ChatGPT-4 to detect surgical wound infections after colorectal surgery
Official title: Evaluation of ChatGPT-4 for the Detection of Surgical Site Infections From Electronic Health Records After Colorectal Surgery: A Diagnostic Accuracy Study.
Run by Hospital de Granollers · NCT06626399 · Data updated 2026-11-12
We will test whether ChatGPT-4 can accurately find surgical site infections from electronic health records in people having elective colorectal resection.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 1100 (estimated) |
| Sponsor | Hospital de Granollers Academic / other |
| Locations | 1 site (Granollers, Barcelona) |
| Status | Recruiting |
| Started | January 15, 2025 |
| Main results expected | September 30, 2025 |
| Study ends | November 30, 2025 |
| Registry record updated | August 15, 2025 |
| Trial ID | NCT06626399 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults undergoing elective colorectal resection with no infection at the time of surgery and no prior intestinal stoma are ideal candidates.
✕Probably not a fit
Patients who had emergency surgery, had an infection present at the time of operation, or have a previous intestinal stoma are excluded and unlikely to benefit.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
Researchers will apply the ChatGPT-4o model to electronic health record data — including clinical notes, microbiology reports, and diagnostic codes — from patients who underwent elective colorectal resection at Hospital General de Granollers. The AI will flag suspected surgical site infections at the three CDC anatomical levels and these flags will be compared with the hospital’s standard manual infection-control surveillance over the 30–90 day postoperative period. The observational analysis will report sensitivity, specificity, and agreement with human surveillance and describe cases of disagreement. The goal is to explore whether automated detection can reduce manual workload and speed identification of postoperative infections.
Why it matters
Potential benefit: If successful, this approach could detect infections sooner and more consistently, enabling earlier treatment and fewer complications.
How similar studies have gone: Prior studies using natural language processing and other AI methods for SSI surveillance have shown promising accuracy in retrospective cohorts, but use of ChatGPT-4 for this specific task is relatively novel.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Elective colorectal resection Exclusion Criteria: * Emergency surgery * Infection present at operation * Previous intestinal stoma
Where it's running
-
Hospital General de Granollers
Granollers, Barcelona, Spain Recruiting
Study contacts
- Study coordinator: Josep Badia, MD, PhD
- Email: jmbadiaperez@gmail.com
- Phone: 670702099
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Silver foam dressing after cesarean: does it prevent infection as well as standard care?
This trial tests whether a silver-containing foam dressing worn over cesarean incisions is no worse than standard dressings at preventing surgical site infections.
-
Skin staples vs polypropylene skin sutures after elective laparotomy
This trial tests whether skin staples or polypropylene sutures work better for closing the skin after elective abdominal surgery in adults.
-
Hernia Sac Flap Coverage of Mesh in Complex Bony-Edged Ventral Hernias
We’re testing whether using the patient’s own hernia sac as a living flap underneath the mesh helps healing after complex ventral hernia repair when part of the edge is bone.
-
Steri-Strips added to standard wound closure after cesarean delivery
This study tests whether adding Steri-Strips after a C-section helps reduce wound problems for pregnant patients.
-
Cold atmospheric plasma to improve cannulation-site wound healing after extracorporeal life support
This trial will test whether adding cold atmospheric plasma (CAP) to standard wound care helps adults on extracorporeal life support heal cannulation-site wounds faster and with fewer infections.
-
Preventing wound infections in children having open groin surgery with IV antibiotics or antimicrobial-coated sutures
This will test whether a single IV antibiotic dose or antimicrobial-coated sutures prevent wound infections in children having open groin surgery.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.