本文已被：浏览 660次 下载 1379次
Received:December 15, 2021 Revised:January 24, 2022
Received:December 15, 2021 Revised:January 24, 2022
中文摘要: 外周穿刺置入中心静脉导管(PICC)技术被广泛运用于中长期静脉治疗. 在PICC置管时会导致各种并发症和不良反应, 如PICC相关性血栓. 随着机器学习和深度神经网络的不断发展与完善, 为PICC相关性血栓的辅助诊断提供了基于临床医学数据的解决方法. 本文构建了基于DeepFM和XGBoost的融合模型, 针对稀疏数据进行特征融合并能降低过拟合的情况, 能够对PICC相关性血栓提供风险预测. 实验结果表明, 融合模型能够有效地对PICC相关性血栓进行特征重要性提取并预测患病概率, 辅助临床在外周穿刺置过程中识别血栓高危风险因素, 及时进行干预从而预防血栓的发生.
Abstract:The peripherally inserted central catheter (PICC) technology is widely used in medium and long-term venous treatment, but it can cause various complications and adverse reactions, such as PICC-related thrombosis. The continuous development of machine learning and deep neural networks provides a solution for the assisted diagnosis of PICC-related thrombosis based on clinical medical data. In this study, a fusion model of DeepFM and XGBoost is constructed to predict the risks of PICC-related thrombosis, which can perform feature fusion for sparse data and reduce over-fitting. The experiment reveals that the fusion model can effectively extract the feature importance of PICC-related thrombosis, predict the probability of disease, assist the clinic in identifying high-risk factors of thrombosis in PICC, and intervene to prevent the occurrence of thrombosis in time.
keywords: machine learning prediction of thrombosis DeepFM XGBoost fusion model prediction model deep learning
文章编号： 中图分类号： 文献标志码：
基金项目:江苏省研究生科研与实践创新项目(SJCX21_1695)
引用文本：
李莉,谢超,吴迪.基于DeepFM和XGBoost融合模型的静脉血栓预测.计算机系统应用,2022,31(9):376-381
LI Li,XIE Chao,WU Di.Prediction of Venous Thrombosis Based on Fusion Model of DeepFM and XGBoost.COMPUTER SYSTEMS APPLICATIONS,2022,31(9):376-381
李莉,谢超,吴迪.基于DeepFM和XGBoost融合模型的静脉血栓预测.计算机系统应用,2022,31(9):376-381
LI Li,XIE Chao,WU Di.Prediction of Venous Thrombosis Based on Fusion Model of DeepFM and XGBoost.COMPUTER SYSTEMS APPLICATIONS,2022,31(9):376-381
