Skip to content
Curious Context Labs

case study · Healthcare · Custom app

Fuller theatre lists with fewer on-the-day cancellations

How realistic case durations and ready standby patients can make better use of every operating session.

business
Hospitals
build
Custom app
timeline
8–10 weeks
read
3 min

01 the business

Elective surgical centre

8 theatres, 40 lists a week

Lists are planned with average case times. Some overrun and patients are cancelled; others finish early. Late cancellations leave gaps that are hard to fill, and waiting lists grow.

02 before

The problem

Lists are planned with average or guessed case times, so some overrun and get cancelled while others finish early. Late cancellations leave empty slots that are hard to refill at short notice. Waiting lists grow while theatre time goes unused.

  • Lists overrun or finish early unpredictably.
  • Patients are cancelled on the day for incomplete checks.
  • Freed slots go unused.

03 the build

What the AI does

  1. Step 1: Reads the waiting list, surgeon availability, theatre sessions and equipment from your theatre system.
  2. Step 2: Estimates each case's duration from that surgeon's past times for similar procedures.
  3. Step 3: Proposes lists that fit the session, respect clinical priority and keep equipment and staffing in mind.
  4. Step 4: Spots likely late cancellations, such as incomplete pre-operative checks, and suggests standby patients who are ready.
  5. Step 5: Reports overruns, early finishes and late starts by specialty each week.

paused: waiting for a person to approve

How it was put together

  • Estimated case durations from each surgeon's past times for similar procedures.
  • Proposed lists that fit the session and respect clinical priority.
  • Spotted likely cancellations, such as incomplete pre-op checks, and suggested ready standby patients.
  • Reported overruns, early finishes and late starts weekly.

04 human in the loop

Where a person stays in charge

Surgeons and schedulers approve every list. Clinical priority is set by the surgical team, and the tool never removes a patient from a list.

  • Surgeons and schedulers approve every list.
  • Clinical priority is set by the surgical team.
  • The tool never removes a patient from a list.

05 rollout

From kickoff to live in 8–10 weeks

  1. Weeks 1–3Load two years of theatre data and agree rules with surgical leads.
  2. Weeks 4–6Propose lists for two specialties alongside the schedulers.
  3. Weeks 7–10Extend to all specialties with weekly review.

06 after

What changes

More of each session is used for operating, fewer patients are cancelled on the day, and waiting lists move faster.

worked example · your numbers will differ

Assume 40 lists a week and better planning adding one extra case to one list in five, over 46 working weeks.

40 × 20% = 8 extra cases a week, or 368 more operations a year from the same theatres.

What to measure

  • Session time used for operating.
  • On-the-day cancellations.
  • Overruns and early finishes.
  • Patients treated per list.

07 evidence

What the research says

  1. The global nursing shortage was 5.8 million in 2023 and is projected to be 4.1 million in 2030.

    World Health Organization, State of the World's Nursing 2025 (opens in a new tab) · 2025

  2. Around 1 in 10 patients is harmed in health care, and more than half of that harm is preventable.

    World Health Organization, Patient safety fact sheet (opens in a new tab) · 2023

08 lessons

Mistakes to avoid

  • Using averages. Each surgeon's own history matters.
  • Overpacking lists. Overruns cause cancellations.
  • No standby patients. Freed slots need ready patients.

09 questions

Common questions

Does it decide clinical priority?
No. The surgical team sets priority; the tool fits lists around it.
Which theatre systems does it use?
Epic OpTime, Oracle Health SurgiNet and other theatre management systems with data exports.

keep reading

All case studies ->

Tell us how your business runs. We'll tell you where AI fits.

A free 30-minute call. You talk, we ask questions, and you leave with a few concrete ideas — or an honest answer that AI isn't the right fix yet.

Working with teams around the world.