Griffin Ben, Ahrends Christine, Gohil Chetan, Alfaro-Almagro Fidel, Woolrich Mark W, Smith Stephen M, Vidaurre Diego
Oxford Centre for Functional MRI of the Brain (FMRIB), Wellcome Centre for Integrative Neuroimaging, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom.
Center of Functionally Integrative Neuroscience, Department of Clinical Medicine, Aarhus University, Aarhus, Denmark.
Imaging Neurosci (Camb). 2024 Aug 20;2:1-22. doi: 10.1162/imag_a_00267. eCollection 2024 Aug 1.
Beyond structural and time-averaged functional connectivity brain measures, modelling the way brain activity dynamically unfolds can add important information to our understanding and characterisation of individual cognitive traits. One approach to leveraging this information is to extract features from models of brain network dynamics to predict individual traits. However, these predictions are susceptible to variability due to factors such as variation in model estimation induced by the choice of hyperparameters. We suggest that, rather than merely being statistical noise, this variability may be useful in providing complementary information that can be leveraged to improve prediction accuracy. To leverage this variability, we propose the use of stacking, a prediction-driven approach for model selection. Specifically, we combine predictions developed from multiple hidden Markov models-a probabilistic generative model of network dynamics that identifies recurring patterns of brain activity-to demonstrate that stacking can slightly improve the accuracy and robustness of cognitive trait predictions. By comparing analysis from the Human Connectome Project and UK Biobank datasets, we show that stacking is relatively effective at improving prediction accuracy and robustness when there are enough subjects, and that the effectiveness of combining predictions from static and dynamic functional connectivity approaches depends on the length of scan per subject. We also show that the effectiveness of stacking predictions is driven by the accuracy and diversity in the underlying model estimations.
除了结构和时间平均功能连接性脑测量外，对大脑活动动态展开方式进行建模可以为我们理解和刻画个体认知特征增添重要信息。利用这些信息的一种方法是从脑网络动力学模型中提取特征来预测个体特征。然而，由于诸如超参数选择引起的模型估计变化等因素，这些预测容易受到变异性的影响。我们认为，这种变异性可能并非仅仅是统计噪声，而是在提供可用于提高预测准确性的补充信息方面可能有用。为了利用这种变异性，我们建议使用堆叠法，这是一种用于模型选择的预测驱动方法。具体而言，我们结合了从多个隐藏马尔可夫模型（一种识别大脑活动重复模式的网络动力学概率生成模型）得出的预测，以证明堆叠法可以略微提高认知特征预测的准确性和稳健性。通过比较来自人类连接组计划和英国生物银行数据集的分析，我们表明，当有足够多的受试者时，堆叠法在提高预测准确性和稳健性方面相对有效，并且结合静态和动态功能连接方法的预测效果取决于每个受试者的扫描时长。我们还表明，堆叠预测的有效性是由基础模型估计的准确性和多样性驱动的。
