************************************************ % Answers to Frequently Asked Questions on % % Artificial Intelligence in Medicine. % % AIM-FAQ % ************************************************ Version 0.9 Part 3 of 4 [6] AIM RELATED INTERNET RESOURCES (continued from part 2 of FAQ) [6.24] INCLEN-L ADDRESS: INCLEN-L@MCMVM1.CIS.MCMASTER.CA DESCRIPTION: The purpose of this list is to provide units of the International Clinical Epidemiology Network presently connected by electronic mail, with a vehicle for questions and comments to an "expert" in different aspects of clinical epidemiology. To subscribe to this list send a mail/note message to CLIFTONJ@MCMASTER or CLIFTONJ@SSCVAX.CIS.MCMASTER.CA requesting a subscription to list INCLEN-L giving your full name and title. CONTACT: CLIFTONJ@MCMASTER CLIFTONJ@SSCVASX.CIS.MCMASTER.CA [6.25] INFO-GCG ADDRESS: INFO-GCG%UTORONTO.BITNET@VM1.NODAK.EDU DESCRIPTION: Mailing list covering topics in computer aided molecular biology and of particular interest to users and managers of the "Genetics Computer Group" software from the University of Wisconsin. BitNet users can subscribe by sending the following command to LISTSERV@ UTORONTO: SUBscribe INFO-GCG your_full_name where your_full_name is your real name, not your loginid. Non-BitNet users can subscribe by sending the above command in the body of a message to LISTSERV%UTORONTO.BITNET@VM1.NODAK.EDU. CONTACT: Coordinator: John Cargill [6.26] INTUDM-L ADDRESSES: LISTSERV@UTEPA.Bitnet LISTSERV@UTEPVM.EP.UTEXAS.EDU Discuss, conduct and promote interdisciplinary research on the use of intuition in decision making. As archives accumulate they will be stored monthly in INTUDM-L LOGyymm and indexed in INTUDM-L FILELIST. To receive a list of files send the command INDEX INTUDM-L to LISTSERV@UTEPA. To subscribe to INTUDM-L, send the following command to LISTSERV@UTEPA via mail text or interactive message: SUBscribe INTUDM-L Your_full_name. For example: SUBSCRIBE INTUDM-L Joe Student. CONTACT: Listowner: Weton H. Agor [6.27] IRLIST ADDRESS: IRLIST DESCRIPTION: IRList is open to discussion of any topic (vaguely) related to Information Retrieval. Certainly, any material relating to ACM SIGIR (the Special Interest Group on Information Retrieval of the Association for Computing Machinery) is of interest. The field has close ties to artificial intelligence, database management, information and library science, linguistics, etc. A partial list of suitable topics is: Information Management/Processing/Science/Technology AI Applications to IR Hardware aids for IR Abstracting Hypertext and Hypermedia CD-ROM/CD-I/... Indexing/Classification Citations Information Display/Presentation Cognitive Psychology Information Retrieval Applications Communications Networks Information Theory Computational Linguistics Knowledge Representation Computer Science Language Understanding Cybernetics Library Science Data Abstraction Message Handling Dictionary analysis Natural Languages, NL Processing Document Representations Optical disc technology and applications Electronic Books Pattern Recognition, Matching Evidential Reasoning Probabilistic Techniques Expert Systems in IR Speech Analysis Expert Systems use of IR Statistical Techniques Full-Text Retrieval Thesaurus construction Fuzzy Set Theory Contributions may be anything from tutorials to rampant speculation. In particular, the following are sought: Abstracts of Papers, Reports, Dissertations Address Changes Bibliographies Conference Reports Descriptions of Projects/Laboratories Half-Baked Ideas Humorous, Enlightening Anecdotes Histories Questions Requests Seminar Announcements/Summaries Research Overviews Work Planned or in Progress The only real boundaries to the discussion are defined by the topics of other mailing lists. Please do not send communications to both this list and AIList or the Prolog list, except in special cases. The Moderator tries not to overlap much with NL-KR, except when both lists receive