New York
LondonBeijing
An IoT-Based Pregnancy Complexity Identification Using Machine Learning

An IoT-Based Pregnancy Complexity Identification Using Machine Learning

G. Vinoth Chakkaravarthy (Velammal College of Engineering and Technology, India), Raja Lavanya (Thiagarajar College of Engineering, India), and P. Alli (Velammal College of Engineering and Technology, India)
Copyright: © 2023 |Pages: 8
DOI: 10.4018/979-8-3693-1718-1.ch013
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Pregnancy complications have the potential to seriously injure both the mother and the developing baby, increasing the risk of morbidity and mortality. Early detection of high-risk pregnancies is crucial to reducing the likelihood of such issues and improving the health outcomes for mothers and babies. The authors suggest an IoT-based system that uses machine learning to recognise pregnancy complications as a solution to this problem. The system uses a variety of sensors to collect information from pregnant women, including blood pressure, heart rate, foetal heart rate, and temperature sensors. This collected data is then analyzed using machine learning algorithms using supervised learning algorithms for classification and regression analysis. The study's findings indicate that the suggested system can effectively recognize pregnancy complications with high levels of accuracy, sensitivity, specificity, and AUC. The system holds great potential in enhancing maternal and fetal health outcomes by enabling the early detection and intervention of high-risk pregnancies.
Chapter Preview
Top

2. Literature Survey

Numerous research studies have suggested employing IoT-based sensors and ML algorithms for monitoring pregnancy and identifying complications. This section presents an overview of some of the relevant research works conducted in this field.

The paper titled “IoT-Based Risk Level Prediction Model for Maternal Health Care in the Context of Bangladesh” presents a study that explores the potential of IoT and machine learning in predicting the risk level of maternal health in Bangladesh (Ahmed & Kashem, 2020). In order to forecast the risk level of maternal health in real-time, the paper addresses the difficulties in maternal health care in Bangladesh and suggests a risk prediction model that makes use of IoT-based sensors and machine learning algorithms. The study also discusses the design and implementation of the suggested system and assesses its effectiveness using a number of measures.

An overview of an IoT-based wearable system that makes use of accelerometers and machine learning for tracking foetal movement is provided in the paper titled An IoT-based wearable system using accelerometers and machine learning for foetal movement monitoring (Zhao et al, 2019). The technology seeks to offer a non-invasive and economical means for tracking foetal movements, which is a crucial sign of the health of the foetus. A variety of criteria, including accuracy, sensitivity, specificity, and positive predictive value (PPV), are used in the study to assess the system's performance. The findings show that the suggested method has the ability to precisely identify foetal movements and has the potential to be a helpful tool for foetal monitoring throughout pregnancy. According to the findings, the suggested approach had high accuracy rates of 96.6%, 92.1% sensitivity, 98.2% specificity, and PPV.

Complete Chapter List

Search this Book:
Reset