Overview

Artificial intelligence (AI) is proving to be a valuable tool for emergency department (ED) teams, enabling them to predict which patients will require hospital admission significantly earlier than current methods allow. This finding comes from a comprehensive study conducted by the Mount Sinai Health System.

Key Findings

• The study involved collaboration with over 500 ED nurses across seven hospitals.
• Researchers utilized a machine learning model trained on data from more than 1 million past patient visits.
• AI predictions were compared with nurses’ triage assessments over a two-month period.
• The AI model demonstrated reliable performance across diverse hospital settings, accurately predicting admissions.

Benefits of AI in Emergency Care

By providing advance notice of potential admissions, this AI approach can:

• Enhance patient care and overall experience.
• Reduce overcrowding and “boarding” in emergency departments.
• Allow hospitals to allocate resources more effectively.

Expert Insights

Lead author Jonathan Nover, Vice President of Nursing and Emergency Services at Mount Sinai, emphasized the importance of AI in improving admission planning. He stated, “Our goal was to see if AI combined with input from our nurses could help hasten admission planning, a reservation of sorts.”

Future Directions

While the study was limited to a specific health system and timeframe, the researchers aim to implement the AI model into real-time workflows. Future evaluations will focus on:

• Reducing boarding times.
• Improving patient flow.
• Enhancing operational efficiency.

Conclusion

This study highlights the potential of AI not as a replacement for clinicians but as a supportive tool that can help healthcare teams deliver more timely and compassionate care. The findings are expected to pave the way for further clinical testing and integration of AI in emergency departments.

The full study is published in the Mayo Clinic Proceedings: Digital Health.