Refining the diagnostic quality of the abdominal fetal electrocardiogram using the techniques of artificial intelligence

This article deals with utilization of the combination of the fuzzy system and artificial intelligence techniques, called the Adaptive Neuro Fuzzy Inference System ANFIS, with the aim to refine the diagnostic quality of the abdominal fetal electrocardiogram FECG. Within the scope of the experiments carried out and based on the ANFIS structure the authors created a complex system for removing the undesirable mother’s MECG degrading the abdominal FECG. Current research shows that the application of the conventional systems for enhancing the diagnostic quality of the abdominal FECG faces a series of problems (e.g. non-linear character of the task to solve, computational complexity of RLS algorithms, etc.). The need for a higher diagnostic quality of the abdominal FECG is reflected in the authors’ intention to utilize the designed system for the latest intrapartum monitoring method, called ST analysis. In terms of this advanced method, the aspect subjected to a diagnostic analysis is the ST segment of the FECG curve. The results indicate that the system utilizing ANFIS shows better experimental results than the conventional systems based on the LMS or RLS adaptive algorithms. The proposed adaptive system aims to clear any doubts in evaluation of the results of ST analysis while using a non-invasive method of external monitoring. Streszczenie. W artykule przedstawiono wykorzystanie fuzji metod: zbiorów rozmytych i sztucznej inteligencji ANFIS do poprawy jakości diagnostyki elektrokardiografii płodu. Głównym problemem jest usunięcie sygnału pochodzącego od matki który znacznie przewyższa sygnał płodu. (Poprawa jakości sygnału elektrokardiogramu płodu przy wykorzystaniu narzędzi sztucznej inteligencji)