Machine learning algorithms and forced oscillation measurements to categorise the airway obstruction severity in chronic obstructive pulmonary disease

被引:49
作者
Amaral, Jorge L. M.
Lopes, Agnaldo J. [1 ]
Faria, Alvaro C. D. [2 ,3 ]
Melo, Pedro L. [2 ,3 ]
机构
[1] Pedro Ernesto Univ Hosp, Pulm Funct Lab, Rio De Janeiro, Brazil
[2] Univ Estado Rio De Janeiro, Inst Biol Roberto Alcantara Gomes, Biomed Instrumentat Lab, Rio De Janeiro, Brazil
[3] Univ Estado Rio De Janeiro, Inst Biol Roberto Alcantara Gomes, Lab Clin & Expt Res Vasc Biol BioVasc, Rio De Janeiro, Brazil
关键词
Clinical decision support; Classification; Artificial intelligence; Airway obstruction severity; Forced oscillation technique; Chronic obstructive pulmonary disease; SUPPORT VECTOR MACHINES; RESPIRATORY INPUT; IMPEDANCE; COPD; RECOGNITION; MECHANICS; CLASSIFIERS; DIAGNOSIS; FUTURE;
D O I
10.1016/j.cmpb.2014.11.002
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The purpose of this study was to develop automatic classifiers to simplify the clinical use and increase the accuracy of the forced oscillation technique (FOT) in the categorisation of airway obstruction level in patients with chronic obstructive pulmonary disease (COPD). The data consisted of FOT parameters obtained from 168 volunteers (42 healthy and 126 COPD subjects with four different levels of obstruction). The first part of this study showed that FOT parameters do not provide adequate accuracy in identifying COPD subjects in the first levels of obstruction, as well as in discriminating between close levels of obstruction. In the second part of this study, different supervised machine learning (ML) techniques were investigated, including k-nearest neighbour (KNN), random forest (RF) and support vector machines with linear (SVML) and radial basis function kernels (SVMR). These algorithms were applied only in situations where high categorisation accuracy [area under the Receiver Operating Characteristic curve (AUC) >= 0.9] was not achieved with the FOT parameter alone. It was observed that KNN and RF classifiers improved categorisation accuracy. Notably, in four of the six cases studied, an AUC >= 0.9 was achieved. Even in situations where an AUC >= 0.9 was not achieved, there was a significant improvement in categorisation performance (AUC >= 0.83). In conclusion, machine learning classifiers can help in the categorisation of COPD airway obstruction. They can assist clinicians in tracking disease progression, evaluating the risk of future disease exacerbations and guiding therapy. (C) 2014 Elsevier Ireland Ltd. All rights reserved.
引用
收藏
页码:186 / 197
页数:12
相关论文
共 58 条
[1]   An improved method of early diagnosis of smoking-induced respiratory changes using machine learning algorithms [J].
Amaral, Jorge L. M. ;
Lopes, Agnaldo J. ;
Jansen, Jose M. ;
Faria, Alvaro C. D. ;
Melo, Pedro L. .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2013, 112 (03) :441-454
[2]   Machine learning algorithms and forced oscillation measurements applied to the automatic identification of chronic obstructive pulmonary disease [J].
Amaral, Jorge L. M. ;
Lopes, Agnaldo J. ;
Jansen, Jose M. ;
Faria, Alvaro C. D. ;
Melo, Pedro L. .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2012, 105 (03) :183-193
[3]   Automatic Identification of Chronic Obstructive Pulmonary Disease Based on Forced Oscillation Measurements and Artificial Neural Networks [J].
Amaral, Jorge L. M. ;
Faria, Alvaro C. D. ;
Lopes, Agnaldo J. ;
Jansen, Jose M. ;
Melo, Pedro L. .
2010 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2010, :1394-1397
[4]   Shape quantization and recognition with randomized trees [J].
Amit, Y ;
Geman, D .
NEURAL COMPUTATION, 1997, 9 (07) :1545-1588
[5]  
[Anonymous], 2013, GLOBAL STRATEGY DIAG
[6]  
[Anonymous], PRTOOLS4 1 MATLAB TO
[7]  
[Anonymous], ADV COMPUTER VISION
[8]  
[Anonymous], PATTERN RECOGNIT LET
[9]  
[Anonymous], BIOMEDICAL ENG TECHN
[10]  
[Anonymous], 2000, The Nature of Statistical Learning Theory