<ul><li>High hospital readmission rates are associated with significant costs and health risks for patients.</li><li>Predictive models are crucial in supporting clinicians to determine patient hospital readmissions within a short period.</li><li>Combining clinical notes and electronic health records (EHRs) helps in predicting 30-day hospital readmissions.</li><li>A graph neural network (GNN) is used to integrate both information sources, achieving an AUROC of 0.72 and a balanced accuracy of 66.7%.</li></ul>

Prediction of 30-day hospital readmission with clinical notes and EHR information

Discover more