Descriptive and Predictive Analytics on Electronic Health Records using Machine Learning

Abstract

Electronic Health Records are an electronic version of a patient’s health records. Real-time data of a patient’s health history, medications, treatments, diagnosis, immunizations, procedures, laboratory tests and allergies. It is patient-centered data that is made available to authorized users, especially the doctors, and medical professionals, who prescribe different medications based on the ailments. This information is shared between different health care providers to allow access to patients’ medical records to make decisions about patients’ care plans and treatment. Electronic Health Records supports bbuilding an intelligent system that can easily detect the dissimilarities in patient’s medication and can target the provider for relevant educational content. Also helps the health care organizations to get refreshed and updated at minimum risk of the wrong diagnosis during the course of treatment with superior quality of health care services. Real-time data of a patient’s health history and medication processes is used to develop a predictive model. This model provides educational content to healthcare providers, to minimize the risk during the course of treatment, compares the actual practice to clinical guideline, and also increase the quality of health care services.