Petersen Kellen K, Nallapu Bhargav T, Lipton Richard B, Grober Ellen, Ezzati Ali
Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA.
The Saul R. Korey Department of Neurology, Albert Einstein College of Medicine, New York City, NY, USA.
Neuroimage Rep. 2024 Dec;4(4). doi: 10.1016/j.ynirp.2024.100227. Epub 2024 Nov 18.
Alzheimer's disease (AD) is a phenotypically and pathologically heterogenous neurodegenerative disorder. This heterogeneity can be studied and disentangled using data-driven clustering techniques.
We implemented a self-organizing map clustering algorithm on baseline volumetric MRI measures from nine brain regions of interest (ROIs) to cluster 1041 individuals enrolled in the placebo arm of the EXPEDITION3 trial. Volumetric MRI differences were compared among clusters. Demographics as well as baseline and longitudinal cognitive performance metrics were used to evaluate cluster characteristics.
Three distinct clusters, with an overall silhouette coefficient of 0.491, were identified based on MRI volumetrics. Cluster 1 (N = 400) had the largest baseline volumetric measures across all ROIs and the best cognitive performance at baseline. Cluster 2 (N = 269) had larger hippocampal and medial temporal lobe volumes, but smaller parietal lobe volumes in comparison with the third cluster (N = 372). Significant between-group mean differences were observed between Clusters 1 and 2 (difference, 2.38; 95% CI, 1.85 to 2.91; P < 0.001), Clusters 1 and 3 (difference, 1.93; 95% CI, 1.41 to 2.44; P < 0.001), but not between Clusters 2 and 3 (difference, 0.45; 95% CI, -0.11 to 1.02; P = 0.146) in ADAS-14.
Volumetric MRI can be used to identify homogenous clusters of amyloid positive individuals with mild dementia. The groups identified differ in baseline and longitudinal characteristics. Cluster 1 shows little ADAS-14 change over the first 40 weeks of study on placebo treatment and may be unsuitable for identifying early benefits of treatment.
阿尔茨海默病（AD）是一种在表型和病理上具有异质性的神经退行性疾病。这种异质性可以通过数据驱动的聚类技术进行研究和解析。
我们对来自9个感兴趣脑区（ROI）的基线容积MRI测量数据实施了自组织映射聚类算法，以对参加EXPEDITION3试验安慰剂组的1041名个体进行聚类。比较了各聚类之间的容积MRI差异。使用人口统计学数据以及基线和纵向认知表现指标来评估聚类特征。
基于MRI容积测量数据识别出三个不同的聚类，总体轮廓系数为0.491。聚类1（N = 400）在所有ROI中具有最大的基线容积测量值，且在基线时认知表现最佳。与第三聚类（N = 372）相比，聚类2（N = 269）的海马体和内侧颞叶体积较大，但顶叶体积较小。在ADAS - 14中，聚类1和聚类2之间（差异为2.38；95% CI，1.85至2.91；P < 0.001）、聚类1和聚类3之间（差异为1.93；95% CI，1.41至2.44；P < 0.001）观察到显著的组间平均差异，但聚类2和聚类3之间未观察到显著差异（差异为0.45；95% CI， - 0.11至1.02；P = 0.146）。
容积MRI可用于识别患有轻度痴呆的淀粉样蛋白阳性个体的同质聚类。所识别出的组在基线和纵向特征方面存在差异。聚类1在安慰剂治疗的前40周内ADAS - 14变化很小，可能不适用于确定治疗的早期益处。
