Machine Learning Algorithms Based on Clinical Data to Predict Postoperative Complications of Patients With Hepatolithiasis Undergoing Hepatectomy
Machine Learning Algorithms Based on Clinical Data to Predict Postoperative Complications of Patients With Hepatolithiasis Undergoing Hepatectomy
Postoperative complications seriously affect the recovery of patients undergoing hepatectomy. Identifying risk factors and develop predictive models of complications for patients with hepatolithiasis undergoing hepatectomy is important for clinical practice.
Along with the change of lifestyle and dietary habits, many people are diagnosed with hepatolithiasis that is especially prevalent in Asia. Liver resection remains the favorable curative therapy for hepatolithiasis with a relatively low recurrence rate. Although there have been great improvements in surgical techniques and perioperative management, postoperative complications remain commonplace and seriously threat the recovery of patients undergoing hepatectomy. Therefore, it is important to identify risk factors of complications to improve the overall prognosis of patients. We want to collect the clinical information of patients with hepatolithiasis undergoing hepatectomy, including demographic data , laboratory index, histological features and postoperative complications. Patients are followed up at a interval of 3 month after treatment, and the survival data and recurrence rate are recorded. Then the relationship between clinical data and short-term outcomes after surgery are explored. Then models based on clinical features are developed to predict short-term outcomes after hepatectomy.
Inclusion Criteria:
Exclusion Criteria: