SVM-Based Model Combining Patients' Reported Outcomes and Lymphocyte Phenotypes of Depression in Systemic Lupus Erythematosus

Urine-derived stem cells from patients alleviate lupus nephritis via regulating macrophage polarization in a CXCL14-dependent manner

AIM

Mesenchymal stem cells (MSC) exhibit hopeful therapeutic potential for the treatment of lupus nephritis (LN). Nevertheless, most MSC are harvested invasively and only transplantation of allogeneic MSC takes effect. Urine-derived stem cells (USC) can be obtained by noninvasive and safe access. Whether USC can be used for autologous stem cell transplantation to treat LN remains unknown.

MATERIALS AND METHODS

USC were harvested from healthy individuals, systemic lupus erythematosus (SLE) patients with no LN (NLN) and LN patients. The biological characteristics and immunomodulatory ability of three USC types were compared. Therapeutic value of USC for LN in MRL/lpr mice and influence of USC on macrophages were assessed. We further explored the mechanism of USC from LN patients (LN-USC) on macrophage polarization.

KEY FINDINGS

LN-USC exhibited faster proliferation and less apoptosis, significantly upregulated regulatory T cells (Treg) and downregulated antibody secreting cells (ASC). Importantly, LN-USC showed the best effect on LN in MRL/lpr mice among the three USC types. Additionally, LN-USC markedly downregulated M1 polarization of macrophages when injected into MRL/lpr mice or co-cultured with human acute monocytic leukemia cell (THP1)-derived M0 macrophages. Moreover, the regulative effect on macrophage polarization and therapeutic efficacy on LN were reversed after knocking down C-X-C motif chemokine ligand 14 (CXCL14) of LN-USC.

SIGNIFICANCE

These results suggested that transplantation of LN-USC alleviated LN in MRL/lpr mice via inhibiting M1 polarization of macrophages in a CXCL14-dependent manner, indicating that USC serve as a prospective candidate for autologous stem cell therapy of LN.

Organ-based characterization of B cells in patients with systemic lupus erythematosus

Systemic lupus erythematosus (SLE) is a chronic, inflammatory, and progressive autoimmune disease. The unclear pathogenesis, high heterogeneity, and prolonged course of the disease present significant challenges for effective clinical management of lupus patients. Dysregulation of the immune system and disruption of immune tolerance, particularly through the abnormal activation of B lymphocytes and the production of excessive autoantibodies, lead to widespread inflammation and tissue damage, resulting in multi-organ impairment. Currently, there is no systematic review that examines the specificity of B cell characteristics and pathogenic mechanisms across various organs. This paper reviews current research on B cells in lupus patients and summarizes the distinct characteristics of B cells in different organs. By integrating clinical manifestations of organ damage in patients with a focus on the organ-specific features of B cells, we provide a new perspective on enhancing the efficacy of lupus-targeted B cell therapy strategies.

Application of machine learning in depression risk prediction for connective tissue diseases

This study retrospectively collected clinical data from 480 patients with connective tissue diseases (CTDs) at Nanjing First Hospital between August 2019 and December 2023 to develop and validate a multi-classification machine learning (ML) model for assessing depression risk. Addressing the limitations of traditional assessment tools, six ML models were constructed using univariate analysis and the LASSO algorithm, with the categorical boosting (Catboost) model emerging as the best performer, demonstrating strong predictive ability across different depression severity levels (none_F1 = 0.879, mild_F1 = 0.627, moderate and severe_F1 = 0.588). Additionally, the study provided an interpretation of the best-performing model using SHAP and developed a user-friendly R Shiny application ( https://macnomogram.shinyapps.io/Catboost/ ) to facilitate clinical use. The findings suggest that the Catboost model represents a significant advancement in assessing depression risk among CTD patients, highlighting the potential of ML in enhancing mental health management for this patient population.

Study on risk factor analysis and model prediction of hyperuricemia in different populations

Objectives

The purpose of the present study was to explore the influencing factors of hyperuricemia (HUA) in different populations in Shandong Province based on clinical biochemical indicators. A prediction model for HUA was constructed to aid in the early prevention and screening of HUA.

Methods

In total, 705 cases were collected from five hospitals, and the risk factors were analyzed by Pearson correlation analysis, binary logistic regression, and receiver operating characteristic (ROC) curve in the gender and age groups. All data were divided into a training set and test set (7:3). The training set included age, gender, total protein (TP), low-density lipoprotein cholesterol (LDL-C), and 15 other indicators. The random forest (RF) and support vector machine (SVM) methods were used to build the HUA model, and model performances were evaluated through 10-fold cross-validation to select the optimal method. Finally, features were extracted, and the ROC curve of the test set was generated.

Results

TP, LDL-C, and glucose (GLU) were risk factors for HUA, and the area under the curve (AUC) value of the SVM validation set was 0.875.

Conclusion

The SVM model based on clinical biochemical indicators has good predictive ability for HUA, thus providing a reference for the diagnosis of HUA and the development of an HUA prediction model.

Personalized prediction of mortality in patients with acute ischemic stroke using explainable artificial intelligence

BACKGROUND

Research into the acute kidney disease (AKD) after acute ischemic stroke (AIS) is rare, and how clinical features influence its prognosis remain unknown. We aim to employ interpretable machine learning (ML) models to study AIS and clarify its decision-making process in identifying the risk of mortality.

METHODS

We conducted a retrospective cohort study involving AIS patients from January 2020 to June 2021. Patient data were randomly divided into training and test sets. Eight ML algorithms were employed to construct predictive models for mortality. The performance of the best model was evaluated using various metrics. Furthermore, we created an artificial intelligence (AI)-driven web application that leveraged the top ten most crucial features for mortality prediction.

RESULTS

The study cohort consisted of 1633 AIS patients, among whom 257 (15.74%) developed subacute AKD, 173 (10.59%) experienced AKI recovery, and 65 (3.98%) met criteria for both AKI and AKD. The mortality rate stood at 4.84%. The LightGBM model displayed superior performance, boasting an AUROC of 0.96 for mortality prediction. The top five features linked to mortality were ACEI/ARE, renal function trajectories, neutrophil count, diuretics, and serum creatinine. Moreover, we designed a web application using the LightGBM model to estimate mortality risk.

CONCLUSIONS

Complete renal function trajectories, including AKI and AKD, are vital for fitting mortality in AIS patients. An interpretable ML model effectively clarified its decision-making process for identifying AIS patients at risk of mortality. The AI-driven web application has the potential to contribute to the development of personalized early mortality prevention.

Systemic lupus in the era of machine learning medicine

Artificial intelligence and machine learning applications are emerging as transformative technologies in medicine. With greater access to a diverse range of big datasets, researchers are turning to these powerful techniques for data analysis. Machine learning can reveal patterns and interactions between variables in large and complex datasets more accurately and efficiently than traditional statistical methods. Machine learning approaches open new possibilities for studying SLE, a multifactorial, highly heterogeneous and complex disease. Here, we discuss how machine learning methods are rapidly being integrated into the field of SLE research. Recent reports have focused on building prediction models and/or identifying novel biomarkers using both supervised and unsupervised techniques for understanding disease pathogenesis, early diagnosis and prognosis of disease. In this review, we will provide an overview of machine learning techniques to discuss current gaps, challenges and opportunities for SLE studies. External validation of most prediction models is still needed before clinical adoption. Utilisation of deep learning models, access to alternative sources of health data and increased awareness of the ethics, governance and regulations surrounding the use of artificial intelligence in medicine will help propel this exciting field forward.