期刊
NEUROSCIENCE
卷 514, 期 -, 页码 143-152出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neuroscience.2023.01.029
关键词
Alzheimer?s disease dementia (AD) prediction; artificial intelligence; gradient boosting; machine learning (ML) algori-thms; mild cognitive impairment (MCI); random forest (RF)
By comparing the prognostic performances of three supervised machine learning algorithms using multimodal biomarkers, this study found that combining clinical and biological measures can improve the accuracy of predicting conversion from mild cognitive impairment (MCI) to Alzheimer's disease. The results also revealed that neuropsychological test scores, neuroimaging data, and protein measurements are important variables for accurate prediction.
Mild Cognitive Impairment (MCI), identifying a high risk of conversion to Alzheimer's Disease Demen-tia (AD) is a primary goal for patient management. Machine Learning (ML) algorithms are widely employed to pur-sue data-driven diagnostic and prognostic goals. An agreement on the stability of these algorithms -when applied to different biomarkers and other conditions- is far from being reached. In this study, we compared the different prognostic performances of three supervised ML algorithms fed with multimodal biomarkers of MCI subjects obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Random Forest, Gradient Boosting, and eXtreme Gradient Boosting algorithms predict MCI conversion to AD. They can also be simultaneously employed -with the voting procedure- to improve predictivity. AD prediction accuracy is influ-enced by the nature of the data (i.e., neuropsychological test scores, cerebrospinal fluid AD-related proteins and APOE e4, cerebral structural MRI (sMRI) data). In our study, independent of the applied ML algorithms, sMRI data showed the lowest accuracy (0.79) compared to other classes. Multimodal data were helpful in the algo-rithms' performances by combining clinical and biological measures. Accordingly, using the three ML algorithms, the highest accuracy (0.90) was reached by employing neuropsychological and AD-related biomarkers. Finally, the feature selection procedure indicated that the most critical variables in the respective classes were the ADAS-Cog-13 scale, the medial temporal lobe and hippocampus atrophy, and the ratio between phosphorylated Tau and Ab42 proteins. In conclusion, our data support the notion that using multiple ML algorithms and multi-modal biomarkers helps make more accurate and solid predictions.(c) 2023 IBRO. Published by Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据