Program in Neuroscience, University of Western Ontario, London, ON, Canada.
Program in Neuroscience, University of Western Ontario, London, ON, Canada; Brain and Mind Institute, University of Western Ontario, London, ON, Canada; Department of Psychology, University of Western Ontario, London, ON, Canada; Western Institute for Neuroscience, University of Western Ontario, London, ON, Canada.
Dev Cogn Neurosci. 2024 Oct;69:101439. doi: 10.1016/j.dcn.2024.101439. Epub 2024 Aug 22.
Youth diagnosed with Attention-Deficit/Hyperactivity Disorder (ADHD) often show deficits in various measures of higher-level cognition, such as, executive functioning. Poorer cognitive functioning in children with ADHD has been associated with differences in functional connectivity across the brain. However, little is known about the developmental changes to the brain's functional properties linked to different cognitive abilities in this cohort. To characterize these changes, we analyzed fMRI data (ADHD = 373, NT = 106) collected while youth between the ages of 6 and 16 watched a short movie-clip. We applied machine learning models to identify patterns of network connectivity in response to movie-watching that differentially predict cognitive abilities in our cohort. Using out-of-sample cross validation, our models successfully predicted IQ, visual spatial, verbal comprehension, and fluid reasoning in children (ages 6 - 11), but not in adolescents with ADHD (ages 12-16). Connections with the default mode, memory retrieval, and dorsal attention were driving prediction during early and middle childhood, but connections with the somatomotor, cingulo-opercular, and frontoparietal networks were more important in middle childhood. This work demonstrated that machine learning approaches can identify distinct functional connectivity profiles associated with cognitive abilities at different developmental stages in children and adolescents with ADHD.
被诊断患有注意力缺陷多动障碍（ADHD）的年轻人通常在各种高级认知测量中表现出缺陷，例如执行功能。ADHD 儿童的认知功能较差与大脑之间的功能连接差异有关。然而，对于与该队列中不同认知能力相关的大脑功能特性的发育变化知之甚少。为了描述这些变化，我们分析了 fMRI 数据（ADHD = 373，NT = 106），这些数据是在 6 至 16 岁的年轻人观看短片时收集的。我们应用机器学习模型来识别对观看电影做出反应的网络连接模式，这些模式可以预测我们队列中的认知能力。使用样本外交叉验证，我们的模型成功预测了儿童（6-11 岁）的智商、视觉空间、言语理解和流体推理能力，但不能预测 ADHD 青少年（12-16 岁）的这些能力。与默认模式、记忆检索和背侧注意力的连接在幼儿期和中期推动了预测，但与躯体运动、扣带回-脑岛和额顶叶网络的连接在中期更为重要。这项工作表明，机器学习方法可以识别与 ADHD 儿童和青少年不同发育阶段的认知能力相关的不同功能连接特征。
Zotero 插件
