@article {10.3844/ajeassp.2018.1154.1163,
article_type = {journal},
title = {Healthcare Driven by Big Data Analytics},
author = {Alexander, Cheryl Ann and Wang, Lidong},
volume = {11},
number = {3},
year = {2018},
month = {Sep},
pages = {1154-1163},
doi = {10.3844/ajeassp.2018.1154.1163},
url = {https://thescipub.com/abstract/ajeassp.2018.1154.1163},
abstract = {Text messages and social network posts are often included in big data and are frequently invaluable sources of health data. When machine learning or data mining is used, it is important to perform an automatic process for integrating all available and related health data. Artificial Neural Network (ANN) is one of the machine learning methods flexible in using algorithms to detect complicated nonlinear relationships within huge datasets. Pharmacokinetics uses genetics to individualize drug therapy. Because genetic and pharmacological analysis often require large scale computation, Big Data analytics has shown potential in this area. Personal data from various sensors can often be used for making health and treatment recommendations, taking appropriate action for a patient’s lifestyle choices and early diagnosis vital to advancing quality of care. Big data techniques such as hadoop and spark have been used in various areas of healthcare and big data analytics has been employed in great datasets to expose hidden patterns or correlations for effective decision-making. Challenges of big data in healthcare, concerned with gathering material from multifaceted heterogonous patient sources still exist, although hadoop has been employed as the processing unit for heterogeneous data gathered from various body sensors. The most critical necessity in a healthcare big data system is the data security; however, users are continuously applying big data–driven strategies to solve the various problems and challenges.},
journal = {American Journal of Engineering and Applied Sciences},
publisher = {Science Publications}
}