Automated EEG-based prediction of delayed cerebral ischemia after subarachnoid hemorrhage

This dataset supports our study on developing an automated algorithm for predicting delayed cerebral ischemia (DCI) after subarachnoid hemorrhage (SAH) using electroencephalography (EEG). We provide EEG recordings and clinical data from 113 moderate to severe grade SAH patients, along with the code for our machine learning model that integrates multiple EEG features for DCI prediction. The algorithm achieves an area under the receiver-operator curve of 0.73 by day 5 after SAH with good calibration between 48-72 hours, demonstrating the potential of automated, multi-featured EEG assessment for DCI risk prediction. The citation is: [Zheng WL, Kim JA, Elmer J, Zafar SF, Ghanta M, Moura Junior V, Patel A, Rosenthal E, Brandon Westover M. Automated EEG-based prediction of delayed cerebral ischemia after subarachnoid hemorrhage. Clin Neurophysiol. 2022 Nov;143:97-106. doi: 10.1016/j.clinph.2022.08.023. Epub 2022 Sep 11. PMID: 36182752; PMCID: PMC9847346.](https://pmc.ncbi.nlm.nih.gov/articles/PMC9847346/) Code is here: <https://github.com/bdsp-core/SAH_DCI_Prediction_EEG>