Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictability
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.1/12285 |
Resumo: | Background Predicting progression from Mild Cognitive Impairment (MCI) to Alzheimer’s Disease (AD) is an utmost open issue in AD-related research. Neuropsychological assessment has proven to be useful in identifying MCI patients who are likely to convert to dementia. However, the large battery of neuropsychological tests (NPTs) performed in clinical practice and the limited number of training examples are challenge to machine learning when learning prognostic models. In this context, it is paramount to pursue approaches that effectively seek for reduced sets of relevant features. Subsets of NPTs from which prognostic models can be learnt should not only be good predictors, but also stable, promoting generalizable and explainable models. Methods We propose a feature selection (FS) ensemble combining stability and predictability to choose the most relevant NPTs for prognostic prediction in AD. First, we combine the outcome of multiple (filter and embedded) FS methods. Then, we use a wrapper-based approach optimizing both stability and predictability to compute the number of selected features. We use two large prospective studies (ADNI and the Portuguese Cognitive Complaints Cohort, CCC) to evaluate the approach and assess the predictive value of a large number of NPTs. Results The best subsets of features include approximately 30 and 20 (from the original 79 and 40) features, for ADNI and CCC data, respectively, yielding stability above 0.89 and 0.95, and AUC above 0.87 and 0.82. Most NPTs learnt using the proposed feature selection ensemble have been identified in the literature as strong predictors of conversion from MCI to AD. Conclusions The FS ensemble approach was able to 1) identify subsets of stable and relevant predictors from a consensus of multiple FS methods using baseline NPTs and 2) learn reliable prognostic models of conversion from MCI to AD using these subsets of features. The machine learning models learnt from these features outperformed the models trained without FS and achieved competitive results when compared to commonly used FS algorithms. Furthermore, the selected features are derived from a consensus of methods thus being more robust, while releasing users from choosing the most appropriate FS method to be used in their classification task. |
id |
RCAP_f5b4f5a059afcd6f9e875aa1c3fc730d |
---|---|
oai_identifier_str |
oai:sapientia.ualg.pt:10400.1/12285 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictabilityFeature selection;Neuropsychological dataTime windowsMild cognitive impairmentPrognostic predictionAlzheimer's diseaseEnsemble learningBackground Predicting progression from Mild Cognitive Impairment (MCI) to Alzheimer’s Disease (AD) is an utmost open issue in AD-related research. Neuropsychological assessment has proven to be useful in identifying MCI patients who are likely to convert to dementia. However, the large battery of neuropsychological tests (NPTs) performed in clinical practice and the limited number of training examples are challenge to machine learning when learning prognostic models. In this context, it is paramount to pursue approaches that effectively seek for reduced sets of relevant features. Subsets of NPTs from which prognostic models can be learnt should not only be good predictors, but also stable, promoting generalizable and explainable models. Methods We propose a feature selection (FS) ensemble combining stability and predictability to choose the most relevant NPTs for prognostic prediction in AD. First, we combine the outcome of multiple (filter and embedded) FS methods. Then, we use a wrapper-based approach optimizing both stability and predictability to compute the number of selected features. We use two large prospective studies (ADNI and the Portuguese Cognitive Complaints Cohort, CCC) to evaluate the approach and assess the predictive value of a large number of NPTs. Results The best subsets of features include approximately 30 and 20 (from the original 79 and 40) features, for ADNI and CCC data, respectively, yielding stability above 0.89 and 0.95, and AUC above 0.87 and 0.82. Most NPTs learnt using the proposed feature selection ensemble have been identified in the literature as strong predictors of conversion from MCI to AD. Conclusions The FS ensemble approach was able to 1) identify subsets of stable and relevant predictors from a consensus of multiple FS methods using baseline NPTs and 2) learn reliable prognostic models of conversion from MCI to AD using these subsets of features. The machine learning models learnt from these features outperformed the models trained without FS and achieved competitive results when compared to commonly used FS algorithms. Furthermore, the selected features are derived from a consensus of methods thus being more robust, while releasing users from choosing the most appropriate FS method to be used in their classification task.PTDC/EEI-SII/1937/2014; SFRH/BD/95846/2013; SFRH/BD/118872/2016BMCSapientiaPereira, TelmaFerreira, Francisco L.Cardoso, SandraSilva, DinaMendonça, Alexandre deGuerreiro, ManuelaMadeira, Sara C.2019-01-09T12:42:25Z2018-12-192019-01-01T07:33:23Z2018-12-19T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.1/12285engBMC Medical Informatics and Decision Making. 2018 Dec 19;18(1):13710.1186/s12911-018-0710-yinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-24T10:24:14Zoai:sapientia.ualg.pt:10400.1/12285Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:03:38.099730Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictability |
title |
Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictability |
spellingShingle |
Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictability Pereira, Telma Feature selection; Neuropsychological data Time windows Mild cognitive impairment Prognostic prediction Alzheimer's disease Ensemble learning |
title_short |
Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictability |
title_full |
Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictability |
title_fullStr |
Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictability |
title_full_unstemmed |
Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictability |
title_sort |
Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer’s disease: a feature selection ensemble combining stability and predictability |
author |
Pereira, Telma |
author_facet |
Pereira, Telma Ferreira, Francisco L. Cardoso, Sandra Silva, Dina Mendonça, Alexandre de Guerreiro, Manuela Madeira, Sara C. |
author_role |
author |
author2 |
Ferreira, Francisco L. Cardoso, Sandra Silva, Dina Mendonça, Alexandre de Guerreiro, Manuela Madeira, Sara C. |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
Sapientia |
dc.contributor.author.fl_str_mv |
Pereira, Telma Ferreira, Francisco L. Cardoso, Sandra Silva, Dina Mendonça, Alexandre de Guerreiro, Manuela Madeira, Sara C. |
dc.subject.por.fl_str_mv |
Feature selection; Neuropsychological data Time windows Mild cognitive impairment Prognostic prediction Alzheimer's disease Ensemble learning |
topic |
Feature selection; Neuropsychological data Time windows Mild cognitive impairment Prognostic prediction Alzheimer's disease Ensemble learning |
description |
Background Predicting progression from Mild Cognitive Impairment (MCI) to Alzheimer’s Disease (AD) is an utmost open issue in AD-related research. Neuropsychological assessment has proven to be useful in identifying MCI patients who are likely to convert to dementia. However, the large battery of neuropsychological tests (NPTs) performed in clinical practice and the limited number of training examples are challenge to machine learning when learning prognostic models. In this context, it is paramount to pursue approaches that effectively seek for reduced sets of relevant features. Subsets of NPTs from which prognostic models can be learnt should not only be good predictors, but also stable, promoting generalizable and explainable models. Methods We propose a feature selection (FS) ensemble combining stability and predictability to choose the most relevant NPTs for prognostic prediction in AD. First, we combine the outcome of multiple (filter and embedded) FS methods. Then, we use a wrapper-based approach optimizing both stability and predictability to compute the number of selected features. We use two large prospective studies (ADNI and the Portuguese Cognitive Complaints Cohort, CCC) to evaluate the approach and assess the predictive value of a large number of NPTs. Results The best subsets of features include approximately 30 and 20 (from the original 79 and 40) features, for ADNI and CCC data, respectively, yielding stability above 0.89 and 0.95, and AUC above 0.87 and 0.82. Most NPTs learnt using the proposed feature selection ensemble have been identified in the literature as strong predictors of conversion from MCI to AD. Conclusions The FS ensemble approach was able to 1) identify subsets of stable and relevant predictors from a consensus of multiple FS methods using baseline NPTs and 2) learn reliable prognostic models of conversion from MCI to AD using these subsets of features. The machine learning models learnt from these features outperformed the models trained without FS and achieved competitive results when compared to commonly used FS algorithms. Furthermore, the selected features are derived from a consensus of methods thus being more robust, while releasing users from choosing the most appropriate FS method to be used in their classification task. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-12-19 2018-12-19T00:00:00Z 2019-01-09T12:42:25Z 2019-01-01T07:33:23Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.1/12285 |
url |
http://hdl.handle.net/10400.1/12285 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
BMC Medical Informatics and Decision Making. 2018 Dec 19;18(1):137 10.1186/s12911-018-0710-y |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
BMC |
publisher.none.fl_str_mv |
BMC |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133270942679040 |