Random forest prediction method for endometrial cancer postoperative concurrent lower limb deep venous thrombosis

• Main Authors: WANG DONGHONG, XIANG XIAORONG, YANG XU, LIU JUN, XIE QIAN, CHEN YU, GUO MIN, HU XINGXU, MENG ZEYU, WANG QIAN, TIAN KUNMING, XIA QIAN
• Format: Patent
• Language: Chinese; English
• Published: 23.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention discloses a random forest prediction method for concurrent lower limb deep venous thrombosis after comprehensive stage operation of endometrial cancer. The method comprises the following steps: acquiring clinical data of endometrial cancer patients complicated with lower limb deep venous thrombosis after operation; carrying out feature screening by adopting single-factor and multi-factor analysis; and according to the screened features, adopting a random forest model in machine learning to predict whether the endometrial adenocarcinoma postoperation is concurrent with lower limb deep vein thrombosis, and outputting the result. Based on a machine learning method, the relationship model between the model and thrombus occurrence is established to effectively predict the risk of thrombus occurrence of the patient, so that the burden of doctors is relieved, and the diagnosis efficiency is improved. 本发明公开子宫内膜癌全面分期术后并发下肢深静脉血栓的随机森林预测方法。方法包括步骤：获取子宫内膜癌患者术后并发下肢深静脉血栓患者的临床资料；采用单因素及多因素分析进行特征筛选；根据筛选后的特征采用机器学习中