Reasons for Increased Complexity of Healthcare Data
Due to information explosion, big data is deemed to be among the most discussed topics in healthcare information systems recently. The government of US also announced initiative for big data research and development of around 200 million in 2012. Such initiate ensures the possibility of employing big data within large scale database for dealing with considerable concerns faced by the government. Big data is deemed identical to business analytical and intelligence but the data scale is larger. In such scenario, dimensions of three “v” are employed in describing big data that includes variability, velocity and volume.
There is a traditional relationship between business intelligences and healthcare information systems. There are several reasons that results in big data evolution and one among them is increase of in-memory computing. Traditional computers encompass secondary storage devices such as hard drives and entrap processing unit (CPU).
Figure 1: Traditional Relationship between Healthcare Information Systems and Business Intelligence
Transfer of data takes place among the secondary storage and the CPU during data processing. This serves as an economical manner to employ computers, processing speed of the computers is likely to be decreased. Oracle and SAP Hana develops new computer systems that utilizes in-memory systems. For this reason, today’s computer systems are able to deal with large-scale data than before. Another reason for rise in big data is social networking. Within business intelligence and traditional data mining, the data is relied on internal data developed from internal enterprise resource planning systems (ERP) or healthcare information systems. Such data employed in these systems are defined as structured data that is limited. Moreover, popularity of social networking is increasing for over six years that has already presented a huge amount of big data that is helpful in data analysis. Such external data or certain unused internal data is deemed as unstructured information. Big data includes structured and unstructured data derived from interval unused data, external data resources and social media.
Several big data challenges are faced in healthcare information systems that include inferring knowledge from difficult heterogeneous patient sources along with leveraging patient data correlations in longitudinal records. Big data challenges are also present in understanding unstructured clinical notes in correct context. Issues are also present in efficiently dealing with large volumes of medical imaging data along with gathering likely biomarkers and helpful information. Evaluating genomic data serves as a computationally intensive task along with getting associated with standard clinical data adds several complexity layers. Another change associated with big data in healthcare includes gathering patients’ behavioral data through numerous sensors along with several communications and social interactions.
Relevance of Big Data Analytics in Healthcare
Big data can be understood as collection of complex and large data sets that are difficult to process through employing common management techniques or traditional data processing applications. Big data can also be referred as processes, procedures and tools that facilitate healthcare organizations in manipulating, generating and managing large data sets along with storage facilities. Big data in healthcare is focused on recognizing insights from longitudinal, complex, voluminous and heterogeneous data that intends to answer questions those were unanswered previously. In such case, the challenges encompass storing, gathering, sharing, searching and evaluating.
Figure 2: Four V’s of Big Data
The reasons for which abundance or complexity of healthcare data is increasing are explained below:
- Increased incentives to professionals and hospitals to using HER technology
- Standard medical practices changing from being ad-hic to subjective decision making considering evidence based healthcare
- New technologies development too place such as sensors, capturing devices and mobile applications.
- Gathering of genomic information turned out to be cheaper
- Patient social communications in digital forms are observed to increase
- High medical knowledge or discoveries are being gathered
Big data analytics facilitates in attaining advantage from huge amounts of data long with offering appropriate intervention to the right patient at a correct time. It also facilitates healthcare systems in offering personalized care to patients along with offering potential benefits to all aspects of healthcare system that includes payer, provider, management and patient. Objectives of big data analytics in healthcare focuses on introducing data mining researchers to the available sources along with likely challenges and techniques related with employing big data in healthcare system. Big data analytics also considers introducing healthcare practitioners and analysts to the developments within computing field in efficiently dealing and making involvements from heterogeneous and voluminous healthcare data. Healthcare facilities consider offering highly proactive care to patients through regularly monitoring patients’ vital signals. Data gathered from several monitors might get evaluated in real time along with sending alerts for caring providers so that they realize instantly regarding alterations in condition of patients. Processing real-time events with support of machine learned algorithms might offer physicians with viewpoints that can help them to take life saving decisions along with facilitating efficient interventions. Real-time monitoring alters nature of relationship as face-to-face care is not that important.
Figure 3: Big Data Analytics in Healthcare
Major objective of big data analytics in healthcare is to cover data mining and medical informatics communities for fostering interdisciplinary works among two communities. The healthcare industry focuses on employing big data technologies. Big data analytics has increase relevance in healthcare industry for the reason that it offers value based and patient focused care. An objective of modern healthcare systems is to offer optimal healthcare by efficient application of health information technology. This will be for decreasing the healthcare expenses and avoidable overuse along with offering support for re-developed payment structures. Moreover, the expenses of waste, fraud and abuse within healthcare industry are a major factor resulting in increased healthcare costs in US. In such scenario, big data analytics might turn out to be a game changer in healthcare fraud. The centres for Medicaid and Medicare services prevented around $210.7 million within healthcare fraud within a year through employing predictive analytics. United healthcare changed to predictive modeling surrounding that is relied on Hadoop platform of big data for recognizing inefficient claims in repeatable and systematic way along with generating high return on advanced technology or big data.
