# A Combined‐Mode Machine Learning Model for Predicting Stroke Recurrence During Hospitalization in Patients with Acute Minor Ischemic Stroke

## TL;DR

This study uses machine learning to predict stroke recurrence in patients with minor strokes, aiming to help doctors identify high-risk patients.

## Contribution

The study introduces machine learning models specifically for predicting in-hospital stroke recurrence in acute minor ischemic stroke patients.

## Key findings

- Machine learning models outperformed traditional GLM in predicting stroke recurrence.
- Light gradient boosting (LGB) showed the most significant improvement in AUC after optimization.
- The models were developed using data from 322,135 patients across 1439 centers.

## Abstract

Acute minor ischemic stroke patients often experience recurrence shortly after symptom onset, highlighting the importance of predicting stroke recurrence for guiding treatment decisions. This study evaluated the effectiveness of machine learning models in predicting in‐hospital recurrence. The study cohort comprised 322,135 patients with acute minor ischemic stroke from 1439 centers, as established by Chinese Stroke Center Alliance. Patients were randomly allocated into training and test sets by different centers. Models including extreme gradient boosting (XGB), light gradient boosting (LGB), and adaptive boosting (ADA) were developed using fivefold cross‐validation on the training set. Optimization was performed for all models based on the most important variable, history of ischemic stroke. Compared with the traditional generalized linear model (GLM), the XGB, LGB, ADA models yielded area under the curve (AUC) values ranging from 0.788 to 0.803 after optimization. All models showed significant improvements in AUC compared with GLM, with LGB exhibiting the most substantial enhancement after optimization. For the first time, this study developed models specifically designed to predict in‐hospital stroke recurrence in acute minor ischemic stroke patients. This finding aids in identifying high‐risk patients and prompts physicians to provide targeted treatment. However, further external validation is warranted to confirm the model's generalizability.

Study evaluated machine learning methods for predicting in‐hospital stroke recurrence in minor ischemic stroke patients. A cohort comprised 322,135 patients from 1439 centers established by Chinese Stroke Center Alliance was used to develop and test models. Compared with the traditional generalized linear model, light gradient boosting model exhibited the most substantial improvement in AUC. This finding helps identifying high‐risk stroke patients.