机器学习预测淀粉样阴性个体未来淀粉样蛋白β阳性。
Machine learning prediction of future amyloid beta positivity in amyloid-negative individuals.
机构信息
A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, 70150, Finland.
Institute of Clinical Medicine/Neurology, University of Eastern Finland, Kuopio, Finland.
出版信息
Alzheimers Res Ther. 2024 Feb 27;16(1):46. doi: 10.1186/s13195-024-01415-w.
BACKGROUND
The pathophysiology of Alzheimer's disease (AD) involves -amyloid (A ) accumulation. Early identification of individuals with abnormal -amyloid levels is crucial, but A quantification with positron emission tomography (PET) and cerebrospinal fluid (CSF) is invasive and expensive.
METHODS
We propose a machine learning framework using standard non-invasive (MRI, demographics, APOE, neuropsychology) measures to predict future A -positivity in A -negative individuals. We separately study A -positivity defined by PET and CSF.
RESULTS
Cross-validated AUC for 4-year A conversion prediction was 0.78 for the CSF-based and 0.68 for the PET-based A definitions. Although not trained for the clinical status-change prediction, the CSF-based model excelled in predicting future mild cognitive impairment (MCI)/dementia conversion in cognitively normal/MCI individuals (AUCs, respectively, 0.76 and 0.89 with a separate dataset).
CONCLUSION
Standard measures have potential in detecting future A -positivity and assessing conversion risk, even in cognitively normal individuals. The CSF-based definition led to better predictions than the PET-based definition.
背景
阿尔茨海默病（AD）的病理生理学涉及β-淀粉样蛋白（Aβ）的积累。早期识别 Aβ水平异常的个体至关重要，但正电子发射断层扫描（PET）和脑脊液（CSF）的 Aβ定量是侵入性和昂贵的。
方法
我们提出了一个使用标准非侵入性（MRI、人口统计学、APOE、神经心理学）测量值的机器学习框架，以预测 Aβ阴性个体未来 Aβ的阳性情况。我们分别研究了由 PET 和 CSF 定义的 Aβ阳性。
结果
4 年 Aβ转换预测的交叉验证 AUC 分别为 CSF 为 0.78，PET 为 0.68。尽管该模型未针对临床状态变化预测进行训练，但 CSF 模型在预测认知正常/轻度认知障碍（MCI）个体中未来的 MCI/痴呆转换方面表现出色（分别为 0.76 和 0.89，使用单独的数据集）。
结论
标准测量值具有检测未来 Aβ阳性和评估转化风险的潜力，即使在认知正常的个体中也是如此。CSF 定义的预测结果优于 PET 定义。
Zotero 插件