Fetal Arrhythmia: Deep Learning and Clustering Techniques, Analysis Through Permutation Entropy and Genetic Algorithms in Its Early Diagnosis

Valdez Z.I.; Diaz L.A.; Ravelo-Garcia A.G.; Cornejo M.V. · Computing in Cardiology (2023) · DOI: 10.22489/cinc.2023.274

Resumen

Fetal arrhythmias occur in 1-2% of pregnancies and involve irregular fetal heart rhythms, typically outside the 100-200 bpm reference range. This condition can be diagnosed as benign in most cases due to its subsequent natural regularization, but 10% of the registered cases indicate that the presence of irregularities in the fetal heart rhythm can trigger morbidity, fetal hydrops or even imminent death of the fetus. In this context, early and precise diagnosis is crucial for addressing this condition and reducing fetal deaths. That is why, a deep learning model is proposed based on a classifying neural network trained with an ECG database of 6 channels (fetal and maternal) accompanied by an intelligent arrangement of clustering techniques, analysis by permutation entropy and data augmentation based on genetic algorithms. This set of techniques aims to form an effective system for the rapid diagnosis of heart rhythm irregularities present in fetuses, ensuring an overall accuracy greater than 92% in fetal arrhythmia risk stratification.

Instituciones: Universidad Nacional de San Agustín de Arequipa