Expression and diagnostic value of interleukin-22 in rheumatoid arthritis-associated interstitial lung disease.

Rheumatoid arthritis-associated interstitial lung disease (RA-ILD) is characterized by a high incidence and mortality rate, highlighting the need for biomarkers to detect ILD early in RA patients. Previous studies have shown the protective effects of Interleukin-22 (IL-22) in pulmonary fibrosis using mouse models. This study aims to assess IL-22 expression in RA-ILD to validate foundational experiments and explore its diagnostic value. The study included 66 newly diagnosed RA patients (33 with ILD, 33 without ILD) and 14 healthy controls (HC). ELISA was utilized to measure IL-22 levels and perform intergroup comparisons. The correlation between IL-22 levels and the severity of RA-ILD was examined. Logistic regression analysis was employed to screen potential predictive factors for RA-ILD risk and establish a predictive nomogram. The diagnostic value of IL-22 in RA-ILD was assessed using ROC. Subsequently, the data were subjected to 30-fold cross-validation. IL-22 levels in the RA-ILD group were lower than in the RA-No-ILD group and were inversely correlated with the severity of RA-ILD. Logistic regression analysis identified IL-22, age, smoking history, anti-mutated citrullinated vimentin antibody (MCV-Ab), and mean corpuscular hemoglobin concentration (MCHC) as independent factors for distinguishing between the groups. The diagnostic value of IL-22 in RA-ILD was moderate (AUC = 0.75) and improved when combined with age, smoking history, MCV-Ab and MCHC (AUC = 0.97). After 30-fold cross-validation, the average AUC was 0.886. IL-22 expression is dysregulated in the pathogenesis of RA-ILD. This study highlights the potential of IL-22, along with other factors, as a valuable biomarker for assessing RA-ILD occurrence and progression.

Identification of discriminatory factors and construction of nomograms for differentiating AOSD and sepsis.

OBJECTIVE: This study aimed to develop nomogram prediction models to differentiate between adult-onset Still's disease (AOSD) and sepsis. METHODS: We retrospectively collected laboratory test data from 107 hospitalized patients with AOSD and sepsis at the Affiliated Hospital of Xuzhou Medical University. Multivariate binary logistic regression was used to develop nomogram models using arthralgia, WBC, APTT, creatinine, PLT, and ferritin as independent factors. The performance of the model was evaluated by the bootstrap consistency index and calibration curve. RESULTS: Model 1 had an AUC of 0.98 (95% CI, 0.96-1.00), specificity of 0.98, and sensitivity of 0.94. Model 2 had an AUC of 0.96 (95% CI, 0.93-1.00), specificity of 0.92, and sensitivity of 0.94. The fivefold cross-validation yielded an accuracy (ACC) of 0.92 and a kappa coefficient of 0.83 for Model 1, while for Model 2, the ACC was 0.87 and the kappa coefficient was 0.74. CONCLUSION: The nomogram models developed in this study are useful tools for differentiating between AOSD and sepsis. Key Points • The differential diagnosis between AOSD and sepsis has always been a challenge • Delayed treatment of AOSD may lead to serious complications • We developed two nomogram models to distinguish AOSD from sepsis, which were not previously reported • Our models can be used to guide clinical practice with good discrimination.

Establishment of a differential diagnosis method and an online prediction platform for AOSD and sepsis based on gradient boosting decision trees algorithm.

OBJECTIVE: The differential diagnosis between adult-onset Still's disease (AOSD) and sepsis has always been a challenge. In this study, a machine learning model for differential diagnosis of AOSD and sepsis was developed and an online platform was developed to facilitate the clinical application of the model. METHODS: All data were collected from 42 AOSD patients and 50 sepsis patients admitted to Affiliated Hospital of Xuzhou Medical University from December 2018 to December 2021. In addition, 5 AOSD patients and 10 sepsis patients diagnosed in our hospital after March 2022 were collected for external validation. All models were built using the scikit-learn library (version 1.0.2) in Python (version 3.9.7), and feature selection was performed using the SHAP (Shapley Additive exPlanation) package developed in Python. RESULTS: The results showed that the gradient boosting decision tree(GBDT) optimization model based on arthralgia, ferritin × lymphocyte count, white blood cell count, ferritin × platelet count, and α1-acid glycoprotein/creatine kinase could well identify AOSD and sepsis. The training set interaction test (AUC: 0.9916, ACC: 0.9457, Sens: 0.9556, Spec: 0.9578) and the external validation also achieved satisfactory results (AUC: 0.9800, ACC: 0.9333, Sens: 0.8000, Spec: 1.000). We named this discrimination method AIADSS (AI-assisted discrimination of Still's disease and Sepsis) and created an online service platform for practical operation, the website is http://cppdd.cn/STILL1/ . CONCLUSION: We created a method for the identification of AOSD and sepsis based on machine learning. This method can provide a reference for clinicians to formulate the next diagnosis and treatment plan.