An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders
Abstract Background The analysis of health and medical data is crucial for improving the diagnosis precision, treatments and prevention. In this field, machine learning techniques play a key role. However, the amount of health data acquired from digital machines has high dimensionality and not all d...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2019-10-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12859-019-3027-7 |
id |
doaj-5fa57f4d30e740a5bf809be4ccaaf250 |
---|---|
record_format |
Article |
spelling |
doaj-5fa57f4d30e740a5bf809be4ccaaf2502020-11-25T03:36:40ZengBMCBMC Bioinformatics1471-21052019-10-0120111210.1186/s12859-019-3027-7An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disordersJosefa Díaz Álvarez0Jordi A. Matias-Guiu1María Nieves Cabrera-Martín2José L. Risco-Martín3José L. Ayala4Dep. of Computer Architecture and Communications, Universidad de ExtremaduraDep. of Neurology, Hospital Clinico San Carlos, San Carlos Research Health Institute (IdISSC), Universidad ComplutenseDep. of Neurology, Hospital Clinico San Carlos, San Carlos Research Health Institute (IdISSC), Universidad ComplutenseDep. of Computer Architecture and Automation, Universidad ComplutenseDep. of Computer Architecture and Automation, Universidad ComplutenseAbstract Background The analysis of health and medical data is crucial for improving the diagnosis precision, treatments and prevention. In this field, machine learning techniques play a key role. However, the amount of health data acquired from digital machines has high dimensionality and not all data acquired from digital machines are relevant for a particular disease. Primary Progressive Aphasia (PPA) is a neurodegenerative syndrome including several specific diseases, and it is a good model to implement machine learning analyses. In this work, we applied five feature selection algorithms to identify the set of relevant features from 18F-fluorodeoxyglucose positron emission tomography images of the main areas affected by PPA from patient records. On the other hand, we carried out classification and clustering algorithms before and after the feature selection process to contrast both results with those obtained in a previous work. We aimed to find the best classifier and the more relevant features from the WEKA tool to propose further a framework for automatic help on diagnosis. Dataset contains data from 150 FDG-PET imaging studies of 91 patients with a clinic prognosis of PPA, which were examined twice, and 28 controls. Our method comprises six different stages: (i) feature extraction, (ii) expertise knowledge supervision (iii) classification process, (iv) comparing classification results for feature selection, (v) clustering process after feature selection, and (vi) comparing clustering results with those obtained in a previous work. Results Experimental tests confirmed clustering results from a previous work. Although classification results for some algorithms are not decisive for reducing features precisely, Principal Components Analisys (PCA) results exhibited similar or even better performances when compared to those obtained with all features. Conclusions Although reducing the dimensionality does not means a general improvement, the set of features is almost halved and results are better or quite similar. Finally, it is interesting how these results expose a finer grain classification of patients according to the neuroanatomy of their disease.http://link.springer.com/article/10.1186/s12859-019-3027-7Machine learning primary progressive aphasiaSupervised algorithmUnsupervised algorithmClustering Analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Josefa Díaz Álvarez Jordi A. Matias-Guiu María Nieves Cabrera-Martín José L. Risco-Martín José L. Ayala |
spellingShingle |
Josefa Díaz Álvarez Jordi A. Matias-Guiu María Nieves Cabrera-Martín José L. Risco-Martín José L. Ayala An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders BMC Bioinformatics Machine learning primary progressive aphasia Supervised algorithm Unsupervised algorithm Clustering Analysis |
author_facet |
Josefa Díaz Álvarez Jordi A. Matias-Guiu María Nieves Cabrera-Martín José L. Risco-Martín José L. Ayala |
author_sort |
Josefa Díaz Álvarez |
title |
An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders |
title_short |
An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders |
title_full |
An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders |
title_fullStr |
An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders |
title_full_unstemmed |
An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders |
title_sort |
application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders |
publisher |
BMC |
series |
BMC Bioinformatics |
issn |
1471-2105 |
publishDate |
2019-10-01 |
description |
Abstract Background The analysis of health and medical data is crucial for improving the diagnosis precision, treatments and prevention. In this field, machine learning techniques play a key role. However, the amount of health data acquired from digital machines has high dimensionality and not all data acquired from digital machines are relevant for a particular disease. Primary Progressive Aphasia (PPA) is a neurodegenerative syndrome including several specific diseases, and it is a good model to implement machine learning analyses. In this work, we applied five feature selection algorithms to identify the set of relevant features from 18F-fluorodeoxyglucose positron emission tomography images of the main areas affected by PPA from patient records. On the other hand, we carried out classification and clustering algorithms before and after the feature selection process to contrast both results with those obtained in a previous work. We aimed to find the best classifier and the more relevant features from the WEKA tool to propose further a framework for automatic help on diagnosis. Dataset contains data from 150 FDG-PET imaging studies of 91 patients with a clinic prognosis of PPA, which were examined twice, and 28 controls. Our method comprises six different stages: (i) feature extraction, (ii) expertise knowledge supervision (iii) classification process, (iv) comparing classification results for feature selection, (v) clustering process after feature selection, and (vi) comparing clustering results with those obtained in a previous work. Results Experimental tests confirmed clustering results from a previous work. Although classification results for some algorithms are not decisive for reducing features precisely, Principal Components Analisys (PCA) results exhibited similar or even better performances when compared to those obtained with all features. Conclusions Although reducing the dimensionality does not means a general improvement, the set of features is almost halved and results are better or quite similar. Finally, it is interesting how these results expose a finer grain classification of patients according to the neuroanatomy of their disease. |
topic |
Machine learning primary progressive aphasia Supervised algorithm Unsupervised algorithm Clustering Analysis |
url |
http://link.springer.com/article/10.1186/s12859-019-3027-7 |
work_keys_str_mv |
AT josefadiazalvarez anapplicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders AT jordiamatiasguiu anapplicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders AT marianievescabreramartin anapplicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders AT joselriscomartin anapplicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders AT joselayala anapplicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders AT josefadiazalvarez applicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders AT jordiamatiasguiu applicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders AT marianievescabreramartin applicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders AT joselriscomartin applicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders AT joselayala applicationofmachinelearningwithfeatureselectiontoimprovediagnosisandclassificationofneurodegenerativedisorders |
_version_ |
1724548734342135808 |