Construction of a Predictive Model of Gangrenous Cholecystitis Based on Machine Learning

Completed

• Conditions: Gangrenous Cholecystitis
• Interventions: Other: Observational

• Registration Number: NCT06399081
• Lead Sponsor: Dalian Medical University

Brief Summary

Gangrenous cholecystitis is the most common complication of acute cholecystitis.

There is no research using machine learning models to construct predictive diagnostic models for gangrenous cholecystitis.

Detailed Description

This study reviewed the clinical data of 2023 cholecystectomy patients admitted to our center between January 1, 2015, and May 31, 2015, it includes demographic, clinical features, laboratory and imaging indexes, and constructs five commonly used Decision Tree, SVM, Random Forest, XGBoost, AdaBoost models, feature subsets are selected by Recursive Feature Elimination with Cross-Validation and the importance of variables in each model, model performance is evaluated by Balanced accuracy, Recall, Precision, F1score, and the Precision-Recall(PR) curve, and the final results are verified by independent external validation sets.

Study Timeline

• Study Start: 2023-12-01
• Primary Completion: 2024-03-01
• Study Completion: 2024-03-02
• Study First Submitted: 2024-04-29
• Status Verified: 2024-05
• Study First Submitted QC: 2024-05-01
• Last Update Submitted: 2024-05-01
• Study First Posted: 2024-05-03
• Last Update Posted: 2024-05-03

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 1006

Inclusion Criteria

• patients diagnosed with acute cholecystitis or acute exacerbation of chronic cholecystitis in our hospital and receiving complete clinical treatment in our hospital;
• performing cholecystectomy;
• having complete and searchable clinical data, such as patient's age, surgical records, and hospitalization days.

Exclusion Criteria

• previous diagnosis of chronic cholecystitis, this time for elective surgical treatment;
• previous diagnosis of acute cholecystitis, ultrasound-guided cholecystectomy after elective laparoscopic cholecystectomy;
• concomitant with other acute biliary and pancreatic system-related diseases, such as obstructive jaundice caused by choledochal stones, acute cholangitis, acute pancreatitis, etc.;
• exclude patients who combined with other surgery patients such as choledochotomy and lithotripsy, choledochoscopic exploration and lithotripsy, bile-intestinal anastomosis, appendectomy, etc;
• those with incomplete data

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Non-gangrenous cholecystitis	Observational	Non-gangrenous cholecystitis, such as chronic cholecystitis, acute cholecystitis, acute attack of chronic cholecystitis
Gangrenous cholecystitis	Observational	Defined based on intraoperative findings or pathological diagnosis

Primary Outcome Measures

Name	Time	Method
pathological diagnosis of patients with cholecystectomy	30 days	Check the patient's pathological report and whether the pathological description contains phenomena such as full layer ischemic necrosis and ulceration of the gallbladder wall. Diagnose as gangrenous cholecystitis or non-gangrenous cholecystitis.
The predictive performance of diagnostic prediction models	through study completion, an average of 4 months	The predictive diagnosis was obtained by the model and each predictive variable, and the metric (Accuracy, Recall, Precision, F1score) of the model was obtained by comparing with the actual pathological diagnosis.

Secondary Outcome Measures

Name	Time	Method
Alanine transaminase value (ALT, U/L)	through study completion, an average of 4 months	Correlation between liver function and patients with gangrenous cholecystitis and non-gangrenous cholecystitis
Fibrinogen value (g/L)	through study completion, an average of 4 months	Correlation between coagulopathy and patients with gangrenous cholecystitis and non-gangrenous cholecystitis
BMI (Kg/m2)	through study completion, an average of 4 months	Correlation between obesity level and patients with gangrenous cholecystitis and non-gangrenous cholecystitis
WBC value (10*9/L)	through study completion, an average of 4 months	Correlation between WBC and patients with gangrenous cholecystitis and non-gangrenous cholecystitis
D-dimer value	through study completion, an average of 4 months	Correlation between coagulopathy and patients with gangrenous cholecystitis and non-gangrenous cholecystitis
Gallbladder wallness (cm)	through study completion, an average of 4 months	Correlation between Gallbladder wallness and patients with gangrenous cholecystitis and non-gangrenous cholecystitis

Trial Locations

Locations (1)

The Second Hospital of Dalian Medical University; 🇨🇳 Dalian, Liaoning, China