Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive Impairment
ObjectiveAlzheimer’s Disease (AD) is a progressive condition characterized by cognitive decline. AD is often preceded by mild cognitive impairment (MCI), though the diagnosis of both conditions remains a challenge. Early diagnosis of AD, and prediction of MCI progression require data-driven approach...
Main Authors: | , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-05-01
|
Series: | Frontiers in Aging Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnagi.2022.854733/full |
_version_ | 1811292687903490048 |
---|---|
author | Ningxin Dong Changyong Fu Renren Li Wei Zhang Meng Liu Weixin Xiao Hugh M. Taylor Peter J. Nicholas Onur Tanglay Isabella M. Young Karol Z. Osipowicz Michael E. Sughrue Michael E. Sughrue Stephane P. Doyen Yunxia Li |
author_facet | Ningxin Dong Changyong Fu Renren Li Wei Zhang Meng Liu Weixin Xiao Hugh M. Taylor Peter J. Nicholas Onur Tanglay Isabella M. Young Karol Z. Osipowicz Michael E. Sughrue Michael E. Sughrue Stephane P. Doyen Yunxia Li |
author_sort | Ningxin Dong |
collection | DOAJ |
description | ObjectiveAlzheimer’s Disease (AD) is a progressive condition characterized by cognitive decline. AD is often preceded by mild cognitive impairment (MCI), though the diagnosis of both conditions remains a challenge. Early diagnosis of AD, and prediction of MCI progression require data-driven approaches to improve patient selection for treatment. We used a machine learning tool to predict performance in neuropsychological tests in AD and MCI based on functional connectivity using a whole-brain connectome, in an attempt to identify network substrates of cognitive deficits in AD.MethodsNeuropsychological tests, baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI, and diffusion weighted imaging scans were obtained from 149 MCI, and 85 AD patients; and 140 cognitively unimpaired geriatric participants. A novel machine learning tool, Hollow Tree Super (HoTS) was utilized to extract feature importance from each machine learning model to identify brain regions that were associated with deficit and absence of deficit for 11 neuropsychological tests.Results11 models attained an area under the receiver operating curve (AUC-ROC) greater than 0.65, while five models had an AUC-ROC ≥ 0.7. 20 parcels of the Human Connectome Project Multimodal Parcelation Atlas matched to poor performance in at least two neuropsychological tests, while 14 parcels were associated with good performance in at least two tests. At a network level, most parcels predictive of both presence and absence of deficit were affiliated with the Central Executive Network, Default Mode Network, and the Sensorimotor Networks. Segregating predictors by the cognitive domain associated with each test revealed areas of coherent overlap between cognitive domains, with the parcels providing possible markers to screen for cognitive impairment.ConclusionApproaches such as ours which incorporate whole-brain functional connectivity and harness feature importance in machine learning models may aid in identifying diagnostic and therapeutic targets in AD. |
first_indexed | 2024-04-13T04:50:04Z |
format | Article |
id | doaj.art-cc7f13479b7d44e196ffa6b5690db3ee |
institution | Directory Open Access Journal |
issn | 1663-4365 |
language | English |
last_indexed | 2024-04-13T04:50:04Z |
publishDate | 2022-05-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Aging Neuroscience |
spelling | doaj.art-cc7f13479b7d44e196ffa6b5690db3ee2022-12-22T03:01:43ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652022-05-011410.3389/fnagi.2022.854733854733Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive ImpairmentNingxin Dong0Changyong Fu1Renren Li2Wei Zhang3Meng Liu4Weixin Xiao5Hugh M. Taylor6Peter J. Nicholas7Onur Tanglay8Isabella M. Young9Karol Z. Osipowicz10Michael E. Sughrue11Michael E. Sughrue12Stephane P. Doyen13Yunxia Li14Department of Medical Imaging, Tongji Hospital, School of Medicine, Tongji University, Shanghai, ChinaDepartment of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, ChinaDepartment of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, ChinaDepartment of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, ChinaDepartment of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, ChinaDepartment of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, ChinaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaInternational Joint Research Center on Precision Brain Medicine, XD Group Hospital, Xi’an, ChinaOmniscient Neurotechnology, Sydney, NSW, AustraliaDepartment of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, ChinaObjectiveAlzheimer’s Disease (AD) is a progressive condition characterized by cognitive decline. AD is often preceded by mild cognitive impairment (MCI), though the diagnosis of both conditions remains a challenge. Early diagnosis of AD, and prediction of MCI progression require data-driven approaches to improve patient selection for treatment. We used a machine learning tool to predict performance in neuropsychological tests in AD and MCI based on functional connectivity using a whole-brain connectome, in an attempt to identify network substrates of cognitive deficits in AD.MethodsNeuropsychological tests, baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI, and diffusion weighted imaging scans were obtained from 149 MCI, and 85 AD patients; and 140 cognitively unimpaired geriatric participants. A novel machine learning tool, Hollow Tree Super (HoTS) was utilized to extract feature importance from each machine learning model to identify brain regions that were associated with deficit and absence of deficit for 11 neuropsychological tests.Results11 models attained an area under the receiver operating curve (AUC-ROC) greater than 0.65, while five models had an AUC-ROC ≥ 0.7. 20 parcels of the Human Connectome Project Multimodal Parcelation Atlas matched to poor performance in at least two neuropsychological tests, while 14 parcels were associated with good performance in at least two tests. At a network level, most parcels predictive of both presence and absence of deficit were affiliated with the Central Executive Network, Default Mode Network, and the Sensorimotor Networks. Segregating predictors by the cognitive domain associated with each test revealed areas of coherent overlap between cognitive domains, with the parcels providing possible markers to screen for cognitive impairment.ConclusionApproaches such as ours which incorporate whole-brain functional connectivity and harness feature importance in machine learning models may aid in identifying diagnostic and therapeutic targets in AD.https://www.frontiersin.org/articles/10.3389/fnagi.2022.854733/fullcognitive impairmentneuropsychological testsMRIneural networksmachine learningneuroimaging markers |
spellingShingle | Ningxin Dong Changyong Fu Renren Li Wei Zhang Meng Liu Weixin Xiao Hugh M. Taylor Peter J. Nicholas Onur Tanglay Isabella M. Young Karol Z. Osipowicz Michael E. Sughrue Michael E. Sughrue Stephane P. Doyen Yunxia Li Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive Impairment Frontiers in Aging Neuroscience cognitive impairment neuropsychological tests MRI neural networks machine learning neuroimaging markers |
title | Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive Impairment |
title_full | Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive Impairment |
title_fullStr | Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive Impairment |
title_full_unstemmed | Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive Impairment |
title_short | Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive Impairment |
title_sort | machine learning decomposition of the anatomy of neuropsychological deficit in alzheimer s disease and mild cognitive impairment |
topic | cognitive impairment neuropsychological tests MRI neural networks machine learning neuroimaging markers |
url | https://www.frontiersin.org/articles/10.3389/fnagi.2022.854733/full |
work_keys_str_mv | AT ningxindong machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT changyongfu machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT renrenli machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT weizhang machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT mengliu machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT weixinxiao machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT hughmtaylor machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT peterjnicholas machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT onurtanglay machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT isabellamyoung machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT karolzosipowicz machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT michaelesughrue machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT michaelesughrue machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT stephanepdoyen machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment AT yunxiali machinelearningdecompositionoftheanatomyofneuropsychologicaldeficitinalzheimersdiseaseandmildcognitiveimpairment |