A brand new study by shows that the AI-driven encevis spike detection algorithm reaches a sensitivity of 92% with an average per patient FPR of 5.6/hour. This makes it possible to characterize epilepsy patients based on their temporal patterns of interictal epileptiform discharges, circadian rhythms, deep sleep and seizures. Precious insights can be won thanks to encevis automated analysis.  The full paper is available here until July 10th.

Our new project Braincheck, where we will use AI-based analysis of the brain activity during cognitive tests to diagnose early dementia, is presented in the TV program “Road to digital Austria” contribution: https://www.atv.at/road-to-digital-austria/staffel-2-folge-28/d3149135/.

Our newest spike detection is described in this publication together with a study performed with independent data from the Danish Epilepsy Centre in Dianalund. An artificial intelligence-based EEG algorithm for detection of epileptiform EEG discharges: Validation against the diagnostic gold standard. With a sensitivity of 89%, the new encevis spike detection performs better than any previously published algorithm. If you want to try it on your own data, just contact us!

Listen to the podcast about encevis “Automating Spike and Seizure Detection” from Dick Moberg’s Neural Network! Our colleagues Ana Skupch and Franz Fürbass talk about the history and the future of encevis automated analysis of EEG.

A study on automated seizure detection in epilepsy monitoring units is presented in this paper: Improving staff response to seizures on the epilepsy monitoring unit with online EEG seizure detection algorithms. It shows how the encevis seizure detection detects seizures that are missed by the staff and thus improves the safety of the patients.