Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disorders

被引：3

作者：

Momota, Yuki ^{[1
,4
]}

Bun, Shogyoku ^{[1
]}

Hirano, Jinichi ^{[1
]}

Kamiya, Kei ^{[1
]}

Ueda, Ryo ^{[2
]}

Iwabuchi, Yu ^{[3
]}

Takahata, Keisuke ^{[1
,4
]}

Yamamoto, Yasuharu ^{[4
]}

Tezuka, Toshiki ^{[5
]}

Kubota, Masahito ^{[5
]}

Seki, Morinobu ^{[5
]}

Shikimoto, Ryo ^{[1
]}

Mimura, Yu ^{[1
]}

Kishimoto, Taishiro ^{[8
,9
]}

Tabuchi, Hajime ^{[1
]}

Jinzaki, Masahiro ^{[3
]}

Ito, Daisuke ^{[6
,7
]}

Mimura, Masaru ^{[10
]}

机构：

[1] Keio Univ, Sch Med, Dept Neuropsychiat, 35 Shinanomachi,Shinjuku Ku, Tokyo 1608582, Japan

[2] Keio Univ Hosp, Off Radiat Technol, 35 Shinanomachi,Shinjuku Ku, Tokyo 1608582, Japan

[3] Keio Univ, Sch Med, Dept Radiol, 35 Shinanomachi,Shinjuku Ku, Tokyo 1608582, Japan

[4] Natl Inst Quantum Sci & Technol, Inst Quantum Med Sci, Dept Funct Brain Imaging Res, 4-9-1 Anagawa,Inage Ku, Chiba Shi, Chiba 2638555, Japan

[5] Keio Univ, Sch Med, Dept Neurol, 35 Shinanomachi,Shinjuku Ku, Tokyo 1608582, Japan

[6] Keio Univ, Sch Med, Dept Physiol, 35 Shinanomachi,Shinjuku Ku, Tokyo 1608582, Japan

[7] Keio Univ, Memory Ctr, Sch Med, 35 Shinanomachi,Shinjuku Ku, Tokyo 1608582, Japan

[8] Donald & Barbara Zucker Sch Med, Psychiat Dept, Hempstead, NY 11549 USA

[9] Keio Univ, Sch Med, Hills Joint Res Lab Future Prevent Med & Wellness, Mori JP Tower 7F,1-3-1 Azabudai,Minato Ku, Tokyo 1060041, Japan

[10] Keio Univ, Ctr Prevent Med, Mori JP Tower 7th Floor,1-3-1 Azabudai,Minato Ku, Tokyo 1060041, Japan

来源：

SCIENTIFIC REPORTS | 2024年 / 14卷 / 01期

关键词：

Alzheimer's disease; Amyloid-beta; Machine learning; Magnetic resonance imaging; Source-based morphometry; TEMPORAL-LOBE ATROPHY; ALZHEIMERS-DISEASE; CEREBROSPINAL-FLUID; NATIONAL INSTITUTE; DIAGNOSIS; MRI; AGE; DEGENERATION; ASSOCIATION; BIOMARKERS;

D O I：

10.1038/s41598-024-58223-3

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

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 (A beta) 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. A beta-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. A beta-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.

引用

页数：12