Cargando…
A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease
With the advances in machine learning for the diagnosis of Alzheimer’s disease (AD), most studies have focused on either identifying the subject’s status through classification algorithms or on predicting their cognitive scores through regression methods, neglecting the potential association between...
Autores principales: | , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9120529/ https://www.ncbi.nlm.nih.gov/pubmed/35601611 http://dx.doi.org/10.3389/fnagi.2022.810873 |
_version_ | 1784710946355150848 |
---|---|
author | Tabarestani, Solale Eslami, Mohammad Cabrerizo, Mercedes Curiel, Rosie E. Barreto, Armando Rishe, Naphtali Vaillancourt, David DeKosky, Steven T. Loewenstein, David A. Duara, Ranjan Adjouadi, Malek |
author_facet | Tabarestani, Solale Eslami, Mohammad Cabrerizo, Mercedes Curiel, Rosie E. Barreto, Armando Rishe, Naphtali Vaillancourt, David DeKosky, Steven T. Loewenstein, David A. Duara, Ranjan Adjouadi, Malek |
author_sort | Tabarestani, Solale |
collection | PubMed |
description | With the advances in machine learning for the diagnosis of Alzheimer’s disease (AD), most studies have focused on either identifying the subject’s status through classification algorithms or on predicting their cognitive scores through regression methods, neglecting the potential association between these two tasks. Motivated by the need to enhance the prospects for early diagnosis along with the ability to predict future disease states, this study proposes a deep neural network based on modality fusion, kernelization, and tensorization that perform multiclass classification and longitudinal regression simultaneously within a unified multitask framework. This relationship between multiclass classification and longitudinal regression is found to boost the efficacy of the final model in dealing with both tasks. Different multimodality scenarios are investigated, and complementary aspects of the multimodal features are exploited to simultaneously delineate the subject’s label and predict related cognitive scores at future timepoints using baseline data. The main intent in this multitask framework is to consolidate the highest accuracy possible in terms of precision, sensitivity, F1 score, and area under the curve (AUC) in the multiclass classification task while maintaining the highest similarity in the MMSE score as measured through the correlation coefficient and the RMSE for all time points under the prediction task, with both tasks, run simultaneously under the same set of hyperparameters. The overall accuracy for multiclass classification of the proposed KTMnet method is 66.85 ± 3.77. The prediction results show an average RMSE of 2.32 ± 0.52 and a correlation of 0.71 ± 5.98 for predicting MMSE throughout the time points. These results are compared to state-of-the-art techniques reported in the literature. A discovery from the multitasking of this consolidated machine learning framework is that a set of hyperparameters that optimize the prediction results may not necessarily be the same as those that would optimize the multiclass classification. In other words, there is a breakpoint beyond which enhancing further the results of one process could lead to the downgrading in accuracy for the other. |
format | Online Article Text |
id | pubmed-9120529 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-91205292022-05-21 A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease Tabarestani, Solale Eslami, Mohammad Cabrerizo, Mercedes Curiel, Rosie E. Barreto, Armando Rishe, Naphtali Vaillancourt, David DeKosky, Steven T. Loewenstein, David A. Duara, Ranjan Adjouadi, Malek Front Aging Neurosci Neuroscience With the advances in machine learning for the diagnosis of Alzheimer’s disease (AD), most studies have focused on either identifying the subject’s status through classification algorithms or on predicting their cognitive scores through regression methods, neglecting the potential association between these two tasks. Motivated by the need to enhance the prospects for early diagnosis along with the ability to predict future disease states, this study proposes a deep neural network based on modality fusion, kernelization, and tensorization that perform multiclass classification and longitudinal regression simultaneously within a unified multitask framework. This relationship between multiclass classification and longitudinal regression is found to boost the efficacy of the final model in dealing with both tasks. Different multimodality scenarios are investigated, and complementary aspects of the multimodal features are exploited to simultaneously delineate the subject’s label and predict related cognitive scores at future timepoints using baseline data. The main intent in this multitask framework is to consolidate the highest accuracy possible in terms of precision, sensitivity, F1 score, and area under the curve (AUC) in the multiclass classification task while maintaining the highest similarity in the MMSE score as measured through the correlation coefficient and the RMSE for all time points under the prediction task, with both tasks, run simultaneously under the same set of hyperparameters. The overall accuracy for multiclass classification of the proposed KTMnet method is 66.85 ± 3.77. The prediction results show an average RMSE of 2.32 ± 0.52 and a correlation of 0.71 ± 5.98 for predicting MMSE throughout the time points. These results are compared to state-of-the-art techniques reported in the literature. A discovery from the multitasking of this consolidated machine learning framework is that a set of hyperparameters that optimize the prediction results may not necessarily be the same as those that would optimize the multiclass classification. In other words, there is a breakpoint beyond which enhancing further the results of one process could lead to the downgrading in accuracy for the other. Frontiers Media S.A. 2022-05-06 /pmc/articles/PMC9120529/ /pubmed/35601611 http://dx.doi.org/10.3389/fnagi.2022.810873 Text en Copyright © 2022 Tabarestani, Eslami, Cabrerizo, Curiel, Barreto, Rishe, Vaillancourt, DeKosky, Loewenstein, Duara and Adjouadi. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Tabarestani, Solale Eslami, Mohammad Cabrerizo, Mercedes Curiel, Rosie E. Barreto, Armando Rishe, Naphtali Vaillancourt, David DeKosky, Steven T. Loewenstein, David A. Duara, Ranjan Adjouadi, Malek A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease |
title | A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease |
title_full | A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease |
title_fullStr | A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease |
title_full_unstemmed | A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease |
title_short | A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease |
title_sort | tensorized multitask deep learning network for progression prediction of alzheimer’s disease |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9120529/ https://www.ncbi.nlm.nih.gov/pubmed/35601611 http://dx.doi.org/10.3389/fnagi.2022.810873 |
work_keys_str_mv | AT tabarestanisolale atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT eslamimohammad atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT cabrerizomercedes atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT curielrosiee atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT barretoarmando atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT rishenaphtali atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT vaillancourtdavid atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT dekoskystevent atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT loewensteindavida atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT duararanjan atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT adjouadimalek atensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT tabarestanisolale tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT eslamimohammad tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT cabrerizomercedes tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT curielrosiee tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT barretoarmando tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT rishenaphtali tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT vaillancourtdavid tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT dekoskystevent tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT loewensteindavida tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT duararanjan tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease AT adjouadimalek tensorizedmultitaskdeeplearningnetworkforprogressionpredictionofalzheimersdisease |