# Machine learning for predicting thrombotic recurrence in antiphospholipid syndrome

## TL;DR

This paper explores using machine learning, specifically XGB, to better predict thrombotic recurrence in antiphospholipid syndrome, improving personalized treatment strategies.

## Contribution

The study introduces XGB as a superior machine learning model for predicting thrombotic recurrence in antiphospholipid syndrome.

## Key findings

- XGB outperformed other models in predicting thrombotic recurrence with high accuracy and AUC.
- Renal impairment, age, and lupus anticoagulant were identified as key predictors of recurrence.
- Machine learning can enhance personalized risk stratification and optimize anticoagulation strategies.

## Abstract

Thrombotic antiphospholipid syndrome (TAPS) is an autoimmune disorder associated with a high risk of recurrent thromboembolic events. Despite advances in anticoagulation, predicting recurrence remains challenging, underscoring the need for more precise risk stratification to optimize personalized treatment. Traditional predictive models struggle to integrate the complexity of clinical and biochemical risk factors, creating an opportunity for machine learning to enhance prognostic accuracy.

In this study, we evaluated the performance of the extreme gradient boosting (XGB) model in predicting recurrent thrombotic events in TAPS, compared with other machine learning algorithms.

Demographic and clinical data were initially included, and model performance was assessed through multiple metrics, such as accuracy, specificity, precision, and the area under the receiver operating characteristic curve.

XGB outperformed all other models, achieving the highest area under the receiver operating characteristic curve and accuracy, among other evaluated parameters, demonstrating robust predictive capabilities. Key predictors included renal impairment, age, and the presence of lupus anticoagulant, reinforcing the clinical relevance of these factors in risk assessment.

These findings highlight the potential of XGB to improve risk stratification and support clinical decision-making in TAPS. By identifying critical predictors, this approach may optimize anticoagulation strategies and enhance resource allocation. However, further validation in larger cohorts and prospective studies is necessary before clinical integration.

•Novel methodologies for predicting an accurate thrombotic recurrence in antiphospholipid syndrome are needed.•Artificial intelligence can predict thrombotic recurrence in patients with antiphospholipid syndrome.•Renal insufficiency, age, and positive lupus anticoagulant are the main key predictors of thrombotic recurrence.•Machine learning algorithms enable personalized risk stratification and optimize anticoagulation strategies.

Novel methodologies for predicting an accurate thrombotic recurrence in antiphospholipid syndrome are needed.

Artificial intelligence can predict thrombotic recurrence in patients with antiphospholipid syndrome.

Renal insufficiency, age, and positive lupus anticoagulant are the main key predictors of thrombotic recurrence.

Machine learning algorithms enable personalized risk stratification and optimize anticoagulation strategies.