Risk Factors Identification of Sepsis and Septic Shock After Major Abdominal Surgery Based on Artificial Intelligence

Shanghai Jiao Tong University

Status: Completed

Conditions: Postoperative Complications; Sepsis

Treatments: Procedure: Exposure to major abdominal surgery

Study type: Observational

Funder types: Other

Identifiers

NCT06684340

XH-24-009

Details and patient eligibility

About

The goal of this observational study is to identify the risk factors and build the early warning system of sepsis and septic shock after major abdominal surgery based on artificial intelligence. The main questions it aims to answer are:

What are the high risk factors of postoperative sepsis? Which factors can accelerate the progression of sepsis? Researchers will collect perioperative characteristics to construct predictive models of postoperative sepsis in a retrospective abdominal surgical population based on artificial intelligence, and the accuracy of the models were tested in an external dataset.

Enrollment: 22,646 patients

Sex: All

Ages: 18+ years old

Volunteers: No Healthy Volunteers

Inclusion and exclusion criteria

Inclusion Criteria：

1. Patients undergoing major abdominal surgery.

2. The surgeon performing the operation has extensive experience in specialized surgeries such as upper gastrointestinal, hepatobiliary and pancreatic, colorectal, gynecological, and urological surgeries, having completed at least 50 corresponding specialized surgical cases.

3. The anesthesiologist performing the operation has more than 5 years of clinical experience.

4. All surgical patients receive general anesthesia.

5. Patients are aged ≥ 18 years. Exclusion Criteria：

6. Pregnancy-related surgeries (cesarean section, abortion surgery). 2. Patients with known preoperative infection or suspected infection. 3. Severely malnourished patients (BMI reference values are 17 kg/m² for patients < 70 years old and 17.8 kg/m² for patients > 70 years old).

7. Patients who have previously undergone abdominal surgery. 5. Patients without sufficient data, including demographic variables (such as age, gender), surgical details (surgery duration, surgical grade, anesthesia grade, anesthesia duration), and hospitalization details (such as ICU stay, in-hospital mortality).