materials from contributors or from some bulletin board or researchers. There is no objection to distributing material that is destined for conference proceedings or any other publication. The Coordinator is involved in SIGIR Forum and, unless submittors request otherwise, may include submissions in whole or in part in future paper versions of the FORUM. Indeed, this is one form of solicitation for FORUM contributions! Both IRList and the FORUM are unrefereed, and opinions are always those of the author and not of any organization unless there are other indications. Copies of list items should credit the original author, not necessarily the IRList. The IRLIST Archives will be set up for anonymous FTP, and the address will be announced in future issues. To subscribe send the following command to LISTSERV@UCCVMA.BITNET: SUB IR-L your_full_name where "your_full_name" is your real name, not your login Id. Non-BitNet users can join by sending the above command as the only line in the text/body of a message to LISTSERV%UCCVMA.BITNET@VM1.NODAK.EDU. CONTACTS: Moderator: IRLUR%UCCMVSA.BITNET@VM1.NODAK.EDU Editorial Staff: Clifford Lynch Mary Engle Nancy Gusack [6.28] MEDCONS ADDRESS: MEDCONS%FINHUTC.BITNET@VM1.NODAK.EDU DESCRIPTION: This list is not intended for non-professionals or patients, which still are welcome to follow the activity on the list. It is intended for Physicians and investigators in the medical field to allow medical consulting on a voluntary basis. The final responsibility for the care of patients is always that of the personal Physician exclusively. Short descriptions of cases "hard to solve" in the form anamnesis status and laboratory findings - question: what bothered the patient - followed by the diagnosis and cure are encouraged. Real bedside problem solving could also be enlightened by short descriptions of the most exotic and puzzling cases the colleagues have encountered. Absolute anonymity for the patients is required. Please favour Latin and professional terminology to make it easier to keep laymen from obstructing the list. Contributions from the field of so called alternative medicine are obsolete, and will not be redistributed to the subscribers. BitNet users can subscribe by sending the following command to LISTSERV@FINHUTC: SUBSCRIBE MEDCONS Your_full_name where "Your_full_name" is your real name, not your login Id. Non-BitNet users can join by sending the above command in the text/body of a message to LISTSERV%FINHUTC.BITNET@VM1.NODAK.EDU. CONTACT: Coordinator: Dr. Mikael Peder [6.29] MEDINF-L ADDRESS: MEDINF-L%DEARN.BITNET@CUNYVM.CUNY.EDU DESCRIPTION: Mailing list for people working in medical data processing/medical informatics. For those in BITNET and subscribed to the list its content can be made availabe by: TELL LISTSERV AT DEARN REVIEW MEDINF-L. General information about LISTSERV can be obtained with TELL LISTSERV at DEARN INFO. All requests to be added to or deleted from this list, problems, questions, etc., should be sent to: PL_REI%DHVMHH1.BITNET@CUNYVM.CUNY.EDU or REICHERTZ@SUMEX.STANFORD.EDU. For BITNET users direct subscription is possible by: TELL LISTSERV@DEARN SUBSCRIBE MEDINF-L , and signing off may be done by TELL LISTSERV@DEARN SIGNOFF MEDINF-L. CONTACT: PL_REI%DHVMHH1.BITNET@CUNYVM.CUNY.EDU REICHERTZ@SUMEX.STANFORD.EDU. [6.30] MEDLIB-L ADDRESSES: LISTSERV@UBVM LISTSERV@UBVM.CC.BUFFALO.EDU DESCRIPTION: MEDLIB-L is a forum for librarians in the health sciences. Discussion will include practical and theoretical issues in both the public and technical service areas. This list may be used to exchange ideas, questions, concerns and announcements of particular interest to health sciences librarians. To subscribe to the list send a message or mail to LISTSERV@UBVM on BITNET or LISTSERV@UBVM.CC.BUFFALO.EDU on the Internet with the text or body of the message containing the command SUB MEDLIB-L yourfirstname yourlastname CONTACT: Owner: HSLSTART@UBVM (Nancy Start) Notebook: Yes, public, monthly Subscription: Open [6.31] MEDNETS ADDRESS: MEDNETS%NDSUVM1.BITNET@VM1.NODAK.EDU DESCRIPTION: A forum to discuss medical telecommunication networks in the areas of clinical practice, medical research, and administration. The list is intended to be used for ongoing discussions, information searches, contact searches, surveys, and so on. Contributions sent to this list are automatically archived. You may obtain a list of the available archive files by sending the command "INDEX MEDNETS" to LISTSERV@VM1.NODAK.EDU or LISTSERV@NDSUVM1 on BITNET. These files can then be retrieved by means of a "GET MEDNETS LOGyymmw" command, or by using the database search facilities of LISTSERV. Send an "INFO DATABASE" command to LISTSERV@VM1.NODAK.EDU for more information on DATABASE searches. You may also access these archives via anonymous FTP on the Internet. FTP to host VM1.NODAK.EDU (134.129.111.1) with any password. After you are connected enter CD MEDNETS to access the archives (our file system is NOT hierarchical so to go back to the "root" you would enter CD ANONYMOUS. BitNet users may subscribe by sending a message or e-mail to LISTSERV@NDSUVM1 with the following line in the text/body: SUB MEDNETS your full name where "your full name" is your real name, not your login Id. Non-BitNet users can join the list by sending the above command as the only line in the text/body of a message to LISTSERV@VM1.NODAK.EDU or to LISTSERV%NDSUVM1.BITNET@VM1.NODAK.EDU. CONTACT: Coordinator: Marty Hoag [6.32] MEDNEWS ADDRESS: MEDNEWS%ASUACAD.BITNET@CUNYVM.CUNY.EDU The MEDNEWS LISTSERV list is for distribution of the Health Info-Com Network medical newsletter. It is distributed weekly and contains the latest MMWR from the Center for Disease Control, weekly AIDS Statistics, FDA bulletins, medical news from the United Nations, and other assorted medical news items. Submissions for the newsletter are welcomed; please contact the Editor if you have any questions or newsletter submissions. To subscribe send the following command to LISTSERV@ASUACAD (non-BitNet users send mail to LISTSERV%ASUACAD.BITNET@CUNYVM.CUNY.EDU with the command in the message body): SUBSCRIBE MEDNEWS Your_Full_Name where Your_Full_Name is your real name, not your userid. To unsubscribe, send: UNSUBSCRIBE MEDNEWS CONTACT: Editor: David Dodell [6.33] MEDSTU-L ADDRESS: MEDSTU-L on LISTSERV@UNMVM ADDRESS: The University of New Mexico is pleased to announce that effective immediately, we are hosting a new Listserv discussion list for medical students worldwide. The name of the new list is MEDSTU-L and initially, the list will be unmoderated with subscriptions open. Due to a present limitation on disk storage, notebooks will be kept for a period of 30 days. The impetus for this list was mail I sent out several weeks ago soliciting medical students with e-mail accounts to exchange mail with medical students here. As a result of that solicitation, I found that while there are many medical students with e-mail accounts, most of them are unaware of others with e-mail accounts. Thus, this list. While it is an open list and therefore there is no way of verifying the subscription request, the two list owners respectfully request that the list be limited to students in medical schools. To subscribe to the list send e-mail to LISTSERV@UNMVM and in the body of the message say SUB MEDSTU-L your_first_name your_last_name If you have any questions, please let us know. CONTACTS: Owners: Art St. George STGEORGE@UNMB or STGEORGE@BOOTES.UNM.EDU David Goldstein DGOLDST@UNMB or DGOLDST@BOOTES.UNM.EDU Art St. George, Ph.D. Executive Network Services Officer University of New Mexico High-Tech Access: Soft Touch Access stgeorge@unmb (BITNET) (505) 277-8046 VOICE stgeorge@bootes.unm.edu (Internet) (505) 277-8101 FAX [6.34] ML ADDRESS: ML@ICS.UCI.EDU DESCRIPTION: The Machine Learning List is moderated. Contributions should be relevant to the scientific study of machine learning. Mail contributions