The MediVoice implementation journey: ambient artificial intelligence for clinical documentation.

Area of Science:

• Clinical Informatics
• Artificial Intelligence in Healthcare
• Human-Computer Interaction

Background:

• Healthcare systems face significant clinician documentation burden and cognitive load.
• Ambient Artificial Intelligence (AI) scribes are emerging as a solution to alleviate these pressures.
• The National University Health System, Singapore, sought to implement and evaluate such a tool.

Purpose of the Study:

• To introduce and evaluate MediVoice, an ambient AI scribe developed for clinical settings.
• To assess the usability, accuracy, workflow integration, and time-saving potential of MediVoice.
• To identify key factors for successful broader adoption and implementation of ambient AI scribes.

Main Methods:

• Pilot implementation of MediVoice across diverse clinical settings.
• Rapid evaluation using Plan-Do-Study-Act cycles.
• Assessment by doctors, nurses, and allied health professionals focusing on usability, accuracy, workflow fit, and time savings.

Main Results:

• Iterative refinement of MediVoice based on real-time clinician feedback.
• Identification of critical success factors for broader deployment, including leadership engagement, training, and infrastructure.
• Demonstration of organizational learning through experimentation with AI adoption.

Conclusions:

• Ambient AI scribes offer significant benefits but require more than technical proficiency for success.
• Effective implementation hinges on continuous adaptation, workflow alignment, and cross-professional collaboration.
• Organizational readiness, governance, and supportive infrastructure are crucial for integrating AI tools into clinical environments.