Comparisons of SLE-DAS and SLEDAI-2K and classification of disease activity based on the SLE-DAS with reference to patient-reported outcomes

Application of machine learning in assessing disease activity in SLE

OBJECTIVE

SLE is a chronic autoimmune disease with immune complex deposition in various organs, causing inflammation. The Systemic Lupus Erythematosus Disease Activity Index 2000 assesses disease severity but is subjective. This study aimed to construct a machine learning model based on objective laboratory indicators to assess SLE disease activity.

METHODS

A retrospective study was conducted on 319 patients with SLE, collecting their clinical characteristics and laboratory indicators as model-building indicators. Multiple machine learning algorithms were employed to construct models for assessing SLE disease activity.

RESULTS

The patients were divided into two cohorts, cohort 1 used as the training set to build the machine learning models and cohort 2 for external validation. Six laboratory indicators, including anti-dsDNA (IFT), quantitative anti-dsDNA, neutrophils, globulin, proteinuria and NK cells, were selected to construct the SLE disease activity evaluation model. The XGBoost model demonstrated superior performance in distinguishing active SLE, with an area under the receiver operating characteristic curve of 0.934, accuracy of 0.925, sensitivity of 0.969, specificity of 0.750 and F1 score of 0.954.

CONCLUSIONS

This pioneering machine learning model, using objective laboratory indicators, enhances clinical feasibility and provides a novel method for assessing SLE disease activity, that may enable timely evaluation of SLE activity, facilitating preparation for treatment and prognosis.

Evaluation of disease activity in systemic lupus erythematosus using standard deviation of lymphocyte volume combined with red blood cell count and lymphocyte percentage

Systemic lupus erythematosus (SLE) commonly damages the blood system and often manifests as blood cell abnormalities. The performance of biomarkers for predicting SLE activity still requires further improvement. This study aimed to analyze blood cell parameters to identify key indicators for a SLE activity prediction model. Clinical data of 138 patients with SLE (high activity, n = 40; moderate activity, n = 44; mild activity, n = 37; low activity, n = 17) and 100 healthy controls (HCs) were retrospectively analyzed. Data from 89 paired admission-discharge patients with SLE were collected. Differences and associations between blood cell parameters and disease indicators, as well as the relationship between the these parameters and organ damage, were examined. Machine-learning methods were employed to develop a prediction model for disease activity evaluation. Most blood cell parameters (22/26, 84.62%) differed significantly between patients with SLE and HCs. Analysis of 89 paired patients with SLE revealed significant changes in most blood cell parameters at discharge. The standard deviation of lymphocyte volume (SD-V-LY), red blood cell (RBC) count, lymphocyte percentage (LY%), hemoglobin(HGB), hematocrit(HCT), and neutrophil percentage(NE%) correlated with disease activity. By employing machine learning, an optimal model was established to predict active SLE using SD-V-LY, RBC count, and LY% (area under the curve [AUC] = 0.908, sensitivity = 0.811). External validation indicated impressive performance (AUC = 0.940, sensitivity = 0.833). Correlation analysis revealed that SD-V-LY was positively correlated with ESR, IgG, IgA, and IgM but was negatively correlated with C3 and C4. The RBC count was linked to renal and hematopoietic system impairments, whereas LY% was associated with joint/muscle involvement. In conclusion, SD-V-LY is associated with SLE disease activity. SD-V-LY combined with RBC count and LY% contributes to a prediction model, which can be utilized as an effective tool for assessing SLE activity.

Environmental triggers of autoimmunity: The association between bisphenol analogues and systemic lupus erythematosus

The aim of this research was to examine the correlation between the exposure to bisphenol analogues (BPs), such as bisphenol A (BPA), bisphenol F (BPF), and bisphenol S (BPS), and the risk of developing systemic lupus erythematosus (SLE). Ultra performance liquid chromatography/tandem mass spectrometry (UPLC-MS/MS) was utilized to measure the levels of BPA, BPF, and BPS in the urine of 168 female participants diagnosed with SLE and 175 female participants who were deemed healthy controls. Logistic regression models were utilized to assess the connections between levels of bisphenol and the risk of SLE. The findings indicated that levels of BPA and BPF in the urine of individuals with SLE were markedly elevated compared to those in the control group. Higher exposure to BPA and BPF exhibited positive dose-response relationships with increased SLE risk. No significant associations were identified between BPS and the risk of SLE. These findings suggest exposure to BPA and BPF may be implicated as novel environmental triggers in the development of autoimmunity such as SLE. The significantly increased levels of these bisphenol analogues detected in SLE patients versus healthy controls, along with the associations between higher exposures and elevated SLE risk, which offers crucial hints for comprehending how endocrine-disrupting substances contribute to the genesis of autoimmune illnesses. Further research using robust longitudinal assessments of bisphenol analogue exposures is warranted to corroborate these epidemiological findings. Overall, this study highlights potential environmental risk factors for SLE while calling for additional investigation into the impact of bisphenol exposures on autoimmunity development.

Systemic Lupus Erythematosus Disease Activity Score Remission and Low Disease Activity States Discriminate Drug From Placebo and Better Health-Related Quality of Life

OBJECTIVE

Our objective was to evaluate the ability of Systemic Lupus Erythematosus Disease Activity Score (SLE-DAS) remission and low disease activity (LDA) to discriminate active drug from placebo and to discriminate outcomes in the patients' perspective (health-related quality of life [HR-QoL]) in SLE trials.

METHODS

This was a post hoc analysis of the pooled Belimumab in Subjects With SLE (BLISS)-52 (NCT00424476) and BLISS-76 (NCT00410384) trials data. SLE-DAS remission and LDA attainment and discrimination between belimumab and placebo at 52 weeks were compared using chi-square tests. At week 52, 36-item Short Form Health Survey (SF-36) and Functional Assessment of Chronic Illness Therapy Fatigue (FACIT-F) scores were compared between patients attaining SLE-DAS remission versus nonremission and SLE-DAS LDA versus non-LDA using the t-test and Mann-Whitney test. Mean changes from week 0 to 52 in SF-36 and FACIT-F scores were compared between groups using multivariate regression analysis adjusted for baseline scores.

RESULTS

At week 52, significantly more patients attained SLE-DAS LDA taking belimumab 1 mg/kg (17.9% vs 13.0%; P = 0.023; odds ratio [OR] 1.459; relative risk [RR] 1.377; number needed to treat [NNT] 20.4) and 10 mg/kg (21.7% vs 13.0%; P < 0.001; OR 1.853; RR 1.668; NNT 11.5) compared with placebo. Likewise, more patients attained SLE-DAS remission taking belimumab 10 mg/kg compared to placebo (14.7% vs 10.1%; P = 0.019; OR 1.532; RR 1.454; NNT 21.7). At week 52, patients attaining SLE-DAS remission and LDA presented higher SF-36 domain and summary scores (all P < 0.001) and FACIT-F scores (both P < 0.001). Mean improvements from baseline in SF-36 and FACIT-F scores were significantly higher in patients achieving SLE-DAS remission and LDA.

CONCLUSION

SLE-DAS remission and LDA showed discriminant ability for identifying patients receiving active drug in SLE clinical trials. Attainment of these SLE-DAS targets are associated with better HR-QoL.

Health-related quality of life in Chinese SLE patients: evidence from 1568 SLE patients and 2610 healthy controls

OBJECTIVE

To investigate the effects of systemic lupus erythematosus (SLE) on health-related quality of life (HRQOL), the relationship between disease activity and HRQOL, and potential factors affecting HRQOL in Chinese SLE patients.

METHODS

This study recruited 1568 patients and 2610 controls to explore the effects of SLE on HRQOL. The association between disease activity and HRQOL, and the influencing factors of HRQOL were determined in 1568 patients. Then, we prospectively followed 1096 patients to explore the association between reduced disease activity and improved HRQOL, and the influencing factors of improved HRQOL. The Short-Form 36 (SF-36) and SLE disease activity index (SLEDAI) were used to evaluate HRQOL and disease activity.

RESULTS

Chinese SLE patients had lower HRQOL than controls in all domains (P < 0.001), especially in role-physical (RP) and role-emotional (RE). Compared with SLE patients from outside China, the HRQOL of Chinese patients appeared to be higher in mental component summary (MCS) but lower in RP and RE. SLEDAI was negatively correlated with HRQOL, which was validated using the results of a follow-up study, where SLEDAI reduction was positively associated with HRQOL improvements (P < 0.05). Furthermore, personality, life nervous and experiences of adverse life events may influence HRQOL and HRQOL improvements.

CONCLUSION

SLE significantly affected the HRQOL of Chinese patients, especially in RP and RE. Disease activity was negatively correlated with HRQOL. We also found for the first time some factors affecting HRQOL, which can be regarded as the basis for improving the HRQOL of SLE patients.

Performance of a New Instrument for the Measurement of Systemic Lupus Erythematosus Disease Activity: The SLE-DAS

Systemic lupus erythematosus (SLE) is a chronic systemic autoimmune disease that affects multiple organ systems and manifests in a relapsing-remitting pattern. Consequently, it is paramount for rheumatologists to assess disease activity, identify flare-ups, and establish treatment goals for patients with SLE. In 2019, the Systemic Lupus Erythematosus Disease Activity Score (SLE-DAS) was introduced as a novel tool for measuring disease activity. This tool refines the parameters of the established SLE Disease Activity Index 2000 (SLEDAI-2K) to enhance the assessment process. This review aims to provide an introduction to the Systemic Lupus Erythematosus Disease Activity Score (SLE-DAS) and summarizes research on its development, its comparison with existing disease activity measures, and its performance in clinical settings. Literature searches on PubMed using the keyword "SLE-DAS" were conducted, covering publications from March 2019 to September 2023. Studies that compared SLE-DAS with other SLE disease activity measurement tools were reviewed. Findings indicated that SLE-DAS consistently performs on par with, and sometimes better than, traditional measures in assessing clinically meaningful changes, patient improvement, disease activity, health-related quality of life, hospitalization rates, and disease flare-ups. The association between SLE-DAS and mortality rates among patients with SLE, however, remains to be further explored. Although SLE-DAS is a promising and potentially effective tool for measuring SLE disease activity, additional research is needed to confirm its effectiveness and broaden its clinical use.