Ambient Artificial Intelligence Versus Human Scribes in the Emergency Department

Area of Science:

• Health Informatics
• Artificial Intelligence in Medicine
• Emergency Medicine

Background:

• The integration of artificial intelligence (AI) into healthcare aims to improve efficiency and documentation.
• Human scribes are traditionally used to assist physicians with electronic health record (EHR) documentation.

Purpose of the Study:

• To compare the note quality and EHR time utilization of ambient AI scribes versus human scribes in an emergency department setting.

Main Methods:

• A pilot quality improvement study was conducted with physicians using either human or AI scribes.
• Note quality was assessed using the Physician Documentation Quality Instrument (PDQI-9) by blinded physicians.
• Time metrics and physician contributions within the EHR were recorded and compared between scribe groups.

Main Results:

• AI scribes were associated with increased time spent in the EHR notes section for both adult and pediatric patients.
• Physician contributions to notes were significantly higher when using AI scribes.
• Note quality was similar for adults but lower for pediatric patients when using AI scribes compared to human scribes.

Conclusions:

• Ambient AI scribes require more EHR time and increase physician documentation input compared to human scribes.
• The quality of AI-generated notes may be lower, especially in pediatric emergency care.
• Further research is needed to optimize AI scribe performance and assess long-term impacts.