Cargando…

A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants

Structural magnetic resonance imaging studies have shown that brain anatomical abnormalities are associated with cognitive deficits in preterm infants. Brain maturation and geometric features can be used with machine learning models for predicting later neurodevelopmental deficits. However, traditio...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Zhiyuan, Li, Hailong, Braimah, Adebayo, Dillman, Jonathan R., Parikh, Nehal A., He, Lili
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9483989/
https://www.ncbi.nlm.nih.gov/pubmed/35850161
http://dx.doi.org/10.1016/j.neuroimage.2022.119484
_version_ 1784791790621032448
author Li, Zhiyuan
Li, Hailong
Braimah, Adebayo
Dillman, Jonathan R.
Parikh, Nehal A.
He, Lili
author_facet Li, Zhiyuan
Li, Hailong
Braimah, Adebayo
Dillman, Jonathan R.
Parikh, Nehal A.
He, Lili
author_sort Li, Zhiyuan
collection PubMed
description Structural magnetic resonance imaging studies have shown that brain anatomical abnormalities are associated with cognitive deficits in preterm infants. Brain maturation and geometric features can be used with machine learning models for predicting later neurodevelopmental deficits. However, traditional machine learning models would suffer from a large feature-to-instance ratio (i.e., a large number of features but a small number of instances/samples). Ensemble learning is a paradigm that strategically generates and integrates a library of machine learning classifiers and has been successfully used on a wide variety of predictive modeling problems to boost model performance. Attribute (i.e., feature) bagging method is the most commonly used feature partitioning scheme, which randomly and repeatedly draws feature subsets from the entire feature set. Although attribute bagging method can effectively reduce feature dimensionality to handle the large feature-to-instance ratio, it lacks consideration of domain knowledge and latent relationship among features. In this study, we proposed a novel Ontology-guided Attribute Partitioning (OAP) method to better draw feature subsets by considering the domain-specific relationship among features. With the better-partitioned feature subsets, we developed an ensemble learning framework, which is referred to as OAP-Ensemble Learning (OAP-EL). We applied the OAP-EL to predict cognitive deficits at 2 years of age using quantitative brain maturation and geometric features obtained at term equivalent age in very preterm infants. We demonstrated that the proposed OAP-EL approach significantly outperformed the peer ensemble learning and traditional machine learning approaches.
format Online
Article
Text
id pubmed-9483989
institution National Center for Biotechnology Information
language English
publishDate 2022
record_format MEDLINE/PubMed
spelling pubmed-94839892022-10-15 A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants Li, Zhiyuan Li, Hailong Braimah, Adebayo Dillman, Jonathan R. Parikh, Nehal A. He, Lili Neuroimage Article Structural magnetic resonance imaging studies have shown that brain anatomical abnormalities are associated with cognitive deficits in preterm infants. Brain maturation and geometric features can be used with machine learning models for predicting later neurodevelopmental deficits. However, traditional machine learning models would suffer from a large feature-to-instance ratio (i.e., a large number of features but a small number of instances/samples). Ensemble learning is a paradigm that strategically generates and integrates a library of machine learning classifiers and has been successfully used on a wide variety of predictive modeling problems to boost model performance. Attribute (i.e., feature) bagging method is the most commonly used feature partitioning scheme, which randomly and repeatedly draws feature subsets from the entire feature set. Although attribute bagging method can effectively reduce feature dimensionality to handle the large feature-to-instance ratio, it lacks consideration of domain knowledge and latent relationship among features. In this study, we proposed a novel Ontology-guided Attribute Partitioning (OAP) method to better draw feature subsets by considering the domain-specific relationship among features. With the better-partitioned feature subsets, we developed an ensemble learning framework, which is referred to as OAP-Ensemble Learning (OAP-EL). We applied the OAP-EL to predict cognitive deficits at 2 years of age using quantitative brain maturation and geometric features obtained at term equivalent age in very preterm infants. We demonstrated that the proposed OAP-EL approach significantly outperformed the peer ensemble learning and traditional machine learning approaches. 2022-10-15 2022-07-15 /pmc/articles/PMC9483989/ /pubmed/35850161 http://dx.doi.org/10.1016/j.neuroimage.2022.119484 Text en https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/ (https://creativecommons.org/licenses/by-nc-nd/4.0/) )
spellingShingle Article
Li, Zhiyuan
Li, Hailong
Braimah, Adebayo
Dillman, Jonathan R.
Parikh, Nehal A.
He, Lili
A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants
title A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants
title_full A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants
title_fullStr A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants
title_full_unstemmed A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants
title_short A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants
title_sort novel ontology-guided attribute partitioning ensemble learning model for early prediction of cognitive deficits using quantitative structural mri in very preterm infants
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9483989/
https://www.ncbi.nlm.nih.gov/pubmed/35850161
http://dx.doi.org/10.1016/j.neuroimage.2022.119484
work_keys_str_mv AT lizhiyuan anovelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT lihailong anovelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT braimahadebayo anovelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT dillmanjonathanr anovelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT parikhnehala anovelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT helili anovelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT lizhiyuan novelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT lihailong novelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT braimahadebayo novelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT dillmanjonathanr novelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT parikhnehala novelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants
AT helili novelontologyguidedattributepartitioningensemblelearningmodelforearlypredictionofcognitivedeficitsusingquantitativestructuralmriinverypreterminfants