Applying NoSQL Databases for Operationalizing Clinical Data Mining Models

Part of the Communications in Computer and Information Science book series (CCIS, volume 424)

Abstract

Access to data mining models built in clinical data systems is limited to relatively small groups of researches, while they should be available in real-time to clinicians in order to deliver the results at the point where it is most useful. At the same time, complexity of data processing grows as volume of available data exponentially rises and includes unstructured data. Clinical decision support systems based on relational and multidimensional technology lack capabilities of processing all available data because of its volume and format. On the other hand, NoSQL repositories offer great flexibility and speed in terms of data processing, but requires programming skills. A proposed solution presented in this paper is to combine both of the technologies in a single analytical system. Dual view of the data gathered in the repository allows to use data-mining tools, while Big Data technology delivers necessary data. Key-value style of querying a database enables efficient retrieval of input data for analytical models. Online loading processes guarantee that data is available for analysis immediately after it is produced either by physicians or medical equipment. Finally, this architecture can be successfully moved to the cloud.

Keywords

clinical decision support system big data architecture 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hadoop (February 14, 2014), http://hadoop.apache.org
  2. 2.
    Mongo DB (February 14, 2014), http://www.mongodb.org
  3. 3.
    Bajerski, P., Augustyn, D.R., Bach, M., Brzeski, R., Duszeko, A., Aleksandra, W.: Databases vs. cloud computing. Studia Informatica 33(2A), 9–25 (2012)Google Scholar
  4. 4.
    Data Mining Group: PMML 4.1. Specification (February 14, 2014), http://www.dmg.org/v4-1/GeneralStructure.html/
  5. 5.
    Emam, K.E.: Guide to the De-Identification of Personal Health Information. CRC Press (2013)Google Scholar
  6. 6.
    Groves, P., Kayyali, B., Knott, D., Van Kuiken, S.: The ‘big data’ revolution in healthcare. Tech. rep., McKinsey & Company (January 2013)Google Scholar
  7. 7.
    International Health Terminology Standards Development Organisation (IHTDSDO): SNOMED CT (December 13, 2013), http://www.ihtsdo.org/
  8. 8.
    Khan, A., Doucette, J., Jin, C., Fu, L., Cohen, R.: An ontological approach to data mining for emergency medicine. In: 2011 Northeast Decision Sciences Institute Conference Proceedings 40th Annual Meeting, Montreal, Quebec, Canada, pp. 578–594 (April 2011)Google Scholar
  9. 9.
    Oberije, C.: Mathematical models out-perform doctors in predicting cancer patientsŕesponses to treatment (April 2013), http://www.sciencedaily.com/releases/2013/04/130420110651.htm (retrieved December 13, 2013)
  10. 10.
    Open Data: Augustus. PMML model producer and consumer. Scoring engine (February 14, 2014), https://code.google.com/p/augustus/
  11. 11.
    Savage, N.: Better medicine through machine learning. Commun. ACM 55(1), 17–19 (2012), http://doi.acm.org/10.1145/2063176.2063182 CrossRefGoogle Scholar
  12. 12.
    Yu, S., Rao, B.: Introduction to the special section on clinical data mining. SIGKDD Explor. Newsl. 14(1), 1–3 (2012), http://doi.acm.org/10.1145/2408736.2408738 CrossRefGoogle Scholar
  13. 13.
    Zementis: ADAPA Scoring Engine (February 14, 2014), http://www.zementis.com/adapa.htm/

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Military University of TechnologyWarsawPoland

Personalised recommendations