Clinical Research Directory

AI-based Algorithm Development for Improved Diagnostics in the Intensive Care and Acute Stroke Setting Using Electroencephalography

The goal of this observational study is to develop and validate artificial intelligence (AI) algorithms that use subhairline EEG (a simplified EEG patch placed on the forehead and behind the ears) to predict neurological outcome and to detect intracranial hemorrhage. The study consists of two use cases: (UC1) adults (18 years or older) in postanoxic coma after cardiac arrest who are admitted to the intensive care unit (ICU), and UC2) adults with suspected stroke or suspected subarachnoid hemorrhage (SAH) who present to the emergency department. The primary objectives are: * UC1: to develop and validate an AI-algorithm for outcome prediction in postanoxic coma at 24h after CA based on subhairline EEG. * UC2: to develop and validate an AI-algorithm for detection of ICH among patients with (suspected) stroke based on subhairline EEG and clinical symptoms. Participants will: * UC1: receive a continuous subhairline EEG recording, in addition to the standard scalp EEG used in routine care. The recording starts as soon as possible after ICU admission and continues for up to 72 hours after cardiac arrest. * UC2: receive a single subhairline EEG recording of about 2 minutes as soon as possible after arrival. Clinical data is collected from their medical records. This includes patient characteristics, imaging, treatment and outcome at discharge. There are no follow-up visits. In a final pilot phase, up to 10 patients per setting will be measured with the AI algorithms built into the EEG recording device, to evaluate feasibility and user-friendliness. In all phases, EEG and algorithm results are not used for clinical decisions.