Miller Jacob M, Beales Jeremy T, Montierth Matthew D, Briggs Farren B, Frodsham Scott F, Davis Mary Feller
Department of Microbiology and Molecular Biology, Brigham Young University, Provo, UT 84602, USA.
Department of Population and Quantitative Health Sciences, Case Western Reserve University, Cleveland, OH 44106, USA.
Int J Environ Res Public Health. 2021 Mar 23;18(6):3318. doi: 10.3390/ijerph18063318.
Multiple sclerosis (MS) is an immune-mediated, demyelinating disease of the central nervous system. In this study, an MS cohort and healthy controls were stratified into Caucasian and African American groups. Patient hematological profiles-composed of complete blood count (CBC) and complete metabolic panel (CMP) test values-were analyzed to identify differences between MS cases and controls and between patients with different MS subtypes. Additionally, random forest models were used to determine the aggregate utility of common hematological tests in determining MS disease status and subtype. The most significant and relevant results were increased bilirubin and creatinine in MS cases. The random forest models achieved some success in differentiating between MS cases and controls (AUC values: 0.725 and 0.710, respectively) but were not successful in differentiating between subtypes. However, larger samples that adjust for possible confounding variables, such as treatment status, may reveal the value of these tests in differentiating between MS subtypes.
多发性硬化症(MS)是一种免疫介导的中枢神经系统脱髓鞘疾病。在本研究中,一个MS队列和健康对照被分为白种人和非裔美国人组。分析了由全血细胞计数(CBC)和全代谢组(CMP)测试值组成的患者血液学特征,以确定MS病例与对照之间以及不同MS亚型患者之间的差异。此外,使用随机森林模型来确定常见血液学检测在确定MS疾病状态和亚型方面的综合效用。最显著且相关的结果是MS病例中的胆红素和肌酐升高。随机森林模型在区分MS病例与对照方面取得了一定成功(AUC值分别为0.725和0.710),但在区分亚型方面未成功。然而,调整可能的混杂变量(如治疗状态)后的更大样本,可能会揭示这些检测在区分MS亚型方面的价值。