Ethel Percy Andrus Gerontology Center, Leonard Davis School of Gerontology, University of Southern California, Los Angeles, California, USA.
Corwin D. Denney Research Center, Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, California, USA.
J Gerontol A Biol Sci Med Sci. 2023 Jun 1;78(6):872-881. doi: 10.1093/gerona/glac209.
The biological age of the brain differs from its chronological age (CA) and can be used as biomarker of neural/cognitive disease processes and as predictor of mortality. Brain age (BA) is often estimated from magnetic resonance images (MRIs) using machine learning (ML) that rarely indicates how regional brain features contribute to BA. Leveraging an aggregate training sample of 3 418 healthy controls (HCs), we describe a ridge regression model that quantifies each region's contribution to BA. After model testing on an independent sample of 651 HCs, we compute the coefficient of partial determination R¯p2 for each regional brain volume to quantify its contribution to BA. Model performance is also evaluated using the correlation r between chronological and biological ages, the mean absolute error (MAE ) and mean squared error (MSE) of BA estimates. On training data, r=0.92, MSE=70.94 years, MAE=6.57 years, and R¯2=0.81; on test data, r=0.90, MSE=81.96 years, MAE=7.00 years, and R¯2=0.79. The regions whose volumes contribute most to BA are the nucleus accumbens (R¯p2=7.27%), inferior temporal gyrus (R¯p2=4.03%), thalamus (R¯p2=3.61%), brainstem (R¯p2=3.29%), posterior lateral sulcus (R¯p2=3.22%), caudate nucleus (R¯p2=3.05%), orbital gyrus (R¯p2=2.96%), and precentral gyrus (R¯p2=2.80%). Our ridge regression, although outperformed by the most sophisticated ML approaches, identifies the importance and relative contribution of each brain structure to overall BA. Aside from its interpretability and quasi-mechanistic insights, our model can be used to validate future ML approaches for BA estimation.
大脑的生物年龄与实际年龄（CA）不同，可作为神经/认知疾病过程的生物标志物和死亡率的预测因子。大脑年龄（BA）通常是通过机器学习（ML）从磁共振成像（MRI）中估算出来的，但很少能说明区域大脑特征对 BA 的贡献。我们利用一个由 3418 名健康对照（HC）组成的综合训练样本，描述了一种岭回归模型，该模型可以量化每个区域对 BA 的贡献。在对 651 名 HC 的独立样本进行模型测试后，我们计算了每个区域脑容量对 BA 的偏决定系数 R¯p2，以量化其对 BA 的贡献。还通过比较 BA 的实际年龄和生物年龄之间的相关性 r、BA 估计的平均绝对误差（MAE）和平均平方误差（MSE）来评估模型性能。在训练数据上，r=0.92，MSE=70.94 岁，MAE=6.57 岁，R¯2=0.81；在测试数据上，r=0.90，MSE=81.96 岁，MAE=7.00 岁，R¯2=0.79。对 BA 贡献最大的区域是伏隔核（R¯p2=7.27%）、颞下回（R¯p2=4.03%）、丘脑（R¯p2=3.61%）、脑干（R¯p2=3.29%）、外侧裂后回（R¯p2=3.22%）、尾状核（R¯p2=3.05%）、眶回（R¯p2=2.96%）和中央前回（R¯p2=2.80%）。我们的岭回归虽然不如最复杂的 ML 方法表现出色，但它可以确定每个大脑结构对整体 BA 的重要性和相对贡献。除了可解释性和准机械洞察力外，我们的模型还可以用于验证未来 BA 估计的 ML 方法。
