AN APPLICATION-BASED MACHINE LEARNING APPROACH FOR ENHANCING FETAL HEALTH MONITORING THROUGH FETAL HEART RATE CLASSIFICATION

Abstract

Early detection of fetal health issues through fetal heart rate (FHR) monitoring is crucial for reducing the risk of adverse perinatal outcomes. This invention aims to develop a web-based platform that uses multiple machine learning models, including Support Vector Machines (SVM), Random Forests (RF), and Convolutional Neural Networks (CNN), to improve FHR classification through data analysis. The models will identify normal and abnormal FHR patterns and provide real-time classification results. The application includes a visualization tool for FHR data and can be accessed from hospitals or clinics, making it a powerful tool for short-term and long-term fetal health monitoring goals. The invention aims to enhance prenatal care and potentially reduce adverse perinatal outcomes by deploying machine learning models for FHR classification.

Specification

Description:This invention proposes a technological structure (100) consisting of a web-based platform
(101) that utilizes multiple machine learning models (102) to improve FHR classification
through data analysis. The models identify normal and abnormal FHR patterns and provide
real-time classification results (106). The application can be easily accessed by healthcare
professionals from hospitals or clinics, making it a powerful tool for short-term and long-term
fetal health monitoring goals. The models' ability to analyse FHR input and provide
classifications in real-time makes it a powerful tool for helping healthcare professionals make
informed decisions. , Claims:1. A technological system (100) comprising a web-based application (101) specifically
designed for advanced fetal heart rate (FHR) classification, incorporating real-time data
acquisition and analysis.
2. A The technological system (100) of claim 1, wherein the web-based application (101) for
FHR classification integrates computational Machine Learning (ML) models (102), each
optimized for the analysis of FHR data, equipped with advanced data processing capabilities
(105) that enable real-time preprocessing, normalization, and feature extraction to enhance
analytical accuracy.
3. A The technological system (100) of claims 1 and 2, comprising computational Machine
Learning (ML) models (102) with specialized classification algorithms designed to identify
and categorize complex FHR patterns, facilitating precise detection of potential health issues
and anomalies.
4. A The technological system (100) of claims 1 and 2, wherein an automated FHR
classification system including an integrated FHR data input module (103) and a real-time data
processing unit (104), combined with advanced ML models (102) that perform comprehensive
FHR pattern analysis (105) and provide actionable classification results (106) to support timely
clinical decision-making.

Documents