Use of Big Data in Healthcare Information Systems
An efficient instance of real-world case in data analysis was provided when it was revealed that the retail giant target can recognize whether a person is sick through tracking his behavior. With the help of such data target will be capable to anticipate her future consumption of certain emergency disease specific medicines. It examined the ways in which Target was able to analyze sickness of a person through employing data mining tools. Moreover, as Target employed a statistician in employing data mining techniques for anticipating consumer behavior, the revenue increased drastically.
Figure 4: Big Data Use in Healthcare Information Systems
It has been observed that there is an increased potential for big data within healthcare information systems. For such mainframe based business intelligence or programs of data mining like SAP BW or SAS must have the capability to get upgraded in dealing with big data evaluation. Numerous ERP or healthcare system vendors log with key IT companies such as Microsoft, IBM, SAP, SAS and Oracle have already worked on several big data projects. Research within particular big data applications remains within early stage and under development but numerous general applications is taking place. Within biology aspects, big data has turned out to be innovative technological tool for genomics. It is also confirmed that biologists employ big data for analyzing all the aspects from genes regulation along with genomes evolution in consideration to the reasons for which coastal algae bloom, the microbes that are present in human body cavities and the ways in which genetic makeup of distinct cancers effects the ways in which cancer patients fare. It took almost twelve years for Human Genome Project in evaluating, gathering along with interpreting a great data amount required to develop a map regarding genes. However, this might take a lot of years for Human Genome Project in evaluating, gathering and interpreting a great data amount required to develop a map of numerous genes but it might take just a day for employing new big data technologies in attaining similar results.
Figure 5: Complex Big Data Analytics in Healthcare
Big data can be employed in pharmaceutical development cycle within areas such as clinical monitoring, genomics and pharmacovigilliance. A novel system such as Collaborative assessment and Recommendation Engine (CARE) in order to predict risk of personalized disease. Big data also supports storage along with processing of medical imaging data. Big data healthcare serves as a drive for capitalizing on increasing patient and health system data accessibility in order to develop healthcare innovation. Through making smart application of increasing amount of available data, new insights can be found through re-examining data or combining with other important data. In healthcare this involves mining patient records, biobanks, medical images and test results for diagnosis, insights and decision support advice. This also involves regular evaluation of data streams developed for all the patients, doctors’ office, at home and on move through mobile devices.
Conclusion
The paper focused in investigating the likely effect of big data on healthcare information systems. From the findings it was gathered that big data challenges is present in understanding unstructured clinical notes in correct context. Issues are also present in efficiently dealing with large volumes of medical imaging data along with gathering likely biomarkers and helpful information. There are several reasons that results in big data evolution and one among them is increase of in-memory computing. Big data analytics facilitates in attaining advantage from huge amounts of data long with offering appropriate intervention to the right patient at a correct time. It also facilitates healthcare systems in offering personalized care to patients. It was also revealed that gig data in healthcare remains focused on recognizing insights from longitudinal, complex, voluminous and heterogeneous data that intends to answer questions those were unanswered previously.
References
Belle, Ashwin, et al. “Big data analytics in healthcare.” BioMed research international 2015 (2015).
Bello-Orgaz, Gema, Jason J. Jung, and David Camacho. “Social big data: Recent achievements and new challenges.” Information Fusion 28 (2016): 45-59.
Chen, Min, et al. “Smart clothing: Connecting human with clouds and big data for sustainable health monitoring.” Mobile Networks and Applications 21.5 (2016): 825-845.
Gandomi, Amir, and Murtaza Haider. “Beyond the hype: Big data concepts, methods, and analytics.” International Journal of Information Management 35.2 (2015): 137-144.
George, Gerard, Martine R. Haas, and Alex Pentland. “Big data and management.” Academy of Management Journal 57.2 (2014): 321-326.
Groves, Peter, et al. “The’big data’revolution in healthcare: Accelerating value and innovation.” (2016).
Hu, Han, et al. “Toward scalable systems for big data analytics: A technology tutorial.” IEEE access 2 (2014): 652-687.
Kambatla, Karthik, et al. “Trends in big data analytics.” Journal of Parallel and Distributed Computing 74.7 (2014): 2561-2573.
Kayyali, Basel, David Knott, and Steve Van Kuiken. “The big-data revolution in US health care: Accelerating value and innovation.” Mc Kinsey & Company 2.8 (2013): 1-13.
Luo, Jake, et al. “Big data application in biomedical research and health care: A literature review.” Biomedical informatics insights 8 (2016): 1.
Raghupathi, Wullianallur, and Viju Raghupathi. “Big data analytics in healthcare: promise and potential.” Health information science and systems 2.1 (2014): 3.
Roski, Joachim, George W. Bo-Linn, and Timothy A. Andrews. “Creating value in health care through big data: opportunities and policy implications.” Health affairs 33.7 (2014): 1115-1122.
Wang, Yichuan, LeeAnn Kung, and Terry Anthony Byrd. “Big data analytics: Understanding its capabilities and potential benefits for healthcare organizations.” Technological Forecasting and Social Change (2016).
Zhang, Yin, et al. “Health-CPS: Healthcare cyber-physical system assisted by cloud and big data.” IEEE Systems Journal 11.1 (2017): 88-95.
Order an Essay Now & Get These Features For Free:
Turnitin Report
Formatting
Title Page
Citation
Outline
