Kim Minhoe, Sim Sunkyung, Yang Jaeseok, Kim Minchul
Department of Computer Convergence Software, Korea University, Sejong, Republic of Korea.
Department of Radiology, Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Seoul, Republic of Korea.
Front Hum Neurosci. 2023 Jun 1;17:1202103. doi: 10.3389/fnhum.2023.1202103. eCollection 2023.
Headache is among the most frequent symptoms after coronavirus disease 2019 (COVID-19), so-called long COVID syndrome. Although distinct brain changes have been reported in patients with long COVID, such reported brain changes have not been used for predictions and interpretations in a multivariate manner. In this study, we applied machine learning to assess whether individual adolescents with long COVID can be accurately distinguished from those with primary headaches.
Twenty-three adolescents with long COVID headaches with the persistence of headache for at least 3 months and 23 age- and sex-matched adolescents with primary headaches (migraine, new daily persistent headache, and tension-type headache) were enrolled. Multivoxel pattern analysis (MVPA) was applied for disorder-specific predictions of headache etiology based on individual brain structural MRI. In addition, connectome-based predictive modeling (CPM) was also performed using a structural covariance network.
MVPA correctly classified long COVID patients from primary headache patients, with an area under the curve of 0.73 (accuracy = 63.4%; permutation = 0.001). The discriminating GM patterns exhibited lower classification weights for long COVID in the orbitofrontal and medial temporal lobes. The CPM using the structural covariance network achieved an area under the curve of 0.81 (accuracy = 69.5%; permutation = 0.005). The edges that classified long COVID patients from primary headache were mainly comprising thalamic connections.
The results suggest the potential value of structural MRI-based features for classifying long COVID headaches from primary headaches. The identified features suggest that the distinct gray matter changes in the orbitofrontal and medial temporal lobes occurring after COVID, as well as altered thalamic connectivity, are predictive of headache etiology.
头痛是2019冠状病毒病（COVID-19）后最常见的症状之一，即所谓的“长新冠”综合征。尽管已有报道称“长新冠”患者存在明显的脑部变化，但这些报道的脑部变化尚未用于多变量预测和解释。在本研究中，我们应用机器学习来评估患有“长新冠”的青少年个体是否能与原发性头痛患者准确区分开来。
招募了23名头痛持续至少3个月的“长新冠”头痛青少年患者以及23名年龄和性别匹配的原发性头痛（偏头痛、新发性每日持续性头痛和紧张型头痛）青少年患者。基于个体脑结构MRI，应用多体素模式分析（MVPA）对头痛病因进行疾病特异性预测。此外，还使用结构协方差网络进行基于连接组的预测建模（CPM）。
MVPA能够正确区分“长新冠”患者和原发性头痛患者，曲线下面积为0.73（准确率=63.4%；置换检验=0.001）。在眶额叶和颞内侧叶，区分性的灰质模式对“长新冠”的分类权重较低。使用结构协方差网络的CPM曲线下面积为0.81（准确率=69.5%；置换检验=0.005）。区分“长新冠”患者和原发性头痛患者的边缘主要包括丘脑连接。
结果表明基于结构MRI的特征在区分“长新冠”头痛和原发性头痛方面具有潜在价值。所确定的特征表明，COVID后眶额叶和颞内侧叶出现的明显灰质变化以及丘脑连接改变可预测头痛病因。
