The pathophysiology of Alzheimer’s disease (AD) involves $$\beta$$ -amyloid (A $$\beta$$ ) accumulation. Early identification of individuals with abnormal $$\beta$$ -amyloid levels is crucial, but A $$\beta$$ quantification with positron emission tomography (PET) and cerebrospinal fluid (CSF) is invasive and expensive. We propose a machine learning framework using standard non-invasive (MRI, demographics, APOE, neuropsychology) measures to predict future A $$\beta$$ -positivity in A $$\beta$$ -negative individuals. We separately study A $$\beta$$ -positivity defined by PET and CSF. Cross-validated AUC for 4-year A $$\beta$$ conversion prediction was 0.78 for the CSF-based and 0.68 for the PET-based A $$\beta$$ 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). Standard measures have potential in detecting future A $$\beta$$ -positivity and assessing conversion risk, even in cognitively normal individuals. The CSF-based definition led to better predictions than the PET-based definition.

中文翻译：

---

机器学习预测淀粉样蛋白阴性个体未来β淀粉样蛋白阳性率

阿尔茨海默病 (AD) 的病理生理学涉及 $$\beta$$ -淀粉样蛋白 (A $$\beta$$ ) 积累。早期识别 $$\beta$$ 淀粉样蛋白水平异常的个体至关重要，但使用正电子发射断层扫描 (PET) 和脑脊液 (CSF) 进行 $$\beta$$ 定量是侵入性的且昂贵。我们提出了一个机器学习框架，使用标准的非侵入性（MRI、人口统计学、APOE、神经心理学）测量来预测 A $$\beta$$ 阴性个体未来的 A $$\beta$$ 阳性。我们分别研究由 PET 和 CSF 定义的 A $$\beta$$ 阳性。基于 CSF 的 4 年 A $$\beta$$ 转换预测的交叉验证 AUC 为 0.78，基于 PET 的 A $$\beta$$ 定义为 0.68。尽管没有接受过临床状态变化预测的训练，但基于 CSF 的模型在预测认知正常/MCI 个体未来的轻度认知障碍 (MCI)/痴呆转化方面表现出色（在单独的数据集中，AUC 分别为 0.76 和 0.89）。标准措施有可能检测未来的 A $$\beta$$ 积极性并评估转换风险，即使对于认知正常的个体也是如此。基于 CSF 的定义比基于 PET 的定义产生更好的预测。