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

Dalian Medical University1,006 enrolled

Overview

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.

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 Type

OBSERVATIONAL

Enrollment

1,006

Conditions

Gangrenous Cholecystitis

Interventions

ObservationalOTHER

Observational

Eligibility

Sex: ALL

Medical Language ↔ Plain English

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

Locations (1)

The Second Hospital of Dalian Medical University

Dalian, Liaoning, China

Outcomes

Primary Outcomes

pathological diagnosis of patients with cholecystectomy

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.

Time frame: 30 days

The predictive performance of diagnostic prediction models

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.