Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disorders
Abstract Previous studies have developed and explored magnetic resonance imaging (MRI)-based machine learning models for predicting Alzheimer’s disease (AD). However, limited research has focused on models incorporating diverse patient populations. This study aimed to build a clinically useful predi...
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-58223-3 |
| _version_ | 1797219884621365248 |
|---|---|
| author | Yuki Momota Shogyoku Bun Jinichi Hirano Kei Kamiya Ryo Ueda Yu Iwabuchi Keisuke Takahata Yasuharu Yamamoto Toshiki Tezuka Masahito Kubota Morinobu Seki Ryo Shikimoto Yu Mimura Taishiro Kishimoto Hajime Tabuchi Masahiro Jinzaki Daisuke Ito Masaru Mimura |
| author_facet | Yuki Momota Shogyoku Bun Jinichi Hirano Kei Kamiya Ryo Ueda Yu Iwabuchi Keisuke Takahata Yasuharu Yamamoto Toshiki Tezuka Masahito Kubota Morinobu Seki Ryo Shikimoto Yu Mimura Taishiro Kishimoto Hajime Tabuchi Masahiro Jinzaki Daisuke Ito Masaru Mimura |
| author_sort | Yuki Momota |
| collection | DOAJ |
| description | Abstract Previous studies have developed and explored magnetic resonance imaging (MRI)-based machine learning models for predicting Alzheimer’s disease (AD). However, limited research has focused on models incorporating diverse patient populations. This study aimed to build a clinically useful prediction model for amyloid-beta (Aβ) deposition using source-based morphometry, using a data-driven algorithm based on independent component analyses. Additionally, we assessed how the predictive accuracies varied with the feature combinations. Data from 118 participants clinically diagnosed with various conditions such as AD, mild cognitive impairment, frontotemporal lobar degeneration, corticobasal syndrome, progressive supranuclear palsy, and psychiatric disorders, as well as healthy controls were used for the development of the model. We used structural MR images, cognitive test results, and apolipoprotein E status for feature selection. Three-dimensional T1-weighted images were preprocessed into voxel-based gray matter images and then subjected to source-based morphometry. We used a support vector machine as a classifier. We applied SHapley Additive exPlanations, a game-theoretical approach, to ensure model accountability. The final model that was based on MR-images, cognitive test results, and apolipoprotein E status yielded 89.8% accuracy and a receiver operating characteristic curve of 0.888. The model based on MR-images alone showed 84.7% accuracy. Aβ-positivity was correctly detected in non-AD patients. One of the seven independent components derived from source-based morphometry was considered to represent an AD-related gray matter volume pattern and showed the strongest impact on the model output. Aβ-positivity across neurological and psychiatric disorders was predicted with moderate-to-high accuracy and was associated with a probable AD-related gray matter volume pattern. An MRI-based data-driven machine learning approach can be beneficial as a diagnostic aid. |
| first_indexed | 2024-04-24T12:40:44Z |
| format | Article |
| id | doaj.art-9d1f58f65cab4220bbb024c0bfc69f91 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T12:40:44Z |
| publishDate | 2024-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-9d1f58f65cab4220bbb024c0bfc69f912024-04-07T11:15:14ZengNature PortfolioScientific Reports2045-23222024-04-0114111210.1038/s41598-024-58223-3Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disordersYuki Momota0Shogyoku Bun1Jinichi Hirano2Kei Kamiya3Ryo Ueda4Yu Iwabuchi5Keisuke Takahata6Yasuharu Yamamoto7Toshiki Tezuka8Masahito Kubota9Morinobu Seki10Ryo Shikimoto11Yu Mimura12Taishiro Kishimoto13Hajime Tabuchi14Masahiro Jinzaki15Daisuke Ito16Masaru Mimura17Department of Neuropsychiatry, Keio University School of MedicineDepartment of Neuropsychiatry, Keio University School of MedicineDepartment of Neuropsychiatry, Keio University School of MedicineDepartment of Neuropsychiatry, Keio University School of MedicineOffice of Radiation Technology, Keio University HospitalDepartment of Radiology, Keio University School of MedicineDepartment of Neuropsychiatry, Keio University School of MedicineDepartment of Functional Brain Imaging Research, Institute for Quantum Medical Science, National Institutes for Quantum Science and TechnologyDepartment of Neurology, Keio University School of MedicineDepartment of Neurology, Keio University School of MedicineDepartment of Neurology, Keio University School of MedicineDepartment of Neuropsychiatry, Keio University School of MedicineDepartment of Neuropsychiatry, Keio University School of MedicinePsychiatry Department, Donald and Barbara Zucker School of MedicineDepartment of Neuropsychiatry, Keio University