Vishnu Nair
Research Mentor(s): Andrew Wong
Mentor Department: Internal Medicine
Authors: Vishnu Nair, Andrew Wong
Session: Session 1 (9:00am – 9:50am)
Presentation Type: Poster 62
Abstract
The increasing complexity of hospital operations has led to a growing interest in artificial intelligence (AI) as a means to improve efficiency and patient outcomes. Hospitals face a myriad of challenges, including patient overcrowding, ineffective resource allocation, and administrative burdens, making AI-driven approaches a promising solution for optimizing clinical operations. This narrative review investigates the impact of operational health AI solutions on key clinical outcomes, including patient mortality, length of stay, readmissions, and discharge rates. This study analyzes primary research studies reporting AI applications in hospital-based clinical operations, ensuring a thorough examination of real-world integration. Key methodologies that were analyzed include AI systems, machine learning models, and predictive analytics used to enhance decision-making and streamline processes. Studies were evaluated based on their sample size, reported effectiveness and implementation challenges. Findings indicate that a large number of AI technologies have been developed to optimize operational tasks, but there are significant challenges in the implementation of such models due to data integration issues, algorithmic bias, and regulatory barriers. Additionally, most studies fail to report financial data regarding implementation costs, potential savings, or return on investment, leaving uncertainties regarding cost-effectiveness. This study highlights AI’s potential to enhance hospital operations and provides relevant insights for hospital leadership and policymakers to promote the adoption of AI-driven solutions, ultimately aiming to improve patient care and healthcare system efficiency.
