervision of certified embryologists and fertility specialists. All procedures were repeated ten times per AI model.

Results:

GPT-4o and Gemini performed analyses within 30 seconds, requiring minor corrections from time to time thereafter. However, the process did not reach the stage of data analysis with Claude. GPT-4o, Claude, and Gemini achieved perfect scores on a set of nine knowledge-based questions derived from professional fertility specialist examinations. However, none of the AI models were able to accurately perform karyotype diagnostic tasks in reproductive medicine.

Conclusions:

This rapid processing demonstrates the potential for these AI models to significantly expedite data-intensive tasks in clinical settings. This performance underscores their potential utility as educational tools or decision support systems in reproductive medicine. However, none of the models were able to accurately interpret and diagnose using medical images.