Background. Given the difficulties in identifying absences and assessing the level of consciousness in epilepsy patients, it is extremely relevant to develop digital programs for automatic registration and testing of this type of epileptic seizures and related electroencephalographic (EEG) patterns, including those based on artificial intelligence.Objective: development of an algorithm for automatic detection of absence seizures to test real time patient's consciousness level during long-term video-EEG monitoring.Material and methods. The work on creating an algorithm was carried out during joint doctor/engineer cooperation. Doctors prepared a set of labeled EEG recordings of patients with verified absence epilepsy. Two independent experts in the generated examinations database mapped typical episodes of absence seizures that allowed to develop training and testing samples for a neural network algorithm to detect EEG absence epiactivity. Next, trained neural network was incorporated into Neuron- Spectrum.NET software to compare its accuracy with similar approaches published elsewhere.Results. A neural network algorithm was developed and trained using a mapped database to detect EEG absence epiactivity. A comparative analysis of the effectiveness for the proposed method vs. other approaches showed that the former is comparable in quality, whereas in some aspects – even superior to the latter. Accuracy was assessed using a publicly available database with mapped epiactivity episodes.Conclusion. A hardware and software system for automated assessment of patient’s consciousness level during absence seizure in continuous video-EEG monitoring was proposed. Potentially, neural networks may be applied not only to assess patient’s consciousness level, but also to stop stimulation-mediated seizure onset in the future.