The goal of this observational study is to learn about the risk factors and prediction of postoperative venous thromboembolism (VTE) in patients undergoing lung cancer surgery. The main question it aims to answer is: Which clinical, surgical, and laboratory factors are associated with the development of postoperative deep vein thrombosis (DVT) in lung cancer surgery patients, and can machine learning models accurately predict individual risk? Participants undergoing lung cancer surgery will be prospectively followed for 30 days after surgery. Perioperative clinical data, laboratory results, and imaging findings will be collected to identify VTE risk factors and to develop a predictive model.
Study Type
OBSERVATIONAL
Enrollment
900
The intervention involves the prospective collection of perioperative clinical, laboratory, and imaging data from adult patients undergoing lung cancer surgery. No therapeutic or diagnostic procedures beyond standard care are applied. Collected data will be used to identify risk factors for postoperative deep vein thrombosis (DVT) and to develop machine learning-based predictive models.
The First Hospital of Jilin University, Department of Thoracic Surgery
Changchun, Jilin, China
RECRUITINGIncidence of postoperative deep vein thrombosis (DVT) in lung cancer surgery patients
The primary outcome is the occurrence of postoperative deep vein thrombosis (DVT) within 30 days after lung cancer surgery, confirmed by Doppler ultrasound of the lower extremities. Perioperative clinical, laboratory, and imaging variables will be collected prospectively and analyzed to identify risk factors and develop machine learning-based predictive models for individual DVT risk.
Time frame: From the day of lung cancer surgery to 30 days postoperatively
Identification of perioperative risk factors for postoperative deep vein thrombosis (DVT) in lung cancer surgery patients
Secondary outcomes include the evaluation of clinical, surgical, and laboratory variables associated with postoperative DVT within 30 days. Variables such as age, sex, BMI, comorbidities, tumor characteristics, operative details, and perioperative laboratory results will be analyzed using multivariate logistic regression and machine learning models to identify independent predictors of DVT.
Time frame: From the day of surgery to 30 days postoperatively
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.