PMID- 24001924
OWN - NLM
STAT- MEDLINE
DCOM- 20140611
LR  - 20131018
IS  - 1872-7565 (Electronic)
IS  - 0169-2607 (Linking)
VI  - 112
IP  - 3
DP  - 2013 Dec
TI  - An improved method of early diagnosis of smoking-induced respiratory changes 
      using machine learning algorithms.
PG  - 441-54
LID - S0169-2607(13)00280-0 [pii]
LID - 10.1016/j.cmpb.2013.08.004 [doi]
AB  - The purpose of this study was to develop an automatic classifier to increase the 
      accuracy of the forced oscillation technique (FOT) for diagnosing early 
      respiratory abnormalities in smoking patients. The data consisted of FOT 
      parameters obtained from 56 volunteers, 28 healthy and 28 smokers with low 
      tobacco consumption. Many supervised learning techniques were investigated, 
      including logistic linear classifiers, k nearest neighbor (KNN), neural networks 
      and support vector machines (SVM). To evaluate performance, the ROC curve of the 
      most accurate parameter was established as baseline. To determine the best input 
      features and classifier parameters, we used genetic algorithms and a 10-fold 
      cross-validation using the average area under the ROC curve (AUC). In the first 
      experiment, the original FOT parameters were used as input. We observed a 
      significant improvement in accuracy (KNN=0.89 and SVM=0.87) compared with the 
      baseline (0.77). The second experiment performed a feature selection on the 
      original FOT parameters. This selection did not cause any significant improvement 
      in accuracy, but it was useful in identifying more adequate FOT parameters. In 
      the third experiment, we performed a feature selection on the cross products of 
      the FOT parameters. This selection resulted in a further increase in AUC 
      (KNN=SVM=0.91), which allows for high diagnostic accuracy. In conclusion, machine 
      learning classifiers can help identify early smoking-induced respiratory 
      alterations. The use of FOT cross products and the search for the best features 
      and classifier parameters can markedly improve the performance of machine 
      learning classifiers.
CI  - Copyright (c) 2013 Elsevier Ireland Ltd. All rights reserved.
FAU - Amaral, Jorge L M
AU  - Amaral JL
AD  - Department of Electronics and Telecommunications Engineering, State University of 
      Rio de Janeiro, Rio de Janeiro, Brazil.
FAU - Lopes, Agnaldo J
AU  - Lopes AJ
FAU - Jansen, Jose M
AU  - Jansen JM
FAU - Faria, Alvaro C D
AU  - Faria AC
FAU - Melo, Pedro L
AU  - Melo PL
LA  - eng
PT  - Journal Article
DEP - 20130817
PL  - Ireland
TA  - Comput Methods Programs Biomed
JT  - Computer methods and programs in biomedicine
JID - 8506513
SB  - IM
MH  - *Algorithms
MH  - *Artificial Intelligence
MH  - *Early Diagnosis
MH  - Humans
MH  - ROC Curve
MH  - Respiratory System/*physiopathology
MH  - Smoking/*physiopathology
OTO - NOTNLM
OT  - Artificial intelligence
OT  - Chronic obstructive pulmonary disease
OT  - Clinical decision support
OT  - Early diagnosis
OT  - Forced oscillation technique
OT  - Smoking
EDAT- 2013/09/05 06:00
MHDA- 2014/06/12 06:00
CRDT- 2013/09/05 06:00
PHST- 2013/01/17 00:00 [received]
PHST- 2013/07/23 00:00 [revised]
PHST- 2013/08/07 00:00 [accepted]
PHST- 2013/09/05 06:00 [entrez]
PHST- 2013/09/05 06:00 [pubmed]
PHST- 2014/06/12 06:00 [medline]
AID - S0169-2607(13)00280-0 [pii]
AID - 10.1016/j.cmpb.2013.08.004 [doi]
PST - ppublish
SO  - Comput Methods Programs Biomed. 2013 Dec;112(3):441-54. doi: 
      10.1016/j.cmpb.2013.08.004. Epub 2013 Aug 17.