Lab and field tests measured response rates when writing on different parts of the clipboard.Lower rates in field test because clipboard was on metal work surface of anaesthetic machine.
Field tests measured response rates at different areas of the drug trolley.
Polar plots show 6-point ‘fingerprints’ – signal strength values from 2 tags at 3 readers
Very simple explanation of how sequences of fingerprints build up an activity
Field tests highlight existing SOMs much less accurate on new data => inconsistency of signal strength from day-to-day
Short- to medium-term work
TADAA - Towards Automated Detection of Anaesthetic Activity
HINZ_PostGrad_13 TADAA 1Aura Laboratory
HINZ_PostGrad_13 TADAA 2My road to Health Informatics1Anaesthetic activity 2OutlineResearch methodology3Design and development 4Results and Conclusion5
HINZ_PostGrad_13 TADAA 3Your Text here Your Text hereYour Text hereYour Text hereMy road to Health Informatics• 1991 Graduated B.Comm• 91 - 02 Worked in software development• 03 – 04 M.InfoTech at AUT
HINZ_PostGrad_13 TADAA 4Your Text here Your Text hereYour Text hereYour Text hereAnaesthesia• “Extreme approximation of death” (Euliano, 2004)• “…that even today we understand but partly”(Eger, 2006)• “Every complication has the potential tocause lasting harm to the patient…deviations from the norm must be recognisedpromptly and managed appropriately”(Aitkenhead, 2007)
HINZ_PostGrad_13 TADAA 5Your Text here Your Text hereYour Text hereYour Text hereComplications• 49% of preventable adverse events due to„system factors‟• Poor record keeping• Lack of information• Few standard procedures• Failure to adhere to standards• Poor communication• Organisational culture (Davis, 2003)
HINZ_PostGrad_13 TADAA 6Your Text here Your Text hereYour Text hereYour Text hereSolutions• Standard procedures• WHO Safer Surgery Checklist• Recording, Adherence to procedures
HINZ_PostGrad_13 TADAA 7Task analysis• “A scientific description of theanaesthetist’s task patterns and workloadwould aid in our understanding of thenature of anaesthetist’s job…and providea rational basis for making improvements”(Weinger, 1994)• “A scientific description of theanaesthetist’s task patterns and workloadwould aid in our understanding of thenature of anaesthetist’s job…and providea rational basis for making improvements”(Weinger, 1994)• Evidence-based medicine requiresscientific data to justify improvements
HINZ_PostGrad_13 TADAA 8Gold standard for data collection
HINZ_PostGrad_13 TADAA 10Can we build a system ableto capture more scientificdata, with less risk ofdistraction, and lowerongoing cost?Scientificvalue ?PotentialdistractionExpensiveAutomated Observation ?
HINZ_PostGrad_13 TADAA 11Design Science methodology(Offermann, 2009)Humans are not idealinstrument for captureof scientific dataAnaesthetic recordDrug PrepLocation + orientationAURA LabACSC field testSimulated procedures
HINZ_PostGrad_13 TADAA 18Activity Fingerprinting• Signal strength „fingerprint‟ built up frommultiple tags and readers
HINZ_PostGrad_13 TADAA 19Activity Fingerprinting 2• Fingerprints associated with a location +orientation through SOM clustering
HINZ_PostGrad_13 TADAA 20Activity Fingerprinting 3= Drug Admin IV• Location + orientation sequences associatedwith activity through HMM analysis1 second at drug trolleythen 2 seconds at machinethen 3 seconds at patient
HINZ_PostGrad_13 TADAA 25Conclusion• ARAZ very good at sensing Recording activity• DTAZ good at sensing Drug Prep– But needs more rules to distinguish otheractivity at drug trolley• AF very good at sensing anaesthetist location +orientation– But requires better activity inferencemechanism• RFID sensors less distracting than observers• Higher upfront cost, but lower ongoing cost
HINZ_PostGrad_13 TADAA 27Future development• Real-time viewer– Communication to staff outside theatre• Repository of activity records– Research unfamiliar procedures– Mine by anaesthetist– Mine by procedure type, patient condition, etc• Formulate „best practice‟ for procedure– Recognise deviations in real-time, raise alarm
HINZ_PostGrad_13 TADAA 29ReferencesAitkenhead, A. R., Smith, G., & Rowbotham, D. J. (Eds.). (2007). Textbook of Anaesthesia(Fifth ed.): Elsevier Limited.Davis, P., Lay-Yee, R., Briant, R., Ali, W., Scott, A., & Schug, S. (2003). Adverse events in NewZealand public hospitals II: preventability and clinical context. New Zealand Medical Journal,116(1183).Duong, T. V., Bui, H. H., Phung, D. Q., & Venkatesh, S. (2005). Activity Detection andAbnormality Detection with the Switching Hidden Semi-Markov Model. Paper presented atthe IEEE Conference on Computer Vision and Pattern Recognition.Euliano, T. Y., & Gravenstein, J. S. (2004). Essential Anaesthesia From Science to Practice.Cambridge, UK: Cambridge University Press.Kohonen, T. (2008). Data Management by Self-Organising Maps. Paper presented at the IEEEWorld Conference on Computational Intelligence, Hong Kong, June 1-6.29Anaesthesia > Task Analysis > TADAA > Evaluation > Conclusion
HINZ_PostGrad_13 TADAA 30ReferencesPeffers, K., Tuunanen, T., Rothenberger, M. A., & Chatterjee, S. (2008). A Design ScienceReseach Methdology for Information Systems Research. Journal of ManagementInformation Systems, 24(3), 45-77.Slagle, J., Weinger, M. B., Dinh, M. T. T., Brumer, V. V., & Williams, K. (2002). Assessment ofthe Intrarater and Interrater Reliability of an Established Clinical Task Analysis Methodology.Anesthesiology, 96(5), 1129-1139.Smith, A. F. (2009). In Search of Excellence in Anesthesiology. Anesthesiology, 110(1), 4-5.Weinger, M. B., Herndon, O. W., Zornow, M. H., Paulus, M. P., Gaba, D. M., & Dallen, L. T.(1994). An Objective Methodology for Task Analysis and Workload Assessment inAnaesthesia Providers. Anesthesiology, 80(1), 77-92.30Anaesthesia > Task Analysis > TADAA > Evaluation > Conclusion