A machine learning approach to screen for preclinical Alzheimer's disease
A machine learning approach to screen for preclinical Alzheimer's disease
复制标题
筛选临床前阿尔茨海默病的机器学习方法
DOI：
10.1016/j.neurobiolaging.2021.04.024
复制
发表时间：
2021-06-05
影响因子：
4.2
通讯作者：
Epelbaum, Stephane
中科院分区：
文献类型：
--
作者：
Gaubert, Sinead;Houot, Marion;Epelbaum, Stephane
结合多模式生物标志物有助于阿尔茨海默病 (AD) 的早期诊断。我们从 INSIGHT-preAD 队列中纳入了 304 名认知正常的个体。分别使用 F-18-氟倍他吡和 F-18-氟脱氧葡萄糖 PET 评估淀粉样蛋白和神经变性。我们使用具有非侵入性特征（脑电图 [EEG]、APOE4 基因型、人口统计学、神经心理学和 MRI 数据）的嵌套交叉验证方法来预测： 1/ 淀粉样蛋白状态； 2/ 神经退行性状态； 3/ 5 年随访时下降为前驱 AD。重要的是，即使将通道数量从 224 个减少到 4 个，EEG 对神经变性的预测能力也最强，因为 4 通道 EEG 可以最好地预测神经变性（阴性预测值 [NPV] = 82%，阳性预测值 [PPV] = 38%，特异性 77%，敏感性 45%）。人口统计学、神经心理学数据、APOE4 和海马体积测定相结合，最有力地预测了淀粉样蛋白（80% NPV、41% PPV、70% 特异性、58% 敏感性），并且最有力地预测了 5 年时 AD 前驱期的下降（97% NPV、14% PPV、83% 特异性、50% 敏感性）。因此，机器学习可以使用非侵入性且负担得起的生物标志物帮助筛查临床前 AD 高风险患者。 (C) 2021 Elsevier Inc. 保留所有权利。
Combining multimodal biomarkers could help in the early diagnosis of Alzheimer's disease (AD). We included 304 cognitively normal individuals from the INSIGHT-preAD cohort. Amyloid and neurodegeneration were assessed on F-18-florbetapir and F-18-fluorodeoxyglucose PET, respectively. We used a nested cross-validation approach with non-invasive features (electroencephalography [EEG], APOE4 genotype, demographic, neuropsychological and MRI data) to predict: 1/ amyloid status; 2/ neurodegeneration status; 3/ decline to prodromal AD at 5-year follow-up. Importantly, EEG was most strongly predictive of neurodegeneration, even when reducing the number of channels from 224 down to 4, as 4-channel EEG best predicted neurodegeneration (negative predictive value [NPV] = 82%, positive predictive value [PPV] = 38%, 77% specificity, 45% sensitivity). The combination of demographic, neuropsychological data, APOE4 and hippocampal volumetry most strongly predicted amyloid (80% NPV, 41% PPV, 70% specificity, 58% sensitivity) and most strongly predicted decline to prodromal AD at 5 years (97% NPV, 14% PPV, 83% specificity, 50% sensitivity). Thus, machine learning can help to screen patients at high risk of preclinical AD using non-invasive and affordable biomarkers. (C) 2021 Elsevier Inc. All rights reserved.