Oliveira-Saraiva Duarte, Ferreira Hugo Alexandre
Institute of Biophysics and Biomedical Engineering, Faculty of Sciences of the University of Lisbon, Lisbon, Portugal.
Front Psychiatry. 2023 Feb 15;14:1068397. doi: 10.3389/fpsyt.2023.1068397. eCollection 2023.
The diagnosis of psychiatric disorders is mostly based on the clinical evaluation of the patient's signs and symptoms. Deep learning binary-based classification models have been developed to improve the diagnosis but have not yet reached clinical practice, in part due to the heterogeneity of such disorders. Here, we propose a normative model based on autoencoders.
We trained our autoencoder on resting-state functional magnetic resonance imaging (rs-fMRI) data from healthy controls. The model was then tested on schizophrenia (SCZ), bipolar disorder (BD), and attention-deficit hyperactivity disorder (ADHD) patients to estimate how each patient deviated from the norm and associate it with abnormal functional brain networks' (FBNs) connectivity. Rs-fMRI data processing was conducted within the FMRIB Software Library (FSL), which included independent component analysis and dual regression. Pearson's correlation coefficients between the extracted blood oxygen level-dependent (BOLD) time series of all FBNs were calculated, and a correlation matrix was generated for each subject.
We found that the functional connectivity related to the basal ganglia network seems to play an important role in the neuropathology of BD and SCZ, whereas in ADHD, its role is less evident. Moreover, the abnormal connectivity between the basal ganglia network and the language network is more specific to BD. The connectivity between the higher visual network and the right executive control and the connectivity between the anterior salience network and the precuneus networks are the most relevant in SCZ and ADHD, respectively. The results demonstrate that the proposed model could identify functional connectivity patterns that characterize different psychiatric disorders, in agreement with the literature. The abnormal connectivity patterns from the two independent SCZ groups of patients were similar, demonstrating that the presented normative model was also generalizable. However, the group-level differences did not withstand individual-level analysis implying that psychiatric disorders are highly heterogeneous. These findings suggest that a precision-based medical approach, focusing on each patient's specific functional network changes may be more beneficial than the traditional group-based diagnostic classification.
精神疾病的诊断主要基于对患者体征和症状的临床评估。为改善诊断已开发出基于深度学习的二元分类模型，但尚未应用于临床实践，部分原因是此类疾病的异质性。在此，我们提出一种基于自动编码器的规范模型。
我们使用来自健康对照的静息态功能磁共振成像（rs-fMRI）数据训练自动编码器。然后在精神分裂症（SCZ）、双相情感障碍（BD）和注意力缺陷多动障碍（ADHD）患者中测试该模型，以评估每位患者与正常情况的偏离程度，并将其与异常的脑功能网络（FBN）连接性相关联。rs-fMRI数据处理在FMRIB软件库（FSL）中进行，包括独立成分分析和双重回归。计算所有FBN提取的血氧水平依赖（BOLD）时间序列之间的皮尔逊相关系数，并为每个受试者生成相关矩阵。
我们发现，与基底神经节网络相关的功能连接似乎在BD和SCZ的神经病理学中起重要作用，而在ADHD中其作用不太明显。此外，基底神经节网络与语言网络之间的异常连接在BD中更具特异性。在SCZ和ADHD中，分别是高级视觉网络与右侧执行控制之间的连接以及前显著性网络与楔前叶网络之间的连接最为相关。结果表明，所提出的模型能够识别表征不同精神疾病的功能连接模式，与文献一致。来自两个独立SCZ患者组的异常连接模式相似，表明所呈现的规范模型也具有通用性。然而，组水平差异经不起个体水平分析，这意味着精神疾病具有高度异质性。这些发现表明，基于精准的医学方法，关注每位患者特定的功能网络变化可能比传统的基于组的诊断分类更有益。
