Targeted metabolomics combined with machine learning to identify and validate new biomarkers for early SLE diagnosis and disease activity.

BACKGROUND: The early diagnosis of systemic lupus erythematosus (SLE) and the assessment of disease activity progression remain a great challenge. Targeted metabolomics has great potential to identify new biomarkers of SLE. METHODS: Serum from 44 healthy participants and 89 SLE patients were analyzed using HM400 high-throughput targeted metabolomics. Machine learning (ML) with seven learning models and trained the model several times iteratively selected the two best prediction model in a competitive way, which were independent validated by enzyme-linked immunosorbent (ELISA) with 90 SLE patients. RESULTS: In this study, 146 differential metabolites, most of them organic acids, amino acids, and bile acids, were detected between patients with initial SLE and healthy participants, and 8 potential biomarkers were found by intersection of ML and statistics (area under the curve [AUC] > 0.95) showing a significant positive correlation with clinical indicators. In addition, we identified and validated 2 potential biomarkers for SLE classification (P < 0.05, AUC > 0.775; N-Methyl-L-glutamic acid, L-2-aminobutyric acid) showing a significant correlation with the SLE Disease Activity Index. These differential metabolites were mainly involved in metabolic pathways, amino acid biosynthesis, 2-oxocarboxylic acid metabolism and other pathways. CONCLUSION: This study indicated that the tricarboxylic acid cycle might be associated with SLE drug therapy. We identified 8 diagnostic models biomarkers and 2 biomarkers that could be used to identify initial SLE and distinguish different activity degree, which will promote the development of new tools for the diagnosis and evaluation of SLE.

Obstetric Risk Factors and Serological Characteristics of Early-Onset Neonates Bacterial Infections.

Purpose: To analyze the obstetric high-risk factors and serological characteristics of early-onset neonatal bacterial infections (EONBI). Methods: 119 neonates with early-onset bacterial infection who were admitted to the neonatal ward of our hospital from October 2020 to December 2021 were recorded as the study group, and 100 neonates without bacterial infection who were admitted during the same period were used as the reference group. Comparative analysis of obstetric high-risk factors and serological characteristics of EONBI. Results: There was no statistical difference between the two groups in terms of gender and age at admission (P > 0.05). The gestational age and birth weight of newborns in the study group were lower than those in the reference group (P < 0.001). Comparing the maternal factors of EONBI between the two groups, there was no statistical difference in age, number of obstetric inspections, whether to use antibiotics, and mode of delivery (P > 0.05). Univariate analysis showed that preterm birth, unexplained asphyxia, fecal contamination of amniotic fluid, maternal infection during pregnancy, and premature rupture of membranes ≥18 h were significantly associated with EONBI (P < 0.05); while there was no significant difference between the two groups in the comparison between diabetic mother and child and maternal fever at delivery (P > 0.05). Multifactorial analysis showed that preterm birth, fecal contamination of amniotic fluid, maternal infection during pregnancy, and premature rupture of membranes ≥18 h had a good multivariate dependence on EONBI (P < 0.05), while there was no significant association with unexplained asphyxia, diabetic mother and child, and maternal fever at delivery (P > 0.05). The incidence of neonatal temperature >37.9°C was higher in the study group than in the reference group (P < 0.05), and there were no statistical differences in the comparison of other clinical manifestations (P > 0.05). The CRP level of neonates in the study group (47.33 ± 4.14) mg/L was higher than that of the reference group (4.84 ± 1.03) mg/L (P < 0.001). The WBC level of neonates in the study group (5.64 ± 1.18) 109/L was higher than that of the reference group (0.28 ± 0.04) 109/L (P < 0.001). The PCT level of neonates in the study group (5.41 ± 0.85) µg/L was higher than that of the reference group (0.24 ± 0.07) µg/L (P < 0.001). Conclusion: EONBI is closely associated with several obstetric high-risk factors, including preterm birth, fecal contamination of amniotic fluid, maternal infection during pregnancy, and premature rupture of membranes ≥18 h; EONBI has no specific symptoms and signs, but serum CRP, WBC, and PCT levels are significantly higher than those of newborns without co-infection with bacteria.