Machine learning to optimize cerebrospinal fluid dilution for analysis of MRZH reaction.

OBJECTIVES: To create a supervised machine learning algorithm aimed at predicting an optimal cerebrospinal fluid (CSF) dilution when determining virus specific antibody indices to reduce the need for repeated tests. METHODS: The CatBoost model was trained, optimized, and tested on a dataset with five input variables: albumin quotient, immunoglobulin G (IgG) in CSF, IgG quotient (QIgG), intrathecal synthesis (ITS) and limes quotient (LIM IgG). Albumin and IgG concentrations in CSF and serum were performed by immunonephelometry on Atellica NEPH 630 (Siemens Healthineers, Erlangen, Germany) and ITS and LIM IgG were calculated according to Reiber. Concentrations of IgG antibodies to measles, rubella, varicella zoster and herpes simplex 1/2 viruses were analysed in CSF and serum by ELISA (Euroimmun, Lübeck, Germany). Optimal CSF dilution was defined for each virus and used as a classification variable while the standard operating procedure was set to start at 2×-dilution of CSF. RESULTS: The dataset included 571 samples with the imbalanced distribution of the optimal CSF dilutions: 2× dilution n=440, 3× dilution n=109, 4× dilution n=22. The optimized CatBoost model achieved an area under the curve (AUC) score of 0.971, and a test accuracy of 0.900. The model falsely classified 14 (9.9 %) samples of the testing set but reduced the need for repeated testing compared to the standard protocol by 42 %. The output of the CatBoost model is mostly dependant on the QIgG, ITS and CSF IgG variables. CONCLUSIONS: An accurate algorithm was achieved for predicting the optimal CSF dilution, which reduces the number of test repeats.

Higher MRI lesion load in multiple sclerosis is related to the N-glycosylation changes of cerebrospinal fluid immunoglobulin G.

BACKGROUND: Intrathecal clonal expansion of antibody-producing plasma cells in multiple sclerosis (MS) perpetuates central nervous system injury and is associated with active demyelination. Immunoglobulin G (IgG) effector functions are modulated by linked N-glycan structures. The aim of the study was to detect potential differences in N-glycosylation of IgG in serum and cerebrospinal fluid (CSF) and total sera proteins between people with MS and those in whom the diagnosis of MS was excluded. Furthermore, we investigated the association with standard laboratory biomarkers of intrathecal inflammation as well as clinical and neuroradiological disease activity. METHODS: This cross-sectional study included patients with suspected demyelinating disease. MS diagnosis was based on the 2017 McDonald criteria and controls were patients with excluded MS diagnosis. N-glycans were compared with Expanded Disability Status Scale (EDSS), magnetic resonance imaging (MRI) markers of disease activity and biomarkers of intrathecal inflammation (cell count, CSF-IgG concentration, percentage of intrathecal IgG, oligoclonal bands (OCB), virus-specific antibody index (MRZH reaction)). RESULTS: Differences between groups were observed only in the CSF-IgG N-glycome. In MS, the presence of bisecting N-acetylglucosamine (Padj=2.63E-05) and monogalactosylation (Padj=1.49E-06) were more abundant and associated with positive OCBs. N-glycans monogalactosylated at the α6 arm FA2[6]G1 (r = 0.56) and FA2[6]BG1 (r = 0.45) correlated with percentage of intrathecal IgG, but not total CSF-IgG. This trait was also more abundant in MRZH positive people with MS who had higher MRI lesion load (P = 0.018) but unrelated to active lesions or EDSS. CONCLUSIONS: More abundant monogalactosylation of intrathecally synthesized IgG is the most prominent trait in MS and is associated with higher MRI lesion load.

Antibody response and self-reported adverse reactions following vaccination with Comirnaty: a pilot study from a Croatian university hospital.

This study aimed to determine antibody responses against SARS-CoV-2 spike (S) after both BioNTech-Pfizer Comirnaty vaccine doses and study the correlation with self-perceived adverse reactions. Antibodies determination with Elecsys anti-SARS-CoV-2 S assay was performed a day prior to or just before administration of the second dose and 8-13 days after the second dose. Participants selected from a predefined list of the experienced local (injection site reactions) and/or systemic (fatigue, headache, myalgia, arthralgia, chills and fever) post-vaccination adverse reactions. An average 100-fold increase in antibody titre in naive vaccinees was observed between the two time points (median 67 U/mL vs 2841 U/mL, p<0.001). Participants aged below 50 had higher antibody titres (median 99 U/mL vs 26 U/mL, p=0.003 after the first dose; median 3617 U/mL vs 2556 U/mL, p=0.026 after the second dose). All reported adverse reactions were mild-to-moderate, with more participants declaring systemic reactions after the second dose (p=0.001), without a clear correlation with antibody titre.