Big Data and Bioeconomy in nursing: modernization of education system in nurses

by Katsa Georgia, Koufioti Georgia and Kounios Athanassios

The health system remains one of the sectors where vast amounts of money are devoted annually on the government budget, as medicine is a constantly evolving and rising science. Hospitals and, by extension, medical and nursing staff concentrate on the management of a vast amount of information-data on a routine basis. Effective management and sufficient control of this health information are the cornerstone of better medical care-diagnosis and better management of financial resources in the clinic and therefore in the hospital. The first to introduce the term Big Data was John Massey. Since 1998 in his speeches he has used the term that became widely known in the 1990s, stating: “I was using one label for a range of issues, and I wanted the simplest, shortest phrase to convey that the boundaries of computing keep advancing.”

Basically, Big Data is delineated as a data collection, large in volume, both heterogeneous and complex in structure, which conventional data processing software can not properly manage. The relationship between health care staff and the development of technology (biomedical technology, imaging equipment, etc.) is inextricably intertwined and encompasses all the large volumes of data for which Big Data has prevailed. For early diagnosis, intervention and optimum provision of health services through the use of more effective treatment modalities, the client needs to be considered in a clear and concise manner.

The medical nurse, given that the use of Big Data can lead to changes in his way of working and therefore in the health system, should understand the benefit of exploitation-using such data as giving him the opportunity to export findings from an immense amount of diverse and heterogeneous information in a very short time, without spending vast sums of money and further examinations on patients. Health professionals are often expected to make use of information-data that comes from several sources, either of the same nature or from different sources, for example. Global bibliography, email, medical records, patient registries, etc. Common database management systems can not effectively process Big Data because they are concurrently executed, stored, retrieved and recorded by multiple servers.

The characteristics of Big Data are grouped into 4’V: Volume, Velocity, Variety and Veracity, where the volume refers to ever-increasing global data. In 2020 there will be a total of 35 zettabytes of digital data. As a value all the advantages of using Big Data (statistical and economic analyzes that measure outcomes in the financial sector) are invoked as the rate of the unstoppable-stagnant stream of inhomogeneous data that accumulates over a very short period of time and finally as its validity.

Figure 1. 4V features

If the use, collection and management of Big Data in hospitals is well understood then the importance of Big Data may be tangible and the hospital authorities may take measures in order to provide the staff with the mentioned technology and educate it in order to use this technology properly. Worth mentioning are the so many systems of Big Data, likewise:

1. Apache Hadoop: open-source software code that consists of

• Hadoop Common Utilities (libraries)

• Hadoop Distributed File System (HDFS) (saves data)

• The Hadoop YARN Framework, a resource management platform

• Hadoop Map-Reduce (processes large amount of data)

And manages potential malfunctions when they occur.

2. Apache Spark: is a Big Data editing software that offers the user a Resilient Distributed Dataset (RDD)

3. Talend: is a platform that offers Big Data management products and with Master Data Management (MDM), it is able to process real-time data and perform various processes. Finally, it is provided free of charge and has many features

Figure 2: Talend in conjuction with the Hadoop model

4. NoSQL Databases: through this created the profile of patients – clients and quicker diagnosis of rare diseases and direct advice exams in real time.

5. OpenRefine or Data Cleaner: data cleansing tools (Reconciliation Services)

6. Imaging tools: Tableau, CartoDB, Chartio,

7. Programming languages: Python, Scala, Java, R (programming language that performs computational statistics and graphs)

Figure 3. 3D representation of life expectancy and per capita costs (health services and products) in different countries

The health sector currently employs 8 per cent of Eu citizens (10 per cent of the Gross Domestic Product of the European Union) and welfare spending is expected to increase by a third by 2060. The Organization for Economic Co-operation and Development (OECD) estimates that if health care spending increases, it could save 2% of the Gross Domestic Product (GDP) equivalent to a maximum of 330 billion euros in Europe. Finally, according to the Poneman Institute, 30% of global electronic data is related to health.

Some of the causes for the increase in revenue are: an increase in chronic diseases, an aging population and an increase in health care costs (new trends and innovations-more expensive treatment costs). Appropriately utilizing of Big Data in hospitals will enhance the quality of patient care, minimize hospitalizations, minimize diagnostic time, deduce disease progression, and reduce health care costs., since Big Data will imply ways to mitigate the disease.

Figure 4. Estimation of the future contribution of Big Data to health by health care professionals

As health costs decrease, hospital access increases and the quality of health services decreases, while costs increase, so do patients ‘ access and quality of service for those entitled to access.

Figure 5. Iron Triangle of Healthcare

We are grateful to Ms Katsa, Ms Koufioti and Mr Kounios for kindly providing the original article.

For further reading:

  1. Investing in Health, http:/ec.europaeu/health/strategy/docs/swd_investing_in_ health.PDF
  4. hppt://
  7. http:/,
  8. Jacobs A, ( 6 July 2009 ), The Pathologies of Big Data, ACMQueue
  9. Raghuapathi N., Raghupathi V., Big Data analytics in health care : promise and potential, Health Information Science and System, 2014; 2:3
  10. R. Mashey , (25 April 1998), Big Data and the Next Wave of InfraStress (PDF), Slides from invited talk, Usenix
  11. Steve Lohr ( 1 February 2013), The Original of Big Data : an Etymological Detective Story, New York Times
  12. Welcome to Apache Hadoop!,, Accessed 05 April 2017
  13. Zaharia Matei, Chowdhury Mosharaf, Franklin Michael J., Shenker, Scott, Stoica, Ion, Spark ClusterComputing with Working Sets ( pdf), USENIX Workshop on Hot Topics in Cloud Computing ( Hot Cloud)
1 Star2 Stars3 Stars4 Stars5 Stars (5 votes, average: 4.80 out of 5)

Leave a Reply

Your email address will not be published. Required fields are marked *