A machine learning model for diagnosing acute pulmonary embolism and comparison with Wells score,revised Geneva score,and Years algorithm
A machine learning model for diagnosing acute pulmonary embolism and comparison with Wells score, revised Geneva score, and Years algorithm作者机构:Capital Medical UniversityBeijing 100069China National Center for Respiratory MedicineState Key Laboratory of Respiratory Health and MultimorbidityNational Clinical Research Center for Respiratory DiseasesInstitute of Respiratory MedicineChinese Academy of Medical SciencesDepartment of Pulmonary and Critical Care MedicineCenter of Respiratory MedicineChina-Japan Friendship HospitalBeijing 100029China Institute of Advanced ResearchInfervision Medical Technology Co.Ltd.Beijing 100025China Department of RadiologyChina-Japan Friendship HospitalBeijing 100029China Chinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100730China Department of RadiologyPeking University China-Japan Friendship School of Clinical MedicineBeijing 100191China
出 版 物:《Chinese Medical Journal》 (中华医学杂志(英文版))
年 卷 期:2024年第137卷第6期
页 面:676-682页
核心收录:
学科分类:12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 1002[医学-临床医学] 081104[工学-模式识别与智能系统] 08[工学] 100201[医学-内科学(含:心血管病、血液病、呼吸系病、消化系病、内分泌与代谢病、肾病、风湿病、传染病)] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术(可授工学、理学学位)] 10[医学]
基 金:supported by grants from the Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences(No.2021-I2M-1-049) the Elite Medical Professionals Project of China-Japan Friendship Hospital(No.ZRJY2021-BJ02) the National High Level Hospital Clinical Research Funding(No.2022-NHLHCRF-LX-01)
主 题:Acute pulmonary embolism Machine learning Wells score Revised Geneva score Years algorithm
摘 要:Background:Acute pulmonary embolism(APE)is a fatal cardiovascular disease,yet missed diagnosis and misdiagnosis often occur due to non-specific symptoms and signs.A simple,objective technique will help clinicians make a quick and precise *** population studies,machine learning(ML)plays a critical role in characterizing cardiovascular risks,predicting outcomes,and identifying *** work sought to develop an ML model for helping APE diagnosis and compare it against current clinical probability assessment ***:This is a single-center retrospective *** with suspected APE were continuously enrolled and randomly divided into two groups including training and testing sets.A total of 8 ML models,including random forest(RF),Naïve Bayes,decision tree,K-nearest neighbors,logistic regression,multi-layer perceptron,support vector machine,and gradient boosting decision tree were developed based on the training set to diagnose ***,the model with the best diagnostic performance was selected and evaluated against the current clinical assessment strategies,including the Wells score,revised Geneva score,and Years ***,the ML model was internally validated to assess the diagnostic performance using receiver operating characteristic(ROC)***:The ML models were constructed using eight clinical features,including D-dimer,cardiac troponin T(cTNT),arterial oxygen saturation,heart rate,chest pain,lower limb pain,hemoptysis,and chronic heart *** eight ML models,the RF model achieved the best performance with the highest area under the curve(AUC)(AUC=0.774).Compared to the current clinical assessment strategies,the RF model outperformed the Wells score(P=0.030)and was not inferior to any other clinical probability assessment *** AUC of the RF model for diagnosing APE onset in internal validation set was ***:Based on RF algorithm,a novel prediction model was finally constructed for AP