School of MedicineDepartment of Radiology, Keio University School of MedicineDepartment of Physiology, Keio University School of MedicineCenter for Preventive Medicine, Keio UniversityAbstract Previous studies have developed and explored magnetic resonance imaging (MRI)-based machine learning models for predicting Alzheimer’s disease (AD). However, limited research has focused on models incorporating diverse patient populations. This study aimed to build a clinically useful prediction model for amyloid-beta (Aβ) deposition using source-based morphometry, using a data-driven algorithm based on independent component analyses. Additionally, we assessed how the predictive accuracies varied with the feature combinations. Data from 118 participants clinically diagnosed with various conditions such as AD, mild cognitive impairment, frontotemporal lobar degeneration, corticobasal syndrome, progressive supranuclear palsy, and psychiatric disorders, as well as healthy controls were used for the development of the model. We used structural MR images, cognitive test results, and apolipoprotein E status for feature selection. Three-dimensional T1-weighted images were preprocessed into voxel-based gray matter images and then subjected to source-based morphometry. We used a support vector machine as a classifier. We applied SHapley Additive exPlanations, a game-theoretical approach, to ensure model accountability. The final model that was based on MR-images, cognitive test results, and apolipoprotein E status yielded 89.8% accuracy and a receiver operating characteristic curve of 0.888. The model based on MR-images alone showed 84.7% accuracy. Aβ-positivity was correctly detected in non-AD patients. One of the seven independent components derived from source-based morphometry was considered to represent an AD-related gray matter volume pattern and showed the strongest impact on the model output. Aβ-positivity across neurological and psychiatric disorders was predicted with moderate-to-high accuracy and was associated with a probable AD-related gray matter volume pattern. An MRI-based data-driven machine learning approach can be beneficial as a diagnostic aid.https://doi.org/10.1038/s41598-024-58223-3Alzheimer’s diseaseAmyloid-βMachine learningMagnetic resonance imagingSource-based morphometry |
| spellingShingle | Yuki Momota Shogyoku Bun Jinichi Hirano Kei Kamiya Ryo Ueda Yu Iwabuchi Keisuke Takahata Yasuharu Yamamoto Toshiki Tezuka Masahito Kubota Morinobu Seki Ryo Shikimoto Yu Mimura Taishiro Kishimoto Hajime Tabuchi Masahiro Jinzaki Daisuke Ito Masaru Mimura Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disorders Scientific Reports Alzheimer’s disease Amyloid-β Machine learning Magnetic resonance imaging Source-based morphometry |
| title | Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disorders |
| title_full | Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disorders |
| title_fullStr | Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disorders |
| title_full_unstemmed | Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disorders |
| title_short | Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disorders |
| title_sort | amyloid β prediction machine learning model using source based morphometry across neurocognitive disorders |
| topic | Alzheimer’s disease Amyloid-β Machine learning Magnetic resonance imaging Source-based morphometry |
| url | https://doi.org/10.1038/s41598-024-58223-3 |
| work_keys_str_mv | AT yukimomota amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT shogyokubun amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT jinichihirano amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT keikamiya amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT ryoueda amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT yuiwabuchi amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT keisuketakahata amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT yasuharuyamamoto amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT toshikitezuka amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT masahitokubota amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT morinobuseki amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT ryoshikimoto amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT yumimura amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT taishirokishimoto amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT hajimetabuchi amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT masahirojinzaki amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT daisukeito amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders AT masarumimura amyloidbpredictionmachinelearningmodelusingsourcebasedmorphometryacrossneurocognitivedisorders |