to ml@ics.uci.edu. Mail requests to be added or deleted to ml-request@ics.uci.edu. Back issues may be FTP'd from ics.uci.edu in pub/ml-list/V/ or N.Z where X and N are the volume and number of the issue; ID: anonymous PASSWORD: CONTACT: Moderator: Michael Pazzani [6.35] NEURON [Last Update 11/92] ADDRESS: NEURON@@cattell.psych.upenn.edu DESCRIPTION: NEURON is a list (in digest form) dealing with all aspects of neural networks (and any type of network or neuromorphic system), especially: NATURAL SYSTEMS Software Simulations Neurobiology Hardware Neuroscience Digital ARTIFICIAL SYSTEMS Analog Neural Networks Optical Algorithms Cellular Automatons Some key words which may stir up some further interest include: Hebbian Systems Widrow-Hoff Algorithm Perceptron Threshold Logic Holography Content Addressable Memories Lyapunov Stability Criterion Navier-Stokes Equation Annealing Spin Glasses Locally Couples Systems Globally Coupled Systems Dynamical Systems (Adaptive) Control Theory Back-Propagation Generalized Delta Rule Pattern Recognition Vision Systems Parallel Distributed Processing Connectionism Any contribution in these areas is accepted. Any of the following are reasonable: Abstracts Reviews Lab Descriptions Research Overviews Work Planned or in Progress Half-Baked Ideas Conference Announcements Conference Reports Bibliographies History Connectionism Puzzles and Unsolved Problems Anecdotes, Jokes, and Poems Queries and Requests Address Changes (Bindings) Archived files/messages will be sent to individuals on request. All requests to be added to or deleted from this list, problems, questions, etc., should be sent to neuron-request@cattell.psych.upenn.edu CONTACT: Moderator: Peter Marvit [6.36] NL-KR ADDRESS: nl-kr@cs.rpi.edu DESCRIPTION: NL-KR is open to discussion of any topic related to the natural language (both understanding and generation) and knowledge representation, both as subfields of AI. The Moderator's interests are primarily in: Knowledge Representation Natural Language Understanding Discourse Understanding Philosophy of Language Plan Recognition Computational Linguistics Contributions are also welcome on topics such as: Cognitive Psychology (as related to NL/KR) Human Perception (same) Linguistics Machine Translation Computer and Information Science (as may be used to implement various Logic Programming (same) NL systems) Contributions may be anything from tutorials to speculation. In particular, the following are sought: Puzzles and Unsolved Problems Anecdotes, Jokes, and Poems Abstracts Reviews Lab Descriptions Research Overviews Work Planned or in Progress Half-Baked Ideas Conference Announcements Conference Reports Bibliographies History of NL/KR Queries and Requests Address Changes (Bindings) This list is in some sense a spin-off of the AIList, and as such, a certain amount of overlap is expected. The primary concentration of this list should be NL and KR, that is, natural language (be it understanding, generation, recognition, parsing, semantics, pragmatics, etc.) and how we should represent knowledge (aquisition, access, completeness, etc. are all valid issues). Topics deemed to be outside the general scope of this list will be forwarded to AIList (or other more appropriate list) or rejected. Readers are warned not to submit any information that is export-controlled or classified. All requests to be added to or deleted from this list, problems, questions, etc., should be sent to NL-KR-REQUEST@cs.rpi.edu. CONTACT: Moderator: Christopher Welty weltyc@cs.rpi.edu [6.37] RNA ADDRESS: LISTSERV@UTFSM.BITNET DESCRIPTION: RNA is a Neural Net list in Spanish. Lista de Informacion sobre Redes de Neuronas Artificiales. RNA es una lista dedicada a todas aquellas personas interesadas en el desarrollo e investigacion en el campo de las Redes de Neuronas Artificiales. El proposito de esta lista es intercambiar informacion, favorecer el encuentro de personas con intereses afines, promover la formacion de grupