Huaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China.
Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, OH, 45219, USA.
Eur Child Adolesc Psychiatry. 2021 Jan;30(1):55-64. doi: 10.1007/s00787-020-01483-x. Epub 2020 Feb 1.
Children of individuals with bipolar disorder (bipolar offspring) are at increased risk for developing mood disorders, but strategies to predict mood episodes are unavailable. In this study, we used support vector machine (SVM) to characterize the potential of proton magnetic resonance spectroscopy (H-MRS) in predicting the first mood episode in youth bipolar offspring. From a longitudinal neuroimaging study, 19 at-risk youth who developed their first mood episode (converters), and 19 without mood episodes during follow-up (non-converters) were selected and matched for age, sex and follow-up time. Baseline H-MRS data were obtained from anterior cingulate cortex (ACC) and bilateral ventrolateral prefrontal cortex (VLPFC). Glutamate (Glu), myo-inositol (mI), choline (Cho), N-acetyl aspartate (NAA), and phosphocreatine plus creatine (PCr + Cr) levels were calculated. SVM with a linear kernel was adopted to classify converters and non-converters based on their baseline metabolites. SVM allowed the significant classification of converters and non-converters across all regions for Cho (accuracy = 76.0%), but not for other metabolites. Considering all metabolites within each region, SVM allowed the significant classification of converters and non-converters for left VLPFC (accuracy = 76.5%), but not for right VLPFC or ACC. The combined mI, PCr + Cr, and Cho from left VLPFC achieved the highest accuracy differentiating converters from non-converters (79.0%). Our findings from this exploratory study suggested that H-MRS levels of mI, Cho, and PCr + Cr from left VLPFC might be useful to predict the development of first mood episode in youth bipolar offspring using machine learning. Future studies that prospectively examine and validate these metabolites as predictors of mood episodes in high-risk individuals are necessary.
儿童患有双相情感障碍（双相后代）的风险增加，患有情绪障碍，但目前尚无预测情绪发作的策略。在这项研究中，我们使用支持向量机（SVM）来描述质子磁共振波谱（H-MRS）在预测青年双相情感障碍后代首次情绪发作中的潜力。从一项纵向神经影像学研究中，选择了 19 名出现首次情绪发作的高危青年（转化者）和 19 名在随访期间没有情绪发作的青年（非转化者），并进行了年龄、性别和随访时间的匹配。基线 H-MRS 数据来自前扣带回皮层（ACC）和双侧腹外侧前额叶皮层（VLPFC）。计算谷氨酸（Glu）、肌醇（mI）、胆碱（Cho）、N-乙酰天冬氨酸（NAA）和磷酸肌酸加肌酸（PCr+Cr）水平。采用线性核 SVM 基于基线代谢物对转化者和非转化者进行分类。SVM 允许 Cho 对转化者和非转化者进行跨所有区域的显著分类（准确率=76.0%），但其他代谢物则不行。考虑每个区域内的所有代谢物，SVM 允许对左 VLPFC 中的转化者和非转化者进行显著分类（准确率=76.5%），但对右 VLPFC 或 ACC 则不行。左 VLPFC 中的 mI、PCr+Cr 和 Cho 的联合分析可实现对转化者和非转化者的最高准确率（79.0%）。本探索性研究的结果表明，左 VLPFC 中的 mI、Cho 和 PCr+Cr 的 H-MRS 水平可能有助于使用机器学习预测青年双相情感障碍后代首次情绪发作的发展。有必要进行前瞻性研究来检验和验证这些代谢物作为高危人群情绪发作的预测因子。
