Weng Ruiyuan, Xu Yudian, Gao Xinjie, Cao Linlin, Su Jiabin, Yang Heng, Li He, Ding Chenhuan, Pu Jun, Zhang Meng, Hao Jiheng, Xu Wei, Ni Wei, Qian Kun, Gu Yuxiang
Department of Neurosurgery, Huashan Hospital of Fudan University, Shanghai, 200040, P. R. China.
Neurosurgical Institute of Fudan University, Shanghai, 201107, P. R. China.
Adv Sci (Weinh). 2025 Feb;12(8):e2405580. doi: 10.1002/advs.202405580. Epub 2024 Dec 31.
Moyamoya disease (MMD) is a progressive cerebrovascular disorder that increases the risk of intracranial ischemia and hemorrhage. Timely diagnosis and intervention can significantly reduce the risk of new-onset stroke in patients with MMD. However, the current diagnostic methods are invasive and expensive, and non-invasive diagnosis using biomarkers of MMD is rarely reported. To address this issue, nanoparticle-enhanced laser desorption/ionization mass spectrometry (LDI MS) was employed to record serum metabolic fingerprints (SMFs) with the aim of establishing a non-invasive diagnosis method for MMD. Subsequently, a diagnostic model was developed based on deep learning algorithms, which exhibited high accuracy in differentiating the MMD group from the HC group (AUC = 0.958, 95% CI of 0.911 to 1.000). Additionally, hierarchical clustering analysis revealed a significant association between SMFs across different groups and vascular cognitive impairment in MMD. This approach holds promise as a novel and intuitive diagnostic method for MMD. Furthermore, the study may have broader implications for the diagnosis of other neurological disorders.
烟雾病（MMD）是一种进行性脑血管疾病，会增加颅内缺血和出血的风险。及时诊断和干预可显著降低烟雾病患者新发中风的风险。然而，目前的诊断方法具有侵入性且费用高昂，利用烟雾病生物标志物进行的非侵入性诊断鲜有报道。为解决这一问题，采用纳米颗粒增强激光解吸/电离质谱法（LDI MS）记录血清代谢指纹图谱（SMF），旨在建立一种烟雾病的非侵入性诊断方法。随后，基于深度学习算法开发了一种诊断模型，该模型在区分烟雾病组和健康对照组（HC组）时表现出很高的准确性（AUC = 0.958，95% CI为0.911至1.000）。此外，层次聚类分析显示不同组间的血清代谢指纹图谱与烟雾病中的血管性认知障碍之间存在显著关联。这种方法有望成为一种新颖且直观的烟雾病诊断方法。此外，该研究可能对其他神经系统疾病的诊断具有更广泛的意义。
