Wilson F. Engel: AI in the ER for Real-Time EBM: A Family of Web-Enabled Intelligent Agents for Non-Intrusive, User-Friendly Application of Evidence-Based Medicine in Actual Practice CSIT 2000 : 55-60
Last Century as Millennial "Y2K" fears compounded and armies of unsung heroes struggled to assure that no electronic Apocalypse would upset the cyber-future, a few intrepid, seasoned pioneers of the computer-and-telecommunications revolution began with hope to consider what might be possible "after" in the best case. They dared to carry forward apparently disparate ideas to their inevitable integrations in systems whose power and ubiquity will transform life, work, thought and even, perhaps, the nature of humankind. Kurzweil, for example, in The Age of Spiritual Machines (1999) envisioned that by the year 2030 Artificial Intelligence (AI) shall have become a friendly and useful complement to human activity. Others wrote about entire new families of software-advantaged medical appliances. We now envision the evolution of a family of Intelligent Agents (IA) for medicine. Built within a shared, privacy-sensitive and secure evolutionary context for medical missions, this "IA family" will directly, but not obtrusively, assist clinicians in real-time analysis-and-response "steps" through refining probabilities, reducing risks -- and pain, improving care, saving lives, raising practitioners' confidence and limiting both institutional and personal liabilities. Responsible creativity must begin to render this vision practical in an iterative process involving many players, particularly user-practitioners who value Evidence-Based Medicine (EBM). Indeed, AI is one catalyst by which EBM can be directed, as originally intended, to improving care. The Emergency Room (ER), augmented by AI, is just the right arena in which to demonstrate the power of filtering and focusing the plethora of new statistical data on actual practice. With the proper technical framework, evolutionary design engineering can improve ER care and also constructively affect, inter alia, the three-tiered medical record, the electronic chart, the cycle times from research to practice to research again, the agility and viability of telemedicine nd disaster relief, and the currency and efficacy of medical education.
Copyright © 2000 by the Institute for Contemporary Education "JurInfoR-MSU". Permission to copy without fee all or part of this material is granted provided that the copies are not made or distributed for direct commercial advantage, the CSIT copyright notice and the title of the publication and its date appear, and notice is given that copying is by permission of the Institute for Contemporary Education JMSUICE. To copy otherwise, or to republish, requires a fee and/or special permission from the JMSUICE.
Heinz Schweppe and Yuri S. Kabalnov (Eds.): CSIT'2000, Proceedings of 2nd International Workshop on Computer Science and Information Technologies, September 18-23, 2000, Ufa, Russia. USATU Publishers & JurInfoR-MSU Publishing 2000, ISBN 5-86911-312-1