Toward a diagnostic CART model for Ischemic heart disease and idiopathic dilated cardiomyopathy based on heart rate total variability

被引:9
作者
Accardo, Agostino [1 ]
Restivo, Luca [2 ,3 ]
Ajcevic, Milos [1 ]
Miladinovic, Aleksandar [1 ,4 ]
Iscra, Katerina [1 ]
Silveri, Giulia [1 ]
Merlo, Marco [2 ,3 ]
Sinagra, Gianfranco [2 ,3 ]
机构
[1] Univ Trieste, Dept Engn & Architecture, Trieste, Italy
[2] Azienda Sanitaria Univ Giuliano Isontina ASUGI, Cardiovasc Dept, Trieste, Italy
[3] Univ Trieste, Trieste, Italy
[4] Inst Maternal & Child Hlth IRCCS Burlo Garofolo, Trieste, Italy
关键词
Computer-aided diagnosis; Heart rate variability; Ischemic heart disease; Dilated cardiomyopathy; Interpretable machine learning; ASSOCIATION; SOCIETY; SEX;
D O I
10.1007/s11517-022-02618-9
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Diagnosis of etiology in early-stage ischemic heart disease (IHD) and dilated cardiomyopathy (DCM) patients may be challenging. We aimed at investigating, by means of classification and regression tree (CART) modeling, the predictive power of heart rate variability (HRV) features together with clinical parameters to support the diagnosis in the early stage of IHD and DCM. The study included 263 IHD and 181 DCM patients, as well as 689 healthy subjects. A 24 h Holter monitoring was used and linear and non-linear HRV parameters were extracted considering both normal and ectopic beats (heart rate total variability signal). We used a CART algorithm to produce classification models based on HRV together with relevant clinical (age, sex, and left ventricular ejection fraction, LVEF) features. Among HRV parameters, MeanRR, SDNN, pNN50, LF, LF/HF, LFn, FD, Beta exp were selected by the CART algorithm and included in the produced models. The model based on pNN50, FD, sex, age, and LVEF features presented the highest accuracy (73.3%). The proposed approach based on HRV parameters, age, sex, and LVEF features highlighted the possibility to produce clinically interpretable models capable to differentiate IHD, DCM, and healthy subjects with accuracy which is clinically relevant in first steps of the IHD and DCM diagnostic process.
引用
收藏
页码:2655 / 2663
页数:9
相关论文
共 39 条
[1]   Influence of smoking and other cardiovascular risk factors on heart rate circadian rhythm in normotensive and hypertensive subjects [J].
Accardo, Agostino ;
Silveri, Giulia ;
Ajcevic, Milos ;
Miladinovic, Aleksandar ;
Pascazio, Lorenzo .
PLOS ONE, 2021, 16 (09)
[2]   Influence of ageing on circadian rhythm of heart rate variability in healthy subjects [J].
Accardo, Agostino ;
Merlo, Marco ;
Silveri, Giulia ;
Del Popolo, Lucia ;
Dalla Libera, Luca ;
Restivo, Luca ;
Cinquetti, Martino ;
Cannata, Antonio ;
Sinagra, Gianfranco .
JOURNAL OF CARDIOVASCULAR MEDICINE, 2021, 22 (05) :405-413
[3]   Detection of subjects with ischemic heart disease by using machine learning technique based on heart rate total variability parameters [J].
Accardo, Agostino ;
Silveri, Giulia ;
Merlo, Marco ;
Restivo, Luca ;
Ajcevic, Milos ;
Sinagra, Gianfranco .
PHYSIOLOGICAL MEASUREMENT, 2020, 41 (11)
[4]  
Ahmad MA, 2018, IEEE INT CONF HEALT, P447, DOI [10.1145/3233547.3233667, 10.1109/ICHI.2018.00095]
[5]   RETRACTED: Machine Learning for Ischemic Heart Disease Diagnosis Aided by Evolutionary Computing (Retracted Article) [J].
Alsaffar, Mohammad ;
Alshammari, Abdullah ;
Alshammari, Gharbi ;
Aljaloud, Saud ;
Almurayziq, Tariq S. ;
Abdoon, Fadam Muteb ;
Abebaw, Solomon .
APPLIED BIONICS AND BIOMECHANICS, 2021, 2021
[6]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[7]  
Camm AJ, 1996, CIRCULATION, V93, P1043
[8]  
Cusenza M, 2010, COMPUT CARDIOL CONF, V37, P935
[9]   Machine Learning and the Profession of Medicine [J].
Darcy, Alison M. ;
Louie, Alan K. ;
Roberts, Laura Weiss .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2016, 315 (06) :551-552
[10]   Machine Learning in Medicine [J].
Deo, Rahul C. .
CIRCULATION, 2015, 132 (20) :1920-1930