Leveraging Artificial Intelligence to Improve Clinical Appropriateness of Inpatient Designation

Strategic Insights -

A recent study published by the Journal of Doctoral Nursing Practice has demonstrated the potential of artificial intelligence (AI) in reducing observation service volume in hospitals. The research, conducted at the University of Connecticut, found that the implementation of an AI tool in a utilization management (UM) registered nurse (RN) department can effectively reduce observation service discharge rates by improving the identification of comorbidities and enhancing the assessment of medical necessity.

Key Takeaways:

  • The study found that the implementation of an AI tool in a UM RN department reduced observation service discharge rates by 12.75% monthly average compared to 16.69% monthly average in the pre-implementation period.
  • The AI-generated Care Level Score, a key component of the AI tool, played a central role in guiding conversations with providers and advocating for appropriate patient placement.
  • The study demonstrated potential for better decision-making in recommending inpatient appropriateness and reducing observation service volume.
  • The research team found that the implementation of the AI tool was effective in enhancing the identification of comorbidities and assessing medical necessity, leading to improved assessment of severity of illness for inpatient admission.
  • The study highlights the need for better utilization management in assigning observation service versus inpatient admission.
  • The research was guided by Neuman's Systems Model and was conducted in a large academic health system.
  • The study's findings suggest that AI can play a significant role in improving clinical appropriateness of inpatient designation in a utilization management setting.

Statistics:

  • 12.75% monthly average observation service discharge rates post-implementation
  • 16.69% monthly average observation service discharge rates pre-implementation
  • 4.94% reduction in observation service discharge rates post-implementation
  • 10 patients' comorbidities were identified by the AI tool during the study period

Sources:

  • NewsRx. New Findings from University of Connecticut in the Area of Artificial Intelligence Reported (Leveraging Artificial Intelligence to Improve Clinical Appropriateness of Inpatient Designation in a Utilization Management Setting). Journal of Engineering. October 13, 2025; p 1980.
  • Leveraging Artificial Intelligence to Improve Clinical Appropriateness of Inpatient Designation in a Utilization Management Setting. Journal of Doctoral Nursing Practice, 2025.