Can machine learning predict late seizures after intracerebral hemorrhages? Evidence from real-world data.

introductionIntracerebral hemorrhage represents 15 % of all strokes and it is associated with a high risk of post-stroke epilepsy. However, there are no reliable methods to accurately predict those at higher risk for developing seizures despite their importance in planning treatments, allocating resources, and advancing post-stroke seizure research. Existing risk models have limitations and have not taken advantage of readily available real-world data and artificial intelligence. This study aims to evaluate the performance of Machine-learning-based models to predict post-stroke seizures at 1 year and 5 years after an intracerebral hemorrhage in unselected patients across multiple healthcare organizations. DESIGN/

methodsWe identified patients with intracerebral hemorrhage (ICH) without a prior diagnosis of seizures from 2015 until inception (11/01/22) in the TriNetX Diamond Network, using the International Classification of Diseases, Tenth Revision (ICD-10) I61 (I61.0, I61.1, I61.2, I61.3, I61.4, I61.5, I61.6, I61.8, and I61.9). The outcome of interest was any ICD-10 diagnosis of seizures (G40/G41) at 1 year and 5 years following the first occurrence of the diagnosis of intracerebral hemorrhage. We applied a conventional logistic regression and a Light Gradient Boosted Machine (LGBM) algorithm, and the performance of the model was assessed using the area under the receiver operating characteristics (AUROC), the area under the precision-recall curve (AUPRC), the F1 statistic, model accuracy, balanced-accuracy, precision, and recall, with and without seizure medication use in the models.

resultsA total of 85,679 patients had an ICD-10 code of intracerebral hemorrhage and no prior diagnosis of seizures, constituting our study cohort. Seizures were present in 4.57 % and 6.27 % of patients within 1 and 5 years after ICH, respectively. At 1-year, the AUROC, AUPRC, F1 statistic, accuracy, balanced-accuracy, precision, and recall were respectively 0.7051 (standard error: 0.0132), 0.1143 (0.0068), 0.1479 (0.0055), 0.6708 (0.0076), 0.6491 (0.0114), 0.0839 (0.0032), and 0.6253 (0.0216). Corresponding metrics at 5 years were 0.694 (0.009), 0.1431 (0.0039), 0.1859 (0.0064), 0.6603 (0.0059), 0.6408 (0.0119), 0.1094 (0.0037) and 0.6186 (0.0264). These numerical values indicate that the statistical models fit the data very well.

conclusionMachine learning models applied to electronic health records can improve the prediction of post-hemorrhagic stroke epilepsy, presenting a real opportunity to incorporate risk assessments into clinical decision-making in post-stroke care clinical care and improve patients' selection for post-stroke epilepsy research.