Department of Neurology with Institute of Translational Neurology, University of Münster, Münster, Germany.
Institute of Medical Informatics, University of Münster, Münster, Germany.
J Neuroimmunol. 2020 Apr 15;341:577171. doi: 10.1016/j.jneuroim.2020.577171. Epub 2020 Jan 27.
Distinguishing neurosarcoidosis (NS) from multiple sclerosis (MS) remains challenging and available parameters lack discriminatory power. Comprehensive flow cytometry data of blood and CSF leukocytes of patients with NS (n = 24), MS (n = 49) and idiopathic intracranial hypertension (IIH, n = 52) were analyzed by machine learning algorithms. NS featured a specific immune cell pattern with increased activated CD4+ T cells in CSF and increased plasma cells in blood. Combining blood and CSF parameters improved the differentiation. We thereby identify and independently validate a multi-dimensional model of blood and CSF supporting the difficult differential diagnosis between NS and MS.
鉴别神经结节病（NS）和多发性硬化症（MS）仍然具有挑战性，现有的参数缺乏鉴别能力。通过机器学习算法分析了 NS（n=24）、MS（n=49）和特发性颅内高压（IIH，n=52）患者的血液和 CSF 白细胞的综合流式细胞术数据。NS 具有特定的免疫细胞模式，CSF 中激活的 CD4+T 细胞增加，血液中浆细胞增加。结合血液和 CSF 参数可提高鉴别能力。因此，我们确定并独立验证了一个血液和 CSF 的多维模型，支持 NS 和 MS 之间的困难鉴别诊断。
