Predicting Fetal Health Outcomes: Integrating Machine Learning with Prenatal Care Technologies

• Author(s): Pranav Khot ; Vidhi Shukla ; Rimsy Dua ; Dr. S. K. Singh
• Paper ID: 1705465
• Page: 17-25
• Published Date: 01-02-2024
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 7 Issue 8 February-2024

Abstract

The realm of prenatal care is witnessing a transformative shift with the integration of machine learning (ML) techniques, aiming to enhance the accuracy and reliability of fetal health assessments. This research paper delves into the development and application of a novel machine learning based framework for predicting fetal health outcomes. Utilizing a comprehensive dataset derived from cardiotocograms, the study focuses on the extraction and analysis of key features indicative of fetal well-being, such as fetal heart rate patterns and uterine contraction metrics. The methodology encompasses a range of machine learning models, including Support Vector Machines (SVM), Random Forest (RF), and advanced ensemble techniques like XGBoost and LightGBM. These models were meticulously trained and validated to ensure robustness and reliability, with a particular emphasis on addressing the challenges posed by imbalanced datasets typical in medical diagnostics. The performance of these models was evaluated based on standard metrics such as accuracy, sensitivity, specificity and area under the ROC curve (AUC). The findings of this study underscore the potential of ML in revolutionizing fetal health monitoring. The results demonstrate that ML models, particularly ensemble methods, significantly outperform traditional analysis techniques in identifying potential fetal distress and other health concerns. This advancement heralds a new era in prenatal care, where data-driven insights can lead to early intervention and improved health outcomes for both mothers and fetuses. This approach bridges the gap between traditional fetal health assessment methods and cutting-edge machine learning techniques, this research contributes to the ongoing evolution of prenatal care, promising a future where technology-enhanced diagnostics ensure safer pregnancies and healthier babies.

Keywords

Cardiotocography, Ensemble methods, Fetal health assessment, Fetal heart rate, Healthcare technology, LightGBM, LVQ, Machine Learning, Medical diagnostics, Prenatal care, Random Forest (RF), Support Vector Machines (SVM), XGBoost.

Citations

IRE Journals:
Pranav Khot , Vidhi Shukla , Rimsy Dua , Dr. S. K. Singh "Predicting Fetal Health Outcomes: Integrating Machine Learning with Prenatal Care Technologies" Iconic Research And Engineering Journals Volume 7 Issue 8 2024 Page 17-25

IEEE:
Pranav Khot , Vidhi Shukla , Rimsy Dua , Dr. S. K. Singh "Predicting Fetal Health Outcomes: Integrating Machine Learning with Prenatal Care Technologies" Iconic Research And Engineering Journals, 7(8)