Random Forest-Based Machine Learning Model for Fetal Health Classification Using CTG Data

Abstract

A fetus is an unborn baby, developing from the stage of embryo into birth. Pregnancy is typically divided into three-month blocks referred to as trimesters. The fetus develops very fundamentally during this phase, and more frequent visits with a doctor must be made in order to monitor both the baby's and mother's health. Pregnancy generally lasts nine months, and throughout this period, there are certain risks possible which can lead to disabilities or even the death of the fetus. All such conditions are problems and should be averted by timely intervention and screening. Among the most significant of the diagnostic tools used to monitor fetal health are Cardiotocography (CTG). CTG is the measurement of fetal heart movements and uterine contractions that generates data that doctors use in order to figure out fetal health. Complete human observation dependent but sometimes prone to be an error. In order to enhance the validity of such studies, some machine learning (ML) and deep learning (DL) techniques have been put forward. These techniques can be able to better understand CTG data and predict fetal status. The final goal of the current study is to compare the predictive ability of various classification methods and determine which model yields the maximum correct result in identifying the fetus's health.

Ähnliche Arbeiten