背景:淀粉样β(Aβ)斑块是阿尔茨海默病(AD)的神经病理学标志。随着抗淀粉样蛋白单克隆抗体进入市场,预测脑淀粉样蛋白状态对于确定治疗资格至关重要.
目的:在阿尔茨海默病和认知老化(ARMADA)研究中利用机器学习方法预测脑淀粉样蛋白状态。
方法:ARMADA是一项多中心研究,在具有不同认知能力水平(正常,轻度认知障碍,AD型的早期痴呆)。
方法:不同地点的参与者参与ARMADA研究以验证NIHTB。
方法:199名ARMADA参与者有PET或CSF信息(平均年龄76.3±7.7,51.3%为女性,42.3%的部分或完整的大学教育,50.3%研究生学历,88.9%白色,33.2%的AD生物标志物阳性)。
方法:我们使用认知,情感,电机,NIHTB的感觉评分,和人口统计学来预测通过PET或CSF测量的淀粉样蛋白状态。我们应用LASSO和随机森林模型,并使用受试者工作曲线下面积(AUROC)评估鉴定淀粉样蛋白阳性的能力。
结果:在保持测试集上,随机森林模型达到的AUROC为0.74,特异性高于敏感性(AUROC95%CI:0.73-0.76,敏感性0.50,特异性0.88);高于LASSO模型(0.68(95%CI:0.68-0.69))。随机森林模型中重要性最高的10个特征是:图片序列记忆,认知总复合,认知液复合材料,列表排序工作记忆,单词在噪声测试(听力),模式比较处理速度,气味识别,2分钟步行耐力,4米的步行步态速度,和图片词汇。总的来说,我们的模型揭示了认知测量的有效性,电机,和感觉域,与AD生物标志物相关。
结论:我们的结果支持利用NIH工具箱作为一种有效且可标准化的AD生物标志物测量,可以更好地识别淀粉样蛋白阴性(即,高特异性)比阳性病例(即,低灵敏度)。
BACKGROUND: Amyloid-beta (Aβ) plaque is a neuropathological hallmark of Alzheimer\'s disease (AD). As anti-amyloid monoclonal antibodies enter the market, predicting brain amyloid status is critical to determine treatment eligibility.
OBJECTIVE: To predict brain amyloid status utilizing machine learning approaches in the Advancing Reliable Measurement in Alzheimer\'s Disease and Cognitive Aging (ARMADA) study.
METHODS: ARMADA is a multisite study that implemented the National Institute of Health Toolbox for Assessment of Neurological and Behavioral Function (NIHTB) in older adults with different cognitive ability levels (normal, mild cognitive impairment, early-stage dementia of the AD type).
METHODS: Participants across various sites were involved in the ARMADA study for validating the NIHTB.
METHODS: 199 ARMADA participants had either PET or CSF information (mean age 76.3 ± 7.7, 51.3% women, 42.3% some or complete college education, 50.3% graduate education, 88.9% White, 33.2% with positive AD biomarkers).
METHODS: We used cognition, emotion, motor, sensation scores from NIHTB, and demographics to predict amyloid status measured by PET or CSF. We applied LASSO and random forest models and used the area under the receiver operating curve (AUROC) to evaluate the ability to identify amyloid positivity.
RESULTS: The random forest model reached AUROC of 0.74 with higher specificity than sensitivity (AUROC 95% CI:0.73 - 0.76, Sensitivity 0.50, Specificity 0.88) on the held-out test set; higher than the LASSO model (0.68 (95% CI:0.68 - 0.69)). The 10 features with the highest importance from the random forest model are: picture sequence memory, cognition total composite, cognition fluid composite, list sorting working memory, words-in-noise test (hearing), pattern comparison processing speed, odor identification, 2-minutes-walk endurance, 4-meter walk gait speed, and picture vocabulary. Overall, our model revealed the validity of measurements in cognition, motor, and sensation domains, in associating with AD biomarkers.
CONCLUSIONS: Our results support the utilization of the NIH toolbox as an efficient and standardizable AD biomarker measurement that is better at identifying amyloid negative (i.e., high specificity) than positive cases (i.e., low sensitivity).