ChatGPT: a pioneering approach to complex prenatal differential diagnosis

Area of Science:

• Medical Diagnostics
• Artificial Intelligence in Healthcare
• Genetics and Genomics

Background:

• Prenatal diagnosis of rare and complex conditions presents significant challenges.
• Accurate differential diagnosis is crucial for appropriate management and counseling.
• Emerging artificial intelligence tools offer potential support in complex medical scenarios.

Purpose of the Study:

• To explore the utility of ChatGPT in assisting healthcare teams with prenatal diagnosis.
• To evaluate ChatGPT's capability in generating differential diagnoses for rare and complex prenatal cases.
• To identify the limitations and potential risks associated with using AI in this context.

Main Methods:

• A commentary-based analysis of ChatGPT's potential application in prenatal diagnosis.
• Examination of hypothetical deidentified clinical findings to assess AI-generated differential diagnoses.
• Discussion of the ethical and practical considerations for integrating AI into clinical workflows.

Main Results:

• ChatGPT can generate relevant differential diagnoses based on provided clinical information.
• The AI tool demonstrates potential in identifying possibilities for rare and complex prenatal conditions.
• Significant limitations exist, including the need for clinical validation and awareness of potential biases.

Conclusions:

• ChatGPT shows promise as a supportive tool for healthcare teams in prenatal diagnosis.
• Careful consideration of AI limitations and robust clinical oversight are essential for safe implementation.
• Further research is needed to validate AI's role in improving diagnostic accuracy and patient outcomes.