Big Data Research Paper

...

Big Data Frameworks

Medical imaging provides important information on anatomy and organ function in addition to detecting diseases states. Moreover, it is utilized for organ delineation, identifying tumors in lungs, spinal deformity diagnosis, artery stenosis detection, aneurysm detection, and so forth. In these applications, image processing techniques such as enhancement, segmentation, and de- noising in addition to machine learning methods are employed. One of the frameworks developed for analyzing and transformation of such very large imaging datasets is Hadoop that employs MapReduce. MapReduce is a programming paradigm that provides scalability across many servers in a Hadoop cluster with a broad variety of real-world application. With its capability to store and compute large volumes of data, usage of systems Hadoop, MapReduce, and MongoDB is becoming much more common with the healthcare research communities. MongoDB is a free cross-platform document-oriented database which eschews traditional table-based relational database. Typically each health system has its own custom relational database schemas and data models which inhibit interoperability of healthcare data for multi-institutional data sharing or research studies. Furthermore, given the nature of traditional databases integrating data of different types such as streaming waveforms and static EHR data is not feasible. This is where MongoDB and other document-based databases can provide high performance, high availability, and easy scalability for the healthcare data needs. For performing analytics on continuous telemetry waveforms, a module like Apache Spark is especially useful since it provides capabilities to ingest and compute on streaming data along with machine learning and graphing tools. Such technologies allow researchers to utilize data for both real-time as well as retrospective analysis, with the end goal to translate scientific discovery into applications for clinical settings in an effective manner.

Challenges Of Big Data

There is enormous enthusiasm for how big data can address persistent cost and quality deficiencies in the healthcare system, yet the excitement about big data and the analytics it requires appears to have gotten ahead of reality. Without more specific attention to challenges an important tool for transforming healthcare will fail to deliver on its promise.

The first set of challenge is of data storage that includes security, accessibility, and sustainability. Should data be stored centrally or in a federated manner? There are concerns about entrusting health-related data to public clouds. As a result, there is a strong need to come up with alternatives. There are also challenges that are particularly salient in healthcare. Concerns about privacy and security are paramount, although these are increasingly being addressed by new authentication approaches and policies that better safeguard patient-identifiable data. The challenge that demands significantly more attention is ensuring that the data are not only big but that they are good. The problem in healthcare lies with the quality of the data. To derive insights from data, it is critical that they be accurate and relatively complete. When data are systematically biased through either errors or omissions, the correlations that give rise to new insights will be missed or spurious, and could result in misguided confidence or scarce resources dedicated to chasing down dead ends. Even if perfect data accuracy is achieved, a second daunting challenge remains: data fragmentation. Incomplete data are common in clinical practice and reflect highly fragmented healthcare system where patients see multiple clinicians whose EHRs do not communicate. Despite significant policy interest, meaningful level of interoperability has to be achieved and without it, creating a comprehensive picture of patients’ care will be nearly impossible. Incomplete data, like inaccurate data, can also lead to missed or spurious associations that can be wasteful or even harmful to patient care. Choosing and implementing the right technologies to extract value, and finding skilled personnel are also constant challenge involving big data for healthcare.

Conclusion

We are currently in the era of “big data,” in which big data technology is being rapidly applied to biomedical and health-care fields. In this review, we demonstrated various examples in which big data technology has played an important role in modern-day health-care revolution, as it has completely changed people’s view of health-care activity. The first section of this review tells us about what “Big data” is and what is its relevance to healthcare. In the second section benefits of big data in healthcare have been revealed using cases of successful implementation of big data in healthcare. Third section informs us about many different frameworks like Hadoop, Spark, MongoDB and Cassandra that are actively being used for processing unprecedented big data sets, to draw some meaningful information. In the last section we learned that despite big data holds significant promise for improving health care, there are several common challenges facing all the fields in using big data technology.

Citations

Jake Luo, Min Wu, Deepika Gopukumar, Yiqing Zhao. "Big Data Application in Biomedical Research and Health Care: A Literature Review." PMC (2016).

Ashwin Belle, 1 , 2 Raghuram Thiaga M. Reza Soroushmehr, Fatemeh Navidi, Daniel A. Beard, Kayvan Najarian. "Big Data Analytics in Healthcare." BioMed Research International (2015).

Sreenivas R. Sukuma , Ramachandran Natarajan , Regina K. Ferrell , (2015) "Quality of Big Data in health care", International Journal of Health Care Quality Assurance, Vol. 28 Iss: 6, pp.621 - 634

D.Dinov, Ivo. "Methodological challenges and analytic opportunities for modeling and interpreting Big Healthcare Data." Gigasciencev.5; 2016PMC4766610 (2016).

Estela S. Estape, M.T, Ph.D., FASAHP, DHL,* Mary Helen Mays, Ph.D., MPH, MBA, RD, and Elizabeth A. Sternke, Ph.D. "Translation in Data Mining to Advance Personalized Medicine for Health Equity." HHS Author Manuscript (2016).

H. Liyanage, 1 S. de Lusignan,corresponding author1 S-T. Liaw,2 C. Kuziemsky,3 F. Mold,1 P. Krause,4 D. Fleming,1 and S. Jones1. "Big Data Usage Patterns in the Health Care Domain: A Use Case Driven Approach Applied to the Assessment of Vaccination Benefits and Risks." Yearb Med Inform (2014).

M. M. Hansen, corresponding author1 T. Miron-Shatz,2 A. Y. S. Lau,3 and C. Paton4. "Big Data