Prediction of Health Care Data Using Efficient Machine Learning Algorithms

Abstract

Every clinical decision relies on the doctor's expertise and comprehension.This standard procedure may, despite appearances, lead to errors, biases, and increased costs that compromise the patients' Quality of Service (QoS).There is a pressing need for adaptable equipment for critical patient care in developing nations like India.The majority of Indian hospitals are unable to provide their patients with adequate medical care due to a lack of suitable, simple, and expandable intelligent systems.The development of a comprehensive system that will enable hospitals to provide vital patients with a real-time feedback system is the objective of this project.Using IBM cloud computing as a service platform and machine learning, we propose a standard architecture, language, and classification scheme for analyzing vital patient health data (PaaS).The development of a machine learning (ML) method for predicting a patient's fitness is the primary goal of this study.Our models and data are stored and managed by IBM Watson Studio and IBM Cloud.The Base Predictors for our ml models are Nave Bayes, Logistic Regression, the KNeighbors Classifier, the Decision Tree Classifier, the Random Forest Classifier, the Gradient Boosting Classifier, and the MLP Classifier.The precision of the model has been increased by employing the ensemble learning bagging strategy.We use a variety of machine learning algorithms for ensemble learning.The Critical Patient Management System, or CPMS, is a mobile application we developed that allows for real-time data and record viewing.Data that is relevant to ML model training and deployment can be fetched in real time from IBM Cloud and made available through CPMS because of the way the system is built.Doctors can use Ml tendencies to predict a patient's health status.The CPMS will send an SMS notification to the duty physician and nurse to provide immediate care if the situation worsens as anticipated.Hospitals might get a smart healthcare solution if the mission, milliliter models, and mobile application are combined.