DYNA JOURNAL ENGINEERING

Key words:

Artificial intelligence, encephalogram, absence seizures, Gabor filter, correlation in channel, pediatric neurology, supervised learning, model sensitivity, EEG analysis, experimental design.

Article type:

ARTICULO DE INVESTIGACION / RESEARCH ARTICLE

Section:

RESEARCH ARTICLES

The objective of this research is to determine the impact of applying artificial intelligence-based models to electroencephalogram frequencies in order to improve the detection of absence seizures in neuropediatric infant patients, such as supervised neural networks, SOM neural networks, nearest neighbor, decision trees, and random forests, as well as to find the relationship between channels at the time of the seizure. The methodology used is applied, with an explanatory level of research, and the research design is experimental. The sample used consists of four absence seizure events in 2,256 seconds, applying the Gabor filter to the frequencies prior to entering the models so that they become input patterns. At the moments of absence crisis, a channel coherence of 0.63 was identified, highlighting that at the moment of crisis all channels follow the same common pattern. The correlation coefficient R2 = 0.77 and a minimum R2 of 0.57 were identified, indicating the similarity of frequencies at the moment of crisis. A very high standard deviation was identified, highlighting the polypoint tails with more than 5 peaks per crisis in each channel. In testing the artificial intelligence-based models, the sensitivity, specificity, precision, and accuracy values obtained for each model with respect to identifying non-crises, crises, and pre-crises were 0.99, 1.0, 0.99, and 0.93 for the back propagation artificial neural network; 0.99, nan, 0.99, 0.99, for the nearest neighbor 0.99, 0.0, 0.99, 0.97, for decision tree 0.99, 0.0, 0.99, 0.97, and random forest 0.99, nan, 0.99, 0.97, respectively. Therefore, it concludes that there is correct data collection and processing with the learning models to identify seizures.
Key Words: Artificial intelligence, encephalogram, absence seizures, Gabor filter, correlation in channel.