Machine Learning Prediction of Seizures after Ischemic Strokes.
Alain Lekoubou Looti1, justin Petucci2, Avnish Katoch3, Vasant Honavar4
1Penn StateHealth, Hershey Medical Center, 2Institute for Computational and Data Sciences and Clinical and Translational Sciences Institute, 3Clinical and Translational Sciences Institute, 4Data Sciences Program, College of Information Sciences and Technology, Center for Artificial Intelligence Foundations and Scientific Applications, Institute for Computational and Data Sciences, and Clinical and Translational Sciences Institute
Objective:
To develop an artificial intelligence, machine learning prediction model for estimating the risk of seizures at 1 year and 5 years after ischemic stroke (IS).
Background:
Seizures are frequent complications of stroke and are associated with increased mortality, poor functional outcome, and lower quality of life. There are however no established clinical approaches to identify stroke survivors who are at high risk for seizures.  
Design/Methods:

We identified patients with IS without a prior diagnosis of seizures from 2015 until inception (08/09/22) in the TriNetX Diamond Network, using the International Classification of Diseases, Tenth Revision (ICD-10) I63, excluding I63.6. The outcome of interest was any ICD-10 diagnosis of seizures (G40/G41) at 1 year and 5 years following the index IS. We applied a conventional logistic regression and a Light Gradient Boosted Machine (LGBM) algorithm to predict the risk of seizures at 1 year and 5 years.  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.

Results:

We included 444,130 IS patients without a prior diagnosis of seizures. Seizures were present in 20,085 (4.2%) and 24,479 (5.5%) patients within 1 and 5 years after IS, respectively. At 1-year, the AUROC, AUPRC, F1 statistic, accuracy, balanced-accuracy, precision, and recall were respectively 0.7917 (standard error: 0.0029), 0.2604 (0.003), 0.238 (0.0016), 0.819 (0.0024), 0.7267 (0.0008), 0.147 (0.0014), and 0.6252 (0.0036). Corresponding metrics at 5 years were 0.767 (0.0042), 0.2633 (0.0087), 0.2535 (0.0057), 0.8087 (0.0038), 0.7053 (0.0052), 0.1615 (0.0042) and 0.5892 (0.0074).

Conclusions:

Our findings suggest that ML models show good model performance for predicting seizures after IS. Incorporating imaging variables, including markers of brain health could improve these models.

10.1212/WNL.0000000000203063