Artificial Intelligence Assists Surgeons' Decision Making

Jichao Qin

Status: Enrolling

Conditions: Rectal Cancer

Treatments: Other: Artificial intelligence algorithm

Study type: Interventional

Funder types: Other

Identifiers

NCT04999007

TJ-IRB20210643

Details and patient eligibility

About

This study will evaluate whether artificial intelligence technique reduces the temporary ileostomy rate in patients with rectal cancer who receive anterior resection.

Full description

Anastomotic leakage is a serious and life-threatening complication after anterior resection in patients with rectal cancer, and temporary ileostomy was introduced to reduce the serious consequences due to anastomotic leakage. However, whether a temporary ileostomy is applied in the surgery depends on the surgeon's experience, and there are no clinical guidelines to follow. Recently, artificial intelligence has widely been applied in medical field and produced some exciting results, and we have developed a high-performance artificial intelligence model based on 2369 rectal cancer patients, which showed good discrimination of anastomotic leakage and may reduce the temporary ileostomy rate. Hence, this randomized controlled trail will evaluate the artificial intelligence model for guiding surgical decision-making of performing a temporary ileostomy in patients with rectal cancer who receive anterior resection.

Enrollment: 616 estimated patients

Sex: All

Ages: 18 to 85 years old

Volunteers: No Healthy Volunteers

Inclusion criteria

1. Aged older than 18 years and younger than 85 years.
2. Primary rectal adenocarcinoma confirmed by preoperative pathology result.
3. Expected curative resection via total mesorectal excision procedure.
4. American Society of Anesthesiologists (ASA) class I, II, or III.
5. Written informed consent.

Exclusion criteria

1. Pregnant or breastfeeding women.
2. Severe mental disorder or language communication disorder.
3. Hartmann surgery or colostomy is performed intraoperatively.
4. Interrupted of surgery for more than 30 minutes due to any cause.
5. Malignant tumors with other organs

Trial design

Primary purpose: Diagnostic

Allocation: Randomized

Interventional model: Parallel Assignment

Masking: Triple Blind

---

616 participants in 2 patient groups

Control

No Intervention group

Description:

Whether the patients in the control arm will receive a temporary ileostomy depends on surgeons' experience.

Intervention

Experimental group

Description:

Whether the patients in the intervention arm will receive a temporary ileostomy depends on the risk of anastomotic leakage calculated by the artificial intelligence algorithm.

Treatment:

Other: Artificial intelligence algorithm