Artificial-intelligence-augmented clinical medicine

Speaker

Klaus-Peter Adlassnig

Section for Medical Expert and Knowledge-Based Systems,

Center for Medical Statistics, Informatics, and Intelligent Systems, Medical University of Vienna, Austria

 

Abstract

Background

Nowadays, clinical decision making is increasingly based on a large amount of patient medical data, on continuously growing medical knowledge, and on extended best clinical practice guidelines.

Clinical decision support

There is evidence that clinical decision support systems can significantly improve quality of care in, eventually, all areas of clinical medicine [1]. Technically, suitable means to formally represent clinical knowledge and to connect decision support algorithms with patient data sources in a seamless way are prerequisites for successful clinical decision support applications.

Clinical decision support server and Arden Syntax

Arden Syntax, as an internationally standardized formal language for medical knowledge representation and processing [2–4], was implemented as a clinical decision support server and equipped with service-oriented interoperability [5]. This technical solution has already been proven to be deployable in connection with hospital and intensive care information systems and practicable useful in a number of clinical areas [6]. Telemedical and mHealth systems also participate in this technological advance [7].

Routinely-used, fully automated, knowledge-based system for detection and continuous monitoring of ICU-acquired infections

An example for extended clinical decision support in infection control is given by Moni/Surveillance-ICU, a system for the early recognition and the automated monitoring of hospital-acquired infections in intensive care units with adult patients [8–11]. This knowledge-based system includes concepts of fuzziness to formally represent medical linguistic terms. The European Centre for Disease Prevention and Control (ECDC) criteria for hospital-acquired infections [12] form the basis of its knowledge base; results are given in form of degrees indicating to which extent the ECDC definitions are fulfilled by the patient data taken into account.

Artificial-intelligence-augmented clinical medicine

Today, clinical decision support technology becomes integrated in or connected with various health care information systems such as hospital, laboratory, and intensive care information systems, electronic health record, telemedicine, and web-based systems. Thus, many forms of clinical decision support in the diagnostic and therapeutic process render possible, for instance, clinical reminders, alerts, recommendations, support in differential diagnosis, therapy selection, and patient management according to guidelines and protocols. In this context, Arden Syntax, or its extended form Fuzzy Arden Syntax [13, 14], seems highly suitable for developing clinically useful decision support systems. Soon, a new type of proactive clinical information systems will become available. Through web-services, a globally available medical knowledge grid—adapting its content to the individual parameters of the patient—will eventually emerge.

 

References:

[1] Kawamoto, K., Houlihan, C.A., Balas, E.A. & Lobach, D.F. (2005) Improving Clinical Practice Using Clinical Decision Support Systems: A Systematic Review of Trials to Identify Features Critical to Success. British Medical Journal 330(7494), 765–768.

[2] Hripscak, G. (1994) Writing Arden Syntax Medical Logic Modules. Computers in Biology and Medicine 24, 331–363.

[3] Health Level 7. The Arden Syntax for Medical Logic Systems, Version 2.7. Ann Arbor, MI: Health Level Seven, Inc., 2008.

[4] Samwald, M., Fehre, K., de Bruin, J. & Adlassnig, K.-P. (2012) The Arden Syntax Standard for Clinical Decision Support: Experiences and Directions. Journal of Biomedical Informatics 45, 711–718.

[5] Fehre, K. & Adlassnig, K.-P. (2011) Service-Oriented Arden-Syntax-Based Clinical Decision Support. In Schreier, G., Hayn, D. & Ammenwerth, E. (Eds.) Tagungsband der eHealth2011 – Health Informatics meets eHealth – von der Wissenschaft zur Anwendung und zurück, Grenzen überwinden – Continuity of Care, 26.–27. Mai 2011, Wien, Österreichische Computer Gesellschaft, Wien, 123–128.

[6] Adlassnig, K.-P. & Rappelsberger, A. (2008) Medical Knowledge Packages and their Integration into Health-Care Information Systems and the World Wide Web. In Andersen S.K., Klein, G.O., Schulz, S., Aarts, J. & Mazzoleni, M.C. (Eds.) eHealth Beyond the Horizon–Get IT There. Proceedings of the 21st International Congress of the European Federation for Medical Informatics (MIE 2008), IOS Press, Amsterdam, 121–126.

[7] Rudigier, S., Brenner, R. & Adlassnig, K.-P. (2010) Expert-System-Based Interpretation of Hepatitis Serology Test Results as App Store iPhone Application. In Schreier, G., Hayn, D. & Ammenwerth, E. (Eds.) Tagungsband der eHealth2010 – Health Informatics meets eHealth – von der Wissenschaft zur Anwendung und zurück, Der Mensch im Fokus, 6.–7. Mai 2010, Wien, Österreichische Computer Gesellschaft, Wien, 235–240.

[8] Adlassnig, K.-P., Blacky, A. & Koller, W. (2008) Fuzzy-Based Nosocomial Infection Control. In Nikravesh, M., Kacprzyk, J., and Zadeh, L.A. (Eds.) Forging New Frontiers: Fuzzy Pioneers II – Studies in Fuzziness and Soft Computing vol. 218, Springer, Berlin, 343–350.

[9] Adlassnig, K.-P., Blacky, A. & Koller, W. (2009) Artificial-Intelligence-Based Hospital-Acquired Infection Control. In Bushko, R.G. (Ed.) Strategy for the Future of Health, Studies in Health Technology and Informatics 149, IOS Press, Amsterdam, 103–110.

[10] Blacky, A., Mandl, H., Adlassnig, K.-P. & Koller, W. (2011) Fully Automated Surveillance of Healthcare-Associated Infections with MONI-ICU – A Breakthrough in Clinical Infection Surveillance. Applied Clinical Informatics 2(3), 365–372.

[11] De Bruin, J.S., Adlassnig, K.-P., Blacky, A., Mandl, H., Fehre, K. & Koller, W. (2012) Effectiveness of an Automated Surveillance System for Intensive Care Unit-Acquired Infections. Journal of the American Medical Informatics Association, doi:10.1136/amiajnl-2012-000898.

[12] European Centre for Disease Prevention and Control (ECDC). Healthcare-associated Infections Surveillance Network (HAI-Net). http://ecdc.europa.eu/en/activities/surveillance/HAI/Pages/default.aspx.

[13] Vetterlein, T., Mandl, H. & Adlassnig, K.-P. (2010) Fuzzy Arden Syntax: A Fuzzy Programming Language for Medicine. Artificial Intelligence in Medicine 49(1), 1–10.

[14] Vetterlein, T., Mandl, H. & Adlassnig, K.-P. (2010) Processing Gradual Information with Fuzzy Arden Syntax. In Safran, C., Reti, S. & Marin, H. (Eds.) Proceedings of the 13th World Congress on Medical Informatics (MEDINFO 2010), Studies in Health Technology and Informatics 160, IOS Press, Amsterdam, 831–835.