Chang Yang

Chongqing University Cancer Hospital, China

Abstract Title: High-precision prediction model for deep vein thrombosis risk in malignant tumor surgery patients: A big data approach

Biography:

Chang Yang completed her BM at the age of 23 from Tianjin University of Traditional Chinese Medicine. She is a head nurse of the Department of anesthesiology - Chongqing University Cancer Hospital, China. She is a member of Chongqing Health Promotion and Health Education Society and Anesthesia Nursing Professional Committee, Chongqing Nursing Society. She has published more than 10 papers in journals.

Research Interest:

Deep vein thrombosis (DVT) poses a significant risk to patients undergoing malignant tumor surgery, contributing to increased morbidity and mortality. This study aims to develop a high-precision prediction model for assessing DVT risk in these patients, leveraging big data and advanced machine learning algorithms. By utilizing a comprehensive dataset comprising clinical, demographic, and perioperative variables from a large cohort of cancer surgery patients, the model was trained and validated to accurately predict individual DVT risk. The research methodology included retrospective data analysis, feature selection techniques, and the application of various machine learning models, with an emphasis on optimizing predictive accuracy and generalizability. Key findings demonstrate that the model achieved superior performance, with an accuracy rate of over 90%, significantly outperforming traditional risk assessment tools. The most influential predictors identified include patient age, cancer type, previous history of thromboembolism, and specific intraoperative factors. The model's integration into clinical practice has the potential to enhance preoperative risk stratification, enabling personalized preventive interventions for high-risk patients and improving overall surgical outcomes. These results underscore the value of incorporating big data analytics into surgical risk assessment, offering a promising tool for reducing DVT incidence and associated complications in cancer surgery patients. Further research is needed to validate the model across diverse clinical settings and patient populations.

Key Words: Deep vein thrombosis, malignant tumor surgery, big data, machine learning, prediction model.