A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer’s disease
Early detection of Alzheimer’s disease (AD) during the Mild Cognitive Impairment (MCI) stage could enable effective intervention to slow down disease progression. Computer-aided diagnosis of AD relies on a sufficient amount of biomarker data. When this requirement is not fulfilled, transfer learning...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Aging Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnagi.2022.966883/full |
| _version_ | 1817981646320697344 |
|---|---|
| author | Mehdi Shojaie Mercedes Cabrerizo Steven T. DeKosky Steven T. DeKosky David E. Vaillancourt David E. Vaillancourt David E. Vaillancourt David Loewenstein David Loewenstein Ranjan Duara Ranjan Duara Malek Adjouadi Malek Adjouadi |
| author_facet | Mehdi Shojaie Mercedes Cabrerizo Steven T. DeKosky Steven T. DeKosky David E. Vaillancourt David E. Vaillancourt David E. Vaillancourt David Loewenstein David Loewenstein Ranjan Duara Ranjan Duara Malek Adjouadi Malek Adjouadi |
| author_sort | Mehdi Shojaie |
| collection | DOAJ |
| description | Early detection of Alzheimer’s disease (AD) during the Mild Cognitive Impairment (MCI) stage could enable effective intervention to slow down disease progression. Computer-aided diagnosis of AD relies on a sufficient amount of biomarker data. When this requirement is not fulfilled, transfer learning can be used to transfer knowledge from a source domain with more amount of labeled data than available in the desired target domain. In this study, an instance-based transfer learning framework is presented based on the gradient boosting machine (GBM). In GBM, a sequence of base learners is built, and each learner focuses on the errors (residuals) of the previous learner. In our transfer learning version of GBM (TrGB), a weighting mechanism based on the residuals of the base learners is defined for the source instances. Consequently, instances with different distribution than the target data will have a lower impact on the target learner. The proposed weighting scheme aims to transfer as much information as possible from the source domain while avoiding negative transfer. The target data in this study was obtained from the Mount Sinai dataset which is collected and processed in a collaborative 5-year project at the Mount Sinai Medical Center. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset was used as the source domain. The experimental results showed that the proposed TrGB algorithm could improve the classification accuracy by 1.5 and 4.5% for CN vs. MCI and multiclass classification, respectively, as compared to the conventional methods. Also, using the TrGB model and transferred knowledge from the CN vs. AD classification of the source domain, the average score of early MCI vs. late MCI classification improved by 5%. |
| first_indexed | 2024-04-13T23:08:56Z |
| format | Article |
| id | doaj.art-c9fa70936ab14e7b870d1777f626fb10 |
| institution | Directory Open Access Journal |
| issn | 1663-4365 |
| language | English |
| last_indexed | 2024-04-13T23:08:56Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Aging Neuroscience |
| spelling | doaj.art-c9fa70936ab14e7b870d1777f626fb102022-12-22T02:25:37ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652022-10-011410.3389/fnagi.2022.966883966883A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer’s diseaseMehdi Shojaie0Mercedes Cabrerizo1Steven T. DeKosky2Steven T. DeKosky3David E. Vaillancourt4David E. Vaillancourt5David E. Vaillancourt6David Loewenstein7David Loewenstein8Ranjan Duara9Ranjan Duara10Malek Adjouadi11Malek Adjouadi12Department of Electrical and Computer Engineering, Center for Advanced Technology and Education, Florida International University, Miami, FL, United StatesDepartment of Electrical and Computer Engineering, Center for Advanced Technology and Education, Florida International University, Miami, FL, United StatesFixel Institute for Neurological Disorders, University of Florida, Gainesville, FL, United States1Florida ADRC (Alzheimer’s Disease Research Center), University of Florida, Gainesville, FL, United StatesFixel Institute for Neurological Disorders, University of Florida, Gainesville, FL, United States1Florida ADRC (Alzheimer’s Disease Research Center), University of Florida, Gainesville, FL, United StatesDepartment of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, United States1Florida ADRC (Alzheimer’s Disease Research Center), University of Florida, Gainesville, FL, United StatesCenter for Cognitive Neuroscience and Aging, Miller School of Medicine, University of Miami, Miami, FL, United States1Florida ADRC (Alzheimer’s Disease Research Center), University of Florida, Gainesville, FL, United StatesWien Center for Alzheimer’s Disease & Memory Disorders, Mount Sinai Medical Center, Miami, FL, United StatesDepartment of Electrical and Computer Engineering, Center for Advanced Technology and Education, Florida International University, Miami, FL, United States1Florida ADRC (Alzheimer’s Disease Research Center), University of Florida, Gainesville, FL, United StatesEarly detection of Alzheimer’s disease (AD) during the Mild Cognitive Impairment (MCI) stage could enable effective intervention to slow down disease progression. Computer-aided diagnosis of AD relies on a sufficient amount of biomarker data. When this requirement is not fulfilled, transfer learning can be used to transfer knowledge from a source domain with more amount of labeled data than available in the desired target domain. In this study, an instance-based transfer learning framework is presented based on the gradient boosting machine (GBM). In GBM, a sequence of base learners is built, and each learner focuses on the errors (residuals) of the previous learner. In our transfer learning version of GBM (TrGB), a weighting mechanism based on the residuals of the base learners is defined for the source instances. Consequently, instances with different distribution than the target data will have a lower impact on the target learner. The proposed weighting scheme aims to transfer as much information as possible from the source domain while avoiding negative transfer. The target data in this study was obtained from the Mount Sinai dataset which is collected and processed in a collaborative 5-year project at the Mount Sinai Medical Center. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset was used as the source domain. The experimental results showed that the proposed TrGB algorithm could improve the classification accuracy by 1.5 and 4.5% for CN vs. MCI and multiclass classification, respectively, as compared to the conventional methods. Also, using the TrGB model and transferred knowledge from the CN vs. AD classification of the source domain, the average score of early MCI vs. late MCI classification improved by 5%.https://www.frontiersin.org/articles/10.3389/fnagi.2022.966883/fullAlzheimer’s diseasetransfer learningmachine-learningclassificationgradient boosting machinedata distribution |
| spellingShingle | Mehdi Shojaie Mercedes Cabrerizo Steven T. DeKosky Steven T. DeKosky David E. Vaillancourt David E. Vaillancourt David E. Vaillancourt David Loewenstein David Loewenstein Ranjan Duara Ranjan Duara Malek Adjouadi Malek Adjouadi A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer’s disease Frontiers in Aging Neuroscience Alzheimer’s disease transfer learning machine-learning classification gradient boosting machine data distribution |
| title | A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer’s disease |
| title_full | A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer’s disease |
| title_fullStr | A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer’s disease |
| title_full_unstemmed | A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer’s disease |
| title_short | A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer’s disease |
| title_sort | transfer learning approach based on gradient boosting machine for diagnosis of alzheimer s disease |
| topic | Alzheimer’s disease transfer learning machine-learning classification gradient boosting machine data distribution |
| url | https://www.frontiersin.org/articles/10.3389/fnagi.2022.966883/full |
| work_keys_str_mv | AT mehdishojaie atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT mercedescabrerizo atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT steventdekosky atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT steventdekosky atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidevaillancourt atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidevaillancourt atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidevaillancourt atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidloewenstein atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidloewenstein atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT ranjanduara atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT ranjanduara atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT malekadjouadi atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT malekadjouadi atransferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT mehdishojaie transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT mercedescabrerizo transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT steventdekosky transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT steventdekosky transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidevaillancourt transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidevaillancourt transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidevaillancourt transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidloewenstein transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT davidloewenstein transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT ranjanduara transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT ranjanduara transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT malekadjouadi transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease AT malekadjouadi transferlearningapproachbasedongradientboostingmachinefordiagnosisofalzheimersdisease |