首页|机器学习算法在静脉血栓栓塞症防治中的研究进展

机器学习算法在静脉血栓栓塞症防治中的研究进展

扫码查看
原文链接
  • 万方数据
机器学习(ML)作为人工智能的重要分支，现已广泛应用于疾病诊断和评估。静脉血栓栓塞症(VTE)是一种常见的血栓性疾病，临床诊疗过程需要精确高效的评估策略。随着医工交叉逐渐深入和ML方法学的不断优化，在VTE预防诊治领域，ML发挥着越来越重要的作用，相关研究取得显著进展。ML可协助识别VTE的风险因素，建立针对性的风险预测模型。通过对多模态数据的整合，ML可辅助医生快速准确地进行VTE诊断和严重程度评价。在VTE治疗领域，ML可协助制定抗凝药物、剂量和疗程等临床决策，同时预测药物相关不良反应尤其是出血风险。另外，ML也可辅助新药的研发，通过探讨VTE的发病机制从而寻找干预靶点。 As an important branch of artificial intelligence, machine learning (ML) has been widely used in disease diagnosis and evaluation.Venous thromboembolism (VTE) is a common thrombotic disease, which requires accurate and efficient assessment strategies in clinical settings.With the gradual deepening of medical and engineering crossover and the continuous optimization of ML methodology, ML plays an increasingly important role in the prevention and treatment of VTE.Meanwhile, significant progresses have been made on relevant research.ML can help identify the risk factors for VTE and establish a targeted risk prediction model.Through the integration of multi-modality data, ML can assist clinicians to quickly and accurately diagnose and evaluate the severity of VTE.In the field of VTE treatment, ML can assist in making clinical decisions like the use of anticoagulant drugs, dosages and course of treatment, and predicting drug-related adverse effects, especially the risk of bleeding.In addition, ML can also assist in the development of new drugs by exploring the pathogenesis of VTE to find intervention targets.
Research progress of machine learning algorithm in prevention, diagnosis and treatment of venous thromboembolism
As an important branch of artificial intelligence, machine learning (ML) has been widely used in disease diagnosis and evaluation.Venous thromboembolism (VTE) is a common thrombotic disease, which requires accurate and efficient assessment strategies in clinical settings.With the gradual deepening of medical and engineering crossover and the continuous optimization of ML methodology, ML plays an increasingly important role in the prevention and treatment of VTE.Meanwhile, significant progresses have been made on relevant research.ML can help identify the risk factors for VTE and establish a targeted risk prediction model.Through the integration of multi-modality data, ML can assist clinicians to quickly and accurately diagnose and evaluate the severity of VTE.In the field of VTE treatment, ML can assist in making clinical decisions like the use of anticoagulant drugs, dosages and course of treatment, and predicting drug-related adverse effects, especially the risk of bleeding.In addition, ML can also assist in the development of new drugs by exploring the pathogenesis of VTE to find intervention targets.

Venous thromboembolismArtificial intelligenceMachine learning

席霖枫、杨浩宇、刘敏、翟振国、王辰、段思琦

展开 >

首都医科大学中日友好临床医学院，北京　100069

北京大学中日友好临床医学院，北京　100191

中日友好医院放射诊断科，北京　100029

国家呼吸医学中心　呼吸和共病全国重点实验室　国家呼吸疾病临床研究中心　中国医学科学院呼吸病学研究院　中日友好医院呼吸与危重症医学科，北京　100029

展开 >

静脉血栓栓塞 人工智能 机器学习

国家自然科学基金中国医学科学院医学与健康科技创新工程项目中国医学科学院医学与健康科技创新工程项目中国医学科学院医学与健康科技创新工程项目中日友好医院高水平医院临床业务费专项临床研究项目中日友好医院菁英计划人才培育工程

822720812021-I2M-1-0492021-I2M-1-0612022-I2M-C&T-B-1092022-NHLHCRF-LX-01ZRJY2021-BJ02

2024

10.3760/cma.j.cn131368-20231010-00230

国际呼吸杂志
中华医学会 河北医科大学

国际呼吸杂志

CSTPCD
影响因子：0.55
ISSN：1673-436X
年,卷(期)：2024.44(1)
  • 39