Completeness and quality of neurology referral letters generated by a large language model for standardized scenarios

Key Points

• The generated referral letters demonstrated high completeness and quality, enhancing clinical communication.
• Quality metrics indicated that over 85% of the letters met established standards for effective referral.
• Analysis based on standardized scenarios highlighted the model's capability to address varied clinical contexts.
• Supporting accurate and timely referrals, AI-generated letters may reduce miscommunication in healthcare.