FETAL HEART RATE DETECTION ALGORITHM FROM NON-INVASIVE FETAL ELECTROCARDIOGRAM BASED ON TEMPLATE SUBTRACTION EXTRACTION AND QRS DETECTION PAN-TOMPKINS

• Main Author: Nadila, Hasna
• Format: Final Project
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/58407
• Institution: Institut Teknologi Bandung

Fetal distress can be prevented by regular and continuous fetal heart rate (FHR) monitoring. There is an alternative measurement to detect the FHR aside of cardiotochogram (CTG) and Doppler ultrasound by using non-invasive fetal electrocardiogram (NIFECG) which takes place on the surface of the mother's abdomen. However, NIFECG has a problem regarding low signal-to-noise ratio (SNR) caused by some interferences such as maternal ECG (MECG), EMG, EHG, mother’s respiration, motion artifact, and powerline noise. Many studies have focused on developing algorithm to detect FHR from NIFECG consists of three main steps, pre-processing, FECG extraction, and fetal QRS (FQRS) detection. One of the methods to extract FECG from NIFECG is template subtraction that does not require many channels. Nevertheless, it cannot significantly enhance the SNR. While for the QRS detection, the PanTompkins algorithm is frequently used but designed for adult ECG. Other than low SNR, NIFECG also faces a problem related to the standard configuration. It is still unknown where the electrode placement can produce an optimal FECG signal quality. Hence, the objective of this study is to increase FHR accuracy by developing an algorithm based on template subtraction for FECG extraction and modified Pan-Tompkins for FQRS detection. This study also proposes a channel selection process to eliminate low SNR channels that could potentially interfere with FHR detection. Another objective is to analyze NIFECG configuration that has optimal FECG quality based on its SNR value. The results show that the proposed algorithm could produce mean absolute error (MAE) of 1.68 ms and mean square error (MSE) of 8.04 bpm2 . Increasing the SNR threshold for channel selection could decrease MAE and MSE to 1.00 ms and 1.11 bpm2 . NIFECG configuration analysis from the Matonia dataset shows channel 3 has the highest SNR FECG value (20.18 dB) compared to other channels.