Abstract
Intensive care units use sophisticated patient monitoring systems that produce massive amounts of physiological streaming data. Critical care physicians manage several hundred of time-critical health-related variables a day in the course of their work, using data from multiple disjoint systems, running in silos. Patient monitoring devices produce hundreds of alarms per day for each patient, with approximately 90 % being insignificant. These have introduced a significant data and decision overload problem. We present state- of-the-art big data analytical approaches that address these problems. We describe how the combination of “at rest” data mining analytics and streaming analytics is transforming critical care by enabling applications that improve clinicians’ situation awareness at the bedside. We describe novel system architectures together with real-world deployments of big data analytical technologies in critical care environments that are helping physicians to be more proactive in delivering timely care.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Notable examples of data acquisition systems for ICU monitoring devices are Excel Medical Electronics (with their BedMasterEX and BedCom products), CapsuleTech, Airstrip (with their Airstrip ONE product), iSirona and IBM (with its Healthcare Integration Bus product).
- 2.
Excel Medical Electronics offers today a research platform based on OHA that interfaces its BedMasterEX and BedCom data acquisition products with IBM InfoSphere Streams, the stream computing runtime of OHA. Airstrip announced recently its plan to integrate its Airstrip ONE product with InfoSphere Streams.
- 3.
Example companies participating in the Streaming Analytics workshops are CleMetric (http://www.clemetric.com/), Synchronicity In Motion (http://synchronicityinmotion.com/) and UNSCRAMBL (http://unscrambl.com/).
References
Ahmad S, Tejuja A, Newman K, Zarychanski R, Seely A. Clinical review: a review and analysis of heart rate variability and. Crit Care. 2009;13:232.
Arts DG, de Keizer NF, Vroom MB, de Jonge E. Reliability and accuracy of Sequential Organ Failure Assessment (SOFA) scoring. Crit Care Med. 2005;33(9):1988–93. Retrieved from Medscape: http://www.medscape.com/viewarticle/512520_1.
Bai Y, Sow D, Vespa P, Hu X. Real-time processing of continuous physiological signals in a neurocritical care unit on a stream data analytics platform. In: Beng-Ti Ang C, (ed) Intercranial Pressure and Brain Monitoring XV, 1st Edition, Acta Neurochirurgica Suppl. Springer International Publishing, 2016;122(1), DOI 10.1007/978-3-319-22533-3.
Bradley B, Green GC, Batkin I, Seely AJ. Feasibility of continuous multiorgan variability analysis in the intensive care unit. J Crit Care. 2012;27(2):218.e9–20.
Bryce R, Sprague B. Revisiting detrended fluctuation analysis. Sci Rep. 2012;2:315. doi:10.1038/srep00315.
Buchman T. Novel representation of physiologic states during critical illness and recovery. Crit Care. 2010;14:127.
Buchman T. How one hospital is making intensive care smarter with analytics. 2013. Retrieved from A Smarter Planet Blog: http://asmarterplanet.com/blog/2013/11/smarter-care-analytics.html
Cvach M. Monitor alarm fatigue: an integrative review. Biomed Intrum Methodol. 2012;46(4):268–77.
Ebbers M, Abdel-Gayed A, Budhi VB, Dolot F, Kamat V, Picone R, Trevelin J. Addressing data volume, velocity, and variety with IBM InfoSphere Streams V3.0. 2013. Retrieved from IBM Redbooks: http://www.redbooks.ibm.com/abstracts/sg248108.html?Open
Endsley MR. Toward a theory of situation awareness in dynamic systems. Hum Factors. 1995;37(1):32–64.
Gopal Reddy S. Big data saves small babies by detecting nosocomial infections earlier than clinicians. 2014. Retrieved from nuviun connecting great minds: http://nuviun.com/content/news/big-data-saves-small-babies-by-detecting-nosocomial-infections-earlier-than-clinicians
Hamilton PS, Tompkins WJ. Quantitative investigation of QRS detection rules using the MIT/BIH arrhythmia database. IEEE Trans Biomed Eng. 1996;33(12):1157–65.
Hunter D. Excel medical electronics – #BigData for healthcare. 2013. Retrieved from IBM Innovation Center – Chicago: https://www.ibm.com/developerworks/community/blogs/Chicagoiic/entry/excel_medical_electronics_bigdata_for_healthcare?lang=en
IBM. Capture and analyze data in motion. (no date a). Retrieved from InfoSphere Streams: http://www-03.ibm.com/software/products/en/infosphere-streams
IBM. SPSS software: predictive analytics software and solutions. (no date b). Retrieved from http://www-01.ibm.com/software/analytics/spss/
Imhof M. Dimension reduction for physiological variables using graphical modeling. AMIA annual symposium. AMIA; 2003. p. 313–17.
The Joint Commission. The Joint Commission Announces 2014 National Patient Safety Goal. 2013. Retrieved from Joint Commission Perspectives, ®, Volume 33, Issue 7: http://www.jointcommission.org/assets/1/18/jcp0713_announce_new_nspg.pdf
Kirchner P, Böhm M, Reinwald B, Sow D, Schmidt M, Turaga D, Biem A. Large scale discriminative metric learning. In: IPDPS workshops. Phoenix: IEEE; 2014. p. 1656–63.
Koch SH, Weir C, Haar M, Staggers N, Agutter J, Görges M, Westenskow D. Intensive care unit nurses’ information needs and recommendations for integrated displays to improve nurses’ situation awareness. J Am Med Inform Assoc. 2012;19(4):583–90.
Lake DE, Richman JS, Griffin P, Moorman R. Sample entropy analysis of neonatal heart rate variability. Am J Physiol. 2002;283(3):R789–97.
Machine Learning Group at the University of Waikato. Weka 3: data mining software in Java. (no date). Retrieved from http://www.cs.waikato.ac.nz/ml/weka/
M.H. The economist: Babbage science and technology. 2012. Retrieved from Medical devices: a ticking time-bomb: http://www.economist.com/blogs/babbage/2012/05/medical-devices
Manor-Shulman O, Beyene J, Frndova H, Parshuram CS. Quantifying the volume of documented clinical information in critical illness. J Crit Care. 2008;23(2):245–50.
Massachusetts Institute of Technology. MIMIC II. (n.d.). Retrieved from mimic.physionet.org: https://mimic.physionet.org/
Mathworks. MATLAB: the language of technical computing. 1994–2014. Retrieved from http://www.mathworks.com/products/matlab/
Matthews SC, Pronovost PJ. The need for systems integration. J Am Med Assoc. 2011;305(9):934–5.
McGregor C, James A, Eklund M, Sow D, Ebling M, Blount M. Real-time multidimensional temporal analysis of complex high volume physiological data streams in the neonatal intensive care unit. Stud Health Technol Inform. 2013;192:362–6.
Patel VL, Kaufman DR, Cohen T, editors. Cognitive informatics in health and biomedicine. Case studies on critical care, complexity and errors. London: Springer; 2014.
Patrizio A. Helping doctors stitch together real-time data to help intensive care patients. 2013. Retrieved from citeworld.com: http://www.citeworld.com/article/2115650/big-data-analytics/helping-doctors-stitch-together-real-time-data-to-help-intensive-care-patients.html?null
Pohlman,TH. Trauma scoring systems. 2014. Retrieved from Medscape: http://emedicine.medscape.com/article/434076-overview
The R Foundation. The R project for statistical computing. (no date). Retrieved from http://www.r-project.org/
Richman JS, Moorman R. Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol Heart Circ Physiol. 2000;278(6):H2039–49.
Schmidt JM, Sow DM, Crimmins M, Albers D, Agarwal S, Claassen J, Mayer SA. Heart rate variability for preclinical detection of secondary complications after subarachnoid hemorrhage. Neurocrit Care. 2014;20(3):382–9.
Sow D, Turaga DS, Schmidt M. Mining of sensor data in healthcare: a survey. In: Aggarwal C, editor. Managing and mining sensor data. New York: Springer; 2013. p. 459–504.
Stony Brook Medicine. Severe sepsis/septic shock recognition and treatment protocols. 2013. Retrieved from http://www.survivingsepsis.org/SiteCollectionDocuments/Protocols-Sepsis-Treatment-Stony-Brook.pdf
Sun J, Sow D, Hu J, Ebadollahi S. A system for mining temporal physiological data streams for advanced prognostic decision support. In: International conference on data mining (ICDM). Sydney: IEEE; 2010. p. 1061–6.
Terry K. ICU platform first to integrate, analyze monitoring data. 2013. Retrieved from informationweek.com: http://www.informationweek.com/healthcare/clinical-information-systems/icu-platform-first-to-integrate-analyze-monitoring-data/d/d-id/1109600?
Weiser M, Brown JS. Designing calm technology. Powergrid J. 1996;1(1):75–85.
Winchell RJ, Hoyt DB. Spectral analysis of heart rate variability in the sepsis syndrome. J Surg Res. 1996;63(1):11–6.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Sow, D.M. (2016). Big Data Analytical Technologies and Decision Support in Critical Care. In: Weaver, C., Ball, M., Kim, G., Kiel, J. (eds) Healthcare Information Management Systems. Health Informatics. Springer, Cham. https://doi.org/10.1007/978-3-319-20765-0_30
Download citation
DOI: https://doi.org/10.1007/978-3-319-20765-0_30
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20764-3
Online ISBN: 978-3-319-20765-0
eBook Packages: MedicineMedicine (R0)