Machine learning techniques using big data analytics for electronic health record system- a survey

Abstract

During the last few years, big data has become more prominent in healthcare, owing to three main factors: the vast quantity of data accessible, the rising expense of healthcare, and the emphasis on customised treatment. In healthcare, big data processing refers to the generation, collection, analysis, and storage of clinical data that is too large or complicated to be inferred from traditional data processing techniques. In order to analyse these datasets, the system needs sophisticated tools. The Map Reduce and Hadoop programming models are utilised for large-scale data processing because they are efficient parallel computing programming models. Map Reduce, on the other hand, continues to suffer from performance issues. Map Reduce makes use of a shuffle phase individual shuffle service component with an efficient I/O policy in conjunction with an efficient I/O policy. When it comes to conducting significant real-time analysis on massive amounts of data, Hadoop is an excellent tool for doing so. It can even be used to anticipate emergency situations before they occur. It discusses the applications of big data in the healthcare and government sectors. As a result of this article, we have provided an in-depth examination of the use of machine learning methods for big data analysis in the healthcare industry. Furthermore, the advantages and disadvantages of currently available methods, as well as different research difficulties, are discussed. EMR/EHR stands for electronic medical record/electronic health record. It contains information about a patient's medical history as well as diagnoses and treatment plans. It also contains results of laboratory and test tests as well as genomic sequencing, medical imaging and information about insurance providers and other clinical data. Different machine learning techniques that have been applied to diverse healthcare data sets are discussed in this article. In addition, the difficulties associated with processing and managing large amounts of data, as well as their applications. From a different viewpoint, the article aims to expand on the use of machine learning algorithms as well as the need of managing and using large amounts of data in a variety of situations.