An Unstructured Data Representation Enhanced Method for Postoperative Risk Prediction
Postoperative risk prediction has a positive effect on clinical resource plan,emergency plan preparation and postoperative risk and mortality reduction.To employ the unstructured preoperative diagnosis with rich semantic in-formation,this paper proposes a postoperative risk prediction model via unstructured data representation enhance-ment.The model utilizes self-attention to fuse the structured data with unstructured preoperative diagnosis.Com-pared with the baseline methods,the proposed model improves F1-Score by an average of 9.533%on the tasks of the pulmonary complication risk prediction,the ICU admission risk prediction and the cardiovascular adverse risk prediction.
NETL
NSTL
万方数据
