BackgroundIdentification of universal biomarkers to predict systemic lupus erythematosus (SLE) flares is challenging due to the heterogeneity of the disease. Several biomarkers have been reported. However, the data of validated biomarkers to use as a predictor for lupus flares show variation. This study aimed to identify the biomarkers that are sensitive and specific to predict lupus flares.MethodsOne hundred and twenty-four SLE patients enrolled in this study and were prospectively followed up. The evaluation of disease activity achieved by the SLE disease activity index (SLEDAI-2K) and clinical SLEDAI (modified SLEDAI). Patients with active SLE were categorized into renal or non-renal flares. Serum cytokines were measured by multiplex bead-based flow cytometry. The correlation and logistic regression analysis were performed.ResultsLevels of IFN-α, MCP-1, IL-6, IL-8, and IL-18 significantly increased in active SLE and correlated with clinical SLEDAI. Complement C3 showed a weakly negative relationship with IFN-α and IL-18. IL-18 showed the highest positive likelihood ratios for active SLE. Multiple logistic regression analysis showed that IL-6, IL-8, and IL-18 significantly increased odds ratio (OR) for active SLE at baseline while complement C3 and IL-18 increased OR for active SLE at 12 weeks. IL-18 and IL-6 yielded higher sensitivity and specificity than anti-dsDNA and C3 to predict active renal and active non-renal, respectively.ConclusionThe heterogeneity of SLE pathogenesis leads to different signaling mechanisms and mediates through several cytokines. The monitoring of cytokines increases the sensitivity and specificity to determine SLE disease activity. IL-18 predicts the risk of active renal SLE while IL-6 and IL-8 predict the risk of active non-renal. The sensitivity and specificity of these cytokines are higher than the anti-dsDNA or C3. We propose to use the serum level of IL-18, IL-6, and IL-8 to monitor SLE disease activity in clinical practice.
Transformer-based language models, more specifically BERT-based architectures have achieved state-of-the-art performance in many downstream tasks. However, for a relatively low-resource language such as Thai, the choices of models are limited to training a BERT-based model based on a much smaller dataset or finetuning multi-lingual models, both of which yield suboptimal downstream performance. Moreover, large-scale multi-lingual pretraining does not take into account language-specific features for Thai. To overcome these limitations, we pretrain a language model based on RoBERTa-base architecture on a large, deduplicated, cleaned training set (78GB in total size), curated from diverse domains of social media posts, news articles and other publicly available datasets. We apply text processing rules that are specific to Thai most importantly preserving spaces, which are important chunk and sentence boundaries in Thai before subword tokenization. We also experiment with word-level, syllable-level and SentencePiece tokenization with a smaller dataset to explore the effects on tokenization on downstream performance. Our model wangchanberta-baseatt-spm-uncased trained on the 78.5GB dataset outperforms strong baselines (NBSVM, CRF and ULMFit) and multi-lingual models (XLMR and mBERT) on both sequence classification and token classification tasks in human-annotated, mono-lingual contexts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.