# Machine learning-based identification of factors associated with spontaneous abortion in patients with Systemic lupus erythematosus (SLE): Insights from the Egyptian College of Rheumatology (ECR)–SLE cohort

## TL;DR

This study uses machine learning to identify factors linked to spontaneous abortion in women with lupus, showing better performance than traditional methods.

## Contribution

The study introduces a high-performing XGBoost model to identify SLE-SA risk factors using clinical data from a large Egyptian cohort.

## Key findings

- XGBoost outperformed logistic regression with an AUC of 0.99 versus 0.78.
- Positive antiphospholipid antibodies, low complement 3, and longer disease duration were key predictors of spontaneous abortion.
- Hypertension, mucocutaneous ulcers, and use of anticoagulants and steroids were also significant factors.

## Abstract

Systemic lupus erythematosus (SLE), an autoimmune disease, predominantly affects women and is associated with an increased risk of spontaneous abortion (SA). However, traditional analytical methods found a modest relationship between some factors and SLE-SA and were limited to a small sample size, frequently associated with poor predictive performance.

This study aimed to apply and evaluate an Extreme Gradient Boosting (XGBoost) model using routinely collected clinical data to identify patterns associated with spontaneous abortion in women with SLE and to identify the key variables associated with this outcome.

The study included adult SLE women from the Egyptian College of Rheumatology (ECR)-SLE cohort, a national multicenter study, which had available SA data. SA was defined as unexplained pregnancy loss up to 20 weeks of gestation. Patients’ demographics, clinical manifestations, SLE disease activity index (SLEDAI), therapeutic and laboratory data were used as input variables for the logistic regression (LR) and XGBoost models. We evaluated the performance of both the XGBoost and LR models by calculating the area under the receiver operating characteristic curve (AUC) for each model, and then compared these AUC values to assess which model better distinguished between patients with and without SA. The importance and direction of each variable contributing to the risk of SA were evaluated using SHapley Additive exPlanation (SHAP).

A total of 3296 SLE women (mean ± SD age: 32.5 ± 10.1 years; median disease duration: 48 months) were included. The mean SLEDAI score was 11.3 ± 9.5. About 13.9% of the patients included had at least one abortion. Optimized XGBoost performed better (AUC 0.99) compared with LR (AUC 0.78). Positive antiphospholipid antibodies, low complement 3, longer disease duration, hypertension and the presence of mucocutaneous ulcers, as well as anticoagulants and steroid use, were among the important factors associated with SA in SLE patients.

Using information obtained in the clinical settings, the XGBoost identified variables associated with SA in women with SLE, including positive antiphospholipid antibodies, low complement 3 levels and longer disease duration. Further, longitudinal studies are necessary to evaluate the clinical utility of the proposed classification model.