AI Tool Predicts Surgical Scheduling Gaps to Improve OR Utilization

Accurate surgical scheduling remains difficult because case duration and perioperative logistics are unpredictable. With a projected U.S. shortfall of 10,000–19,900 surgeons by 2036, aligning resources with demand is increasingly urgent. Researchers have now identified surgeon-centered factors that can be modeled to predict schedule gaps and improve use of operative time.

Researchers at the University of Massachusetts Amherst analyzed nearly 86,500 surgeries performed at Baystate Medical Center using electronic health record data spanning three years. The team applied machine learning to characterize “gap time,” defined as the interval between when a surgeon completes one case and begins the next. They also introduced a quantitative measure called surgical case demand to capture how taxing a procedure is for the operating surgeon. Findings were published on June 2, 2026 in the Journal of the American Medical Informatics Association.

The analysis identified several characteristics associated with larger surgeon gap times. These included whether the previous or next case was an emergency, whether the preceding surgery involved the chest, whether the following procedure was cardiac, and whether the operation was highly demanding. Ophthalmology and orthopedic procedures were linked to shorter intervals. Surgical case demand was organized into three tiers, ranging from short, elective, low-severity procedures such as lipoma excision or simple dental rehabilitation, to the most onerous tier that includes off-hour emergencies such as brain, abdominal, or spine operations.

The investigators highlighted how current block scheduling is poorly matched to clinical uncertainty. Operating rooms can sit idle because any block shorter than 2.5 hours is unusable for most surgeries. By predicting gap time at the surgeon level, the approach could help identify “collectible time,” defined as a gap long enough to fit another productive task or case. The authors noted that recapturing such time has potential to reduce cost and lighten workload while responding to rising surgical demand.

“Industrial engineering is about understanding and reducing variation. So how can we use the skills and methods we have in engineering and apply those to a high-impact, complex system like health care? We believe that engineering can really make an impact on health care delivery and outcomes,” said Muge Capan, assistant professor in the Riccio College of Engineering at the University of Massachusetts Amherst.

Related Links
University of Massachusetts Amherst