Modeling Workflow, Operational, and Financial Implications of AI-Enabled Same-Day Diagnostic Follow-Up for Screening...

Area of Science:

• Medical Imaging
• Artificial Intelligence in Healthcare
• Health Services Research

Background:

• Evaluating artificial intelligence (AI) in healthcare often prioritizes technical metrics over real-world workflow, operational, and financial impacts.
• Simulation models offer a proactive approach to assess AI implementation effects before clinical deployment.
• Understanding these impacts is crucial for informed decision-making regarding AI adoption.

Purpose of the Study:

• To evaluate an AI-assisted workflow for same-day diagnostic breast imaging using discrete-event simulation.
• To quantify the impact of AI on patient follow-up rates and return visit requirements.
• To assess the operational and financial benefits of integrating AI into breast imaging workflows.

Main Methods:

• Discrete-event simulation modeling was employed.
• The study focused on an AI-assisted workflow for diagnostic breast imaging after abnormal screening mammograms.
• Key performance indicators included patient capture rates, visit efficiency, revenue generation (work relative value units), and clinic operating hours.

Main Results:

• The AI-assisted workflow improved patient capture from screening mammograms by an additional 1.1%, reducing loss to follow-up.
• It eliminated the need for a second visit for diagnostic workup for 11% of patients.
• The workflow increased daily work relative value units by 4.8% (estimated $15,979 annual gain) and extended clinic hours by 2.9% (109.5 hours annually).

Conclusions:

• Simulation modeling is a valuable tool for predicting the operational and financial implications of AI in clinical practice.
• AI-assisted workflows in diagnostic breast imaging can significantly enhance patient management and clinic efficiency.
• The integration of AI has the potential to improve healthcare delivery and financial performance in imaging departments.