Accurate prehospital stroke detection is essential for getting stroke patients to treatment quickly and promoting positive patient outcomes. Currently, inaccurate clinical exams are used for prehospital detection of stroke. We sought to develop a more sensitive and objective method of prehospital stroke detection. We created an experimental electroencephalogram (EEG)-based diagnostic device using artificial intelligence (AI) as a potential tool for detection of acute stroke and large vessel occlusion (LVO) among patients with neurological deficits. Both device performance and feasibility in the emergent setting were assessed. The diagnostic device performed well in identifying stroke and LVO in patients presenting with suspected stroke. The accurate performance of the device in the acute setting indicates that it may be able to support prehospital decision making when triaging patients suspected of having stroke.