Healthcare / Health system
Houston Methodist: Recording perioperative events and managing operating room turnover with image-based AI
- Company
- Houston Methodist
- Country
- United States
- Adoption stage
- In operation
- Source published
- In use from
- Date basis
- The date the source was published. It can differ from the date adoption started.
- How the source was checked
- Read the full source text
The work problem
According to an article Houston Methodist published on its official blog on August 14, 2026, operating rooms require precise coordination between clinical and nonclinical teams, yet many essential workflow steps went undocumented or were recorded late. Circulating nurses manually documented patient arrival, anesthesia readiness, case start and case end, but steps such as room setup, patient transfer and induction were hard to capture in real time.
Technology and data
In December 2022, Houston Methodist deployed Apella's image-based AI platform in the 15-room cardiothoracic operating suite at Walter Tower of Houston Methodist Hospital. In each room, an object detection model and an event detection model analyze images from four wall-mounted cameras to automatically timestamp events such as patient entry, draping and room turnover, and the system sends text alerts to surgeons when a patient arrives, is draped and when the case ends. OR management, housekeeping, infection control and anesthesia leaders review turnover bottlenecks together using the video, which is retained for only 30 days with no audio captured.
Results
When the research team compared 6 months of pre-deployment and 10 months of post-deployment data against a synthetic control built from other Houston Methodist operating room sites, monthly case volume at Walter Tower rose by about 7%, or about 25 cases per month. According to the blog, cardiothoracic and vascular cases stayed between 86% and 87% of the case mix and operative minutes did not decrease, while shorter turnover times allowed more cases to be completed within the same operating room hours.
Limits and open questions
The research paper states that physicians joining and leaving and changes in room assignments during the same period make it hard to attribute the effect to AI alone, and the analysis covers data from June 2022 to September 2023.
Sources
- Image-Based AI Improves OR Efficiency at Houston Methodisthoustonmethodist.org, Accessed
- Implementation of Image-Based Artificial Intelligence Is Associated with Increased Case Volume in a High-Acuity, 15-Room Cardiothoracic Operating Suite at a Tertiary Academic Hospitalpmc.ncbi.nlm.nih.gov, Accessed
Compiled from public sources. These are not results from ATF Works customers.