文献速递儿童青少年精神

自闭症与社交沟通症状严重程度的稳健可泛化可解释人工智能脑指纹

Robust, Generalizable, and Interpretable Artificial Intelligence-Derived Brain Fingerprints of Autism and Social Communication Symptom Severity.
PubMed 文献 · Biol Psychiatry · 2022-02-16

研究利用多队列脑影像与可解释人工智能构建时空深度神经网络(stDNN),在ABIDE队列(n=834)交叉验证中高准确率区分ASD与神经典型对照,并在Stanford(n=202)和GENDAAR(n=90)独立队列中无需额外训练即准确分类;stDNN无法区分ADHD与对照,显示特异性;后扣带皮层与楔前叶特征可稳健预测社交沟通核心缺陷严重程度,但不预测限制/重复行为。

要点

  • stDNN在ABIDE多站点队列交叉验证中区分ASD与对照准确率高。
  • stDNN在Stanford和GENDAAR独立队列无需额外训练即准确分类。
  • 后扣带皮层与楔前叶特征稳健预测社交沟通严重程度,不预测重复行为。

核心结论

  • 跨独立队列复现的发现揭示ASD精神病理学的稳健个体化功能脑指纹,可能有助于更客观精准的表型刻画和靶向治疗。

研究设计与样本

  • 利用多队列脑影像与可解释人工智能构建时空深度神经网络(stDNN)模型。
  • 在ABIDE多站点队列(n=834)进行交叉验证分析。
  • 在Stanford(n=202)和GENDAAR(n=90)独立队列中测试无需额外训练的分类。
  • 测试stDNN区分ADHD与神经典型对照的特异性。

主要发现

  • stDNN在ABIDE队列交叉验证中区分ASD与神经典型对照的准确率 consistently 高。
  • stDNN在Stanford(n=202)和GENDAAR(n=90)独立队列中无需额外训练即准确分类。
  • stDNN无法区分ADHD与神经典型对照,显示模型特异性。
  • 与后扣带皮层和楔前叶、背外侧和腹外侧前额叶皮层、上颞沟相关的脑特征在三个队列中最清晰区分ASD与对照。
  • 后扣带皮层与楔前叶(默认模式网络节点)特征稳健预测ASD核心社交沟通缺陷严重程度,但不预测限制/重复行为。

关键数值与推荐

  • ABIDE队列n=834;Stanford队列n=202;GENDAAR队列n=90。

临床怎么用

  • 原文未报告临床实践建议。

局限性

  • 原文未述局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Autism spectrum disorder (ASD) is among the most pervasive neurodevelopmental disorders, yet the neurobiology of ASD is still poorly understood because inconsistent findings from underpowered individual studies preclude the identification of robust and interpretable neurobiological markers and predictors of clinical symptoms. METHODS: We leverage multiple brain imaging cohorts and exciting recent advances in explainable artificial intelligence to develop a novel spatiotemporal deep neural network (stDNN) model, which identifies robust and interpretable dynamic brain markers that distinguish ASD from neurotypical control subjects and predict clinical symptom severity. RESULTS: stDNN achieved consistently high classification accuracies in cross-validation analysis of data from the multisite ABIDE (Autism Brain Imaging Data Exchange) cohort (n = 834). Crucially, stDNN also accurately classified data from independent Stanford (n = 202) and GENDAAR (Gender Exploration of Neurogenetics and Development to Advanced Autism Research) (n = 90) cohorts without additional training. stDNN could not distinguish attention-deficit/hyperactivity disorder from neurotypical control subjects, highlighting the model's specificity. Explainable artificial intelligence revealed that brain features associated with the posterior cingulate cortex and precuneus, dorsolateral and ventrolateral prefrontal cortex, and superior temporal sulcus, which anchor the default mode network, cognitive control, and human voice processing systems, respectively, most clearly distinguished ASD from neurotypical control subjects in the three cohorts. Furthermore, features associated with the posterior cingulate cortex and precuneus nodes of the default mode network emerged as robust predictors of the severity of core social and communication deficits but not restricted/repetitive behaviors in ASD. CONCLUSIONS: Our findings, replicated across independent cohorts, reveal robust individualized functional brain fingerprints of ASD psychopathology, which could lead to more objective and precise phenotypic characterization and targeted treatments.

来源:Biol Psychiatry,查看原文。版权归原作者所有。

引用

  1. Supekar K, Ryali S, Yuan R, et al. Robust, Generalizable, and Interpretable Artificial Intelligence-Derived Brain Fingerprints of Autism and Social Communication Symptom Severity. Biol Psychiatry. 2022. PMID: 35382930. doi:10.1016/j.biopsych.2022.02.005

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。