Towards for Designing Intelligent Health Care System Based on Machine Learning

Abstract

Health Information Technology (HIT) provides many opportunities for transforming and improving health care systems. HIT enhances the quality of health care delivery, reduces medical errors, increases patient safety, facilitates care coordination, monitors the updated data over time, improves clinical outcomes, and strengthens the interaction between patients and health care providers. Living in modern large cities has a significant negative impact on people’s health, for instance, the increased risk of chronic diseases such as diabetes. According to the rising morbidity in the last decade, the number of patients with diabetes worldwide will exceed 642 million in 2040, meaning that one in every ten adults will be affected. All the previous research on diabetes mellitus indicates that early diagnoses can reduce death rates and overcome many problems. In this regard, machine learning (ML) techniques show promising results in using medical data to predict diabetes at an early stage to save people’s lives. In this paper, we propose an intelligent health care system based on ML methods as a real-time monitoring system to detect diabetes mellitus and examine other health issues such as food and drug allergies of patients. The proposed system uses five machine learning methods: K-Nearest Neighbors, Naïve Bayes, Logistic Regression, Random Forest, and Support Vector Machine (SVM). The system selects the best classification method with high accuracy to optimize the diagnosis of patients with diabetes. The experimental results show that in the proposed system, the SVM classifier has the highest accuracy of 83%.

Big Data in E-government: Classification and Prediction using Machine Learning Algorithms

“…The researchers achieve the targets of this process by increasing the processing time of the proposed model. Therefore, this part enhances the data set, which becomes more ready to use in the later parts [25], as shown in Figure 4. Normalization is particularly useful for classification algorithms involving neural networks or distance measurements such as nearest-neighbor classification and clustering [6].…”

Big Data Framework Classification for Public E-Governance Using Machine Learning Techniques

“…The researchers achieve the targets of this process by increasing the processing time of the proposed model. Therefore, this part enhances the data set, which becomes more ready to use in the later parts [28], as shown in Fig. 3.…”

Dom Tree as the base for webpage content extraction: Review

“…It enters every corner of our life. Health has seen an explosion in digital information stored in Electronic Health Records (EHRs) that need to process automatically [1].…”