ImportanceBrain aging elicits complex neuroanatomical changes influenced by multiple age-related pathologies. Understanding the heterogeneity of structural brain changes in aging may provide insights into preclinical stages of neurodegenerative diseases.ObjectiveTo derive subgroups with common patterns of variation in participants without diagnosed cognitive impairment (WODCI) in a data-driven manner and relate them to genetics, biomedical measures, and cognitive decline trajectories.Design, Setting, and ParticipantsData acquisition for this cohort study was performed from 1999 to 2020. Data consolidation and harmonization were conducted from July 2017 to July 2021. Age-specific subgroups of structural brain measures were modeled in 4 decade-long intervals spanning ages 45 to 85 years using a deep learning, semisupervised clustering method leveraging generative adversarial networks. Data were analyzed from July 2021 to February 2023 and were drawn from the Imaging-Based Coordinate System for Aging and Neurodegenerative Diseases (iSTAGING) international consortium. Individuals WODCI at baseline spanning ages 45 to 85 years were included, with greater than 50 000 data time points.ExposuresIndividuals WODCI at baseline scan.Main Outcomes and MeasuresThree subgroups, consistent across decades, were identified within the WODCI population. Associations with genetics, cardiovascular risk factors (CVRFs), amyloid β (Aβ), and future cognitive decline were assessed.ResultsIn a sample of 27 402 individuals (mean [SD] age, 63.0 [8.3] years; 15 146 female [55%]) WODCI, 3 subgroups were identified in contrast with the reference group: a typical aging subgroup, A1, with a specific pattern of modest atrophy and white matter hyperintensity (WMH) load, and 2 accelerated aging subgroups, A2 and A3, with characteristics that were more distinct at age 65 years and older. A2 was associated with hypertension, WMH, and vascular disease–related genetic variants and was enriched for Aβ positivity (ages ≥65 years) and apolipoprotein E (APOE) ε4 carriers. A3 showed severe, widespread atrophy, moderate presence of CVRFs, and greater cognitive decline. Genetic variants associated with A1 were protective for WMH (rs7209235: mean [SD] B = −0.07 [0.01]; P value = 2.31 × 10−9) and Alzheimer disease (rs72932727: mean [SD] B = 0.1 [0.02]; P value = 6.49 × 10−9), whereas the converse was observed for A2 (rs7209235: mean [SD] B = 0.1 [0.01]; P value = 1.73 × 10−15 and rs72932727: mean [SD] B = −0.09 [0.02]; P value = 4.05 × 10−7, respectively); variants in A3 were associated with regional atrophy (rs167684: mean [SD] B = 0.08 [0.01]; P value = 7.22 × 10−12) and white matter integrity measures (rs1636250: mean [SD] B = 0.06 [0.01]; P value = 4.90 × 10−7).Conclusions and RelevanceThe 3 subgroups showed distinct associations with CVRFs, genetics, and subsequent cognitive decline. These subgroups likely reflect multiple underlying neuropathologic processes and affect susceptibility to Alzheimer disease, paving pathways toward patient stratification at early asymptomatic stages and promoting precision medicine in clinical trials and health care.

中文翻译：

---

认知未受损个体中基于人工智能的大脑衰老模式的遗传和临床相关性

重要性大脑衰老会引发复杂的神经解剖学变化，这些变化受多种与年龄相关的病理影响。了解衰老过程中大脑结构变化的异质性可能有助于深入了解神经退行性疾病的临床前阶段。目的以数据驱动的方式推导未诊断出认知障碍（WODCI）的参与者具有常见变异模式的亚组，并将其与遗传学、生物医学措施联系起来和认知衰退轨迹。设计、设置和参与者该队列研究的数据采集是从 1999 年到 2020 年进行的。数据整合和协调是从 2017 年 7 月到 2021 年 7 月进行的。结构性大脑测量的特定年龄亚组在 4 个十年内建模-使用利用生成对抗网络的深度学习、半监督聚类方法，跨越 45 至 85 岁的长间隔。数据分析时间为 2021 年 7 月至 2023 年 2 月，数据取自衰老和神经退行性疾病成像坐标系统 (iSTAGING) 国际联盟。基线时跨度为 45 至 85 岁的个体 WODCI 被纳入其中，具有超过 50 000 个数据时间点。暴露于基线扫描时的个体 WODCI。主要结果和测量在 WODCI 人群中确定了几十年来一致的三个亚组。评估了与遗传学、心血管危险因素 (CVRF)、β 淀粉样蛋白 (Aβ) 和未来认知能力下降的关联。结果在 27 402 名个体样本中（平均 [SD] 年龄，63.0 [8.3] 岁；15 146 名女性 [55% ]) WODCI，与参考组相比，确定了 3 个亚组：一个典型的衰老亚组，A1，具有中度萎缩和白质高信号 (WMH) 负荷的特定模式，以及 2 个加速衰老亚组，A2 和 A3，具有特征65 岁及以上的人的情况更加明显。A2 与高血压、WMH 和血管疾病相关的遗传变异相关，并且在 Aβ 阳性（年龄≥65 岁）和载脂蛋白 E (APOE) ε4 携带者中富集。A3 表现出严重、广泛的萎缩、中度 CVRF 的存在以及更大的认知能力下降。与 A1 相关的遗传变异对 WMH 具有保护作用（rs7209235：平均值 [SD] B = -0.07 [0.01]；磷值 = 2.31 × 10−9）和阿尔茨海默病（rs72932727：平均值 [SD] B = 0.1 [0.02]；磷值 = 6.49 × 10−9），而 A2 则相反（rs7209235：平均值 [SD] B = 0.1 [0.01]；磷值 = 1.73 × 10−15rs72932727：平均值 [SD] B = −0.09 [0.02]；磷值 = 4.05 × 10−7， 分别）; A3 中的变异与区域萎缩相关（rs167684：平均值 [SD] B = 0.08 [0.01]；磷值 = 7.22 × 10−12）和白质完整性测量（rs1636250：平均值 [SD] B = 0.06 [0.01]；磷值 = 4.90 × 10−7).结论和相关性这 3 个亚组显示出与 CVRF、遗传学和随后的认知能力下降的明显关联。这些亚组可能反映了多种潜在的神经病理过程，并影响对阿尔茨海默病的易感性，为早期无症状阶段的患者分层铺平了道路，并促进临床试验和医疗保健中的精准医疗。