Assessment of the Efficacy of ChatGPT in Detecting Surgical Site Infections Following Elective Colorectal Surgery

NCT06556017 | Completed

• 1 other identifier: HGG2024_03
• Study Type: observational
• Target: 122
• Locations: 1 country
• Sites: 1

Brief Summary

Epidemiological surveillance is one of the eight core components of the World Health Organization Infection Prevention and Control Programmes. These include surveillance programmes for surgical site infection (SSI). At present, for SSI surveillance, infection control teams perform a manual time-consuming work, which could make a transition to automated surveillance leveraging the new information technology. This study aimed to evaluate the ability of ChatGPT-4o to detect surgical site infection at the three anatomical levels.

Conditions

Surgical Site Infection

Keywords

Surgical Site Infection; Surveillance; Artificial intelligence; ChatGPT; natural language processing

Outcome Measures

Primary Outcomes (1)

• Rate of surgical site infection

  Rate of Surgical site infection according to the definitions of the CDC-NHSN (Centers for Disease Control and Prevention-National Healthcare Safety Network)

  30 days

Study Arms (2)

Patients assessed for ILQ using the standard manual surveillance method

Patients undergoing colorectal surgery enrolled in the nationwide ILQ surveillance programme and assessed for ILQ using the standard manual surveillance method.

Diagnostic Test: Diagnosis of SSI

ILQ patients assessed by Open IA's ChatGPT 4 chatbot

Patients undergoing colorectal surgery enrolled in the nationwide ILQ surveillance programme and assessed for ILQ using the Open IA's ChatGPT 4 chatbot.

Diagnostic Test: Diagnosis of SSI

Interventions

Diagnosis of SSI DIAGNOSTIC_TEST

Comparison of the manual system and ChatGPT for SSI diagnosis in colorectal surgery procedures enrolled in the SSI surveillance programme.

ILQ patients assessed by Open IA's ChatGPT 4 chatbot; Patients assessed for ILQ using the standard manual surveillance method

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Patients undergoing elective colorectal surgery in Catalonia in the period 2020-2022

You may qualify if:

• Elective colorectal resection

You may not qualify if:

• Emergency surgery
• Infection present at operation
• Previous intestinal stoma

Sponsors & Collaborators

• Hospital de Granollers: lead

Study Sites (1)

Hospital General de Granollers

Granollers, Barcelona, 08402, Spain

Location

Related Publications (1)

• Badia JM, Casanova-Portoles D, Membrilla E, Rubies C, Pujol M, Sancho J. Evaluation of ChatGPT-4 for the detection of surgical site infections from electronic health records after colorectal surgery: A pilot diagnostic accuracy study. J Infect Public Health. 2025 Feb;18(2):102627. doi: 10.1016/j.jiph.2024.102627. Epub 2024 Dec 18.

  PMID: 39740340 DERIVED

MeSH Terms

Conditions

Surgical Wound Infection

Condition Hierarchy (Ancestors)

Wound Infection; Infections; Postoperative Complications; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Prof

Study Record Dates

• First Submitted: August 13, 2024
• First Posted: August 15, 2024
• Study Start: August 15, 2024
• Primary Completion: September 1, 2024
• Study Completion: September 1, 2024
• Last Updated: October 3, 2024

Record last verified: 2024-10

Locations

ES (1)