Predictive Data Analytics Framework based on Maternal and Child HealthCare System (MCHS) using Machine Learning

Abstract

Because it affects both mother and child health, maternal health research has become a top priority in public health. There aren't many synthetic review papers in this field despite the rising amount of empirical investigations, particularly from developing nations. To inform readers of the state of the subject and suggest areas for future study, an attempt at a synthesis of research in this field appears pertinent.  Predictive analytics has grown in importance as an aid for child welfare services and safeguards for kids in an era of ever-rising data availability.  This cutting-edge technology helps child welfare agencies make better judgments regarding the way to best assist their clientele by forecasting future patterns and outcomes using data gathered from past occurrences. Predictive analytics needs to be used properly, though, just like any other data-driven technology, to ensure efficient and moral business practices. As AI-Artificial Intelligence and ML-Machine Learning become more popular, healthcare forecasting has grown in significance in recent years. Forecasting in the healthcare industry can also help doctors make diagnoses more quickly and accurately. Medical personnel may identify and treat patients more swiftly and precisely by anticipating probable medical occurrences. Better patient outcomes and even financial savings may arise from this.  By simulating human cognition, these systems offer tremendous therapeutic aid and may even make medical diagnoses.  The studies included in this study concentrate on utilising machine learning algorithms to forecast child healthcare. We put the system into practise using a decision tree for CHS, MySQL for reminders about immunizations, and the K-means Elbow technique for maternal registration and notification.