A Real-world Study of Predictive Models of Gangrenous Cholecystitis Based on Machine Learning
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 发起方
- 入组人数
- 1,006
- 试验地点
- 1
- 主要终点
- pathological diagnosis of patients with cholecystectomy
研究概览
简要总结
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.
详细描述
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.
研究设计
- 研究类型
- Observational
- 观察模型
- Case Control
- 时间视角
- Retrospective
入排标准
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •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.
排除标准
- •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
结局指标
主要结局
pathological diagnosis of patients with cholecystectomy
时间窗: 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
时间窗: 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.
次要结局
- Alanine transaminase value (ALT, U/L)(through study completion, an average of 4 months)
- Fibrinogen value (g/L)(through study completion, an average of 4 months)
- BMI (Kg/m2)(through study completion, an average of 4 months)
- WBC value (10*9/L)(through study completion, an average of 4 months)
- D-dimer value(through study completion, an average of 4 months)
- Gallbladder wallness (cm)(through study completion, an average of 4 months)
研究者
Ying Ma
resident physician
Dalian Medical University