摘要
肺栓塞是深静脉血栓形成的一种,主要临床表现为胸痛、呼吸困难、咯血等。发生肺栓塞时,有一个或多个血凝块阻碍血液流向肺部,肺动脉管腔一旦被堵塞,便会直接引起肺循环和呼吸功能障碍,如果是急性重度肺栓塞,有可能在短时间内致死。因此,尽早地发现并诊断肺栓塞,分清危险等级并给予相应的治疗措施尤为重要。机器学习是目前新兴的一个领域,可以从大量的影像学数据中学习并应用于疾病诊断和治疗中。近年来机器学习在肺栓塞中的预测诊断、严重程度评估与现代影像学知识相结合以及疾病预后方面获得快速进展,为临床实践提供了可靠参考。
Pulmonary embolism is a kind of venous thromboembolism,and the main clinical manifestations are chest pain,respiratory distress,haemoptysis,and etc.When pulmonary embolism occurs,one or more blood clots block the blood in the lungs.When pulmonary embolism occurs,one or more blood clots block the blood flow to the lungs.Once the lumen of the pulmonary artery is blocked,it will directly cause pulmonary circulation and respiratory dysfunction,and if it is an acute severe pulmonary embolism,it may cause death in a very short period of time.It may therefore be life-threatening.It is therefore important to detect and diagnose pulmonary embolisms as early as possible,to classify their risk level and to give appropriate treatment.Machine learning is an emerging field that can learn from a large amount of clinical data and be applied to clinical diagnosis and treatment.In this paper,we briefly review the progress of machine learning in predicting the diagnosis of pulmonary embolism,assessing its severity,integrating it with modern imaging knowledge,and its prognosis in recent years,with a view to providing a reference for clinical practice.
作者
徐雪
顾问
XU Xue;GU Wen(Department of Pulmonary and Critical Care Medicine,Xinhua Hospital,Shanghai Jiaotong University School of Medicine,Shanghai 200092,China)
出处
《医学影像学杂志》
2025年第7期149-152,共4页
Journal of Medical Imaging
基金
上海科技发展基金资助项目(编号:22Y11901700)。
关键词
肺栓塞
机器学习
预测模型
预后评估
Pulmonary embolism
Machine learning
Predictive modelling
Prognostic assessment
