一种机器学习方法来区分边界性人格障碍与具有全大脑功能连接的社区参与者
Juha M Lahnakoski1, Tobias Nolte2, Alec Solway3
1Independent Max Planck Research Group for Social Neuroscience, Max Planck Institute of Psychiatry, Munich, Germany; Institute of Neuroscience and Medicine, Brain & Behaviour (INM-7), Research Center Jülich, Wilhelm-Johnen-Straße, 52428 Jülich, Germany; Institute of Systems Neuroscience, Medical Faculty, Heinrich Heine University Düsseldorf, Moorenstr. 5, 40225 Düsseldorf, Germany.
Journal of affective disorders
|May 28, 2024
概括
功能性连接模式在个人中显示出边缘性人格障碍 (BPD) 的中度预测能力. 这些大脑网络差异可以观察到,尽管患者异质,提供潜在的生物标志物.
科学领域:
- 神经科学是一个神经科学.
- 精神病学是一个精神病学.
- 医疗成像医学成像
背景情况:
- 功能连接性 (FC) 被探索为精神障碍的潜在生物标志物,如边缘性人格障碍 (BPD).
- 之前的研究表明,由于样本规模较小和缺乏复制,结果各不相同.
- 与BPD相关的FC变化的清晰空间焦点仍然难以捉摸.
研究的目的:
- 评估FC标志物对BPD的歧视性表现和通用性.
- 确定与BPD相关的特定大脑区域和网络模式.
- 评估FC在诊断BPD中的临床实用性.
主要方法:
- 全脑静止状态功能磁共振成像 (fMRI) 数据来自116名BPD患者和72名对照组.
- 使用重复交叉验证进行训练和验证的分类模型 (例如基于全球ROI,基于种子,基于voxel-to-voxel).
- 对独立的,不匹配的数据子集的概括性评估.
主要成果:
- 全脑FC在分类BPD与对照中达到~70%的准确性,在样本外数据中概括为~61-70%.
- 基于种子的分析得出了类似的准确度 (~70-75%),但具有更大的空间特异性,突出了中线,时间和体运动区域.
- 虽然单变连接性不是预测性的,但弱的局部效应与歧视性的种子区域相关. 临床面试的表现优于自我报告措施.
结论:
- 空间分布的FC模式显示了BPD的中等预测能力.
- 尽管人口异质,这些FC模式具有作为生物标志物的潜力.
- 需要进一步的研究来完善这些标记物,并解决信号变化等局限性.
相关概念视频
Borderline Personality Disorder
40
Borderline Personality Disorder is a complex and multifaceted mental health condition characterized by pervasive instability in interpersonal relationships, self-image, emotions, and impulse control. This instability manifests in extreme emotional reactions, fear of abandonment, and self-destructive behaviors. The disorder significantly impacts daily functioning, often leading to distress in both personal and professional domains.
Genetic and Environmental Contributions
Borderline Personality...
Genetic and Environmental Contributions
Borderline Personality...
40
Brain Imaging
227
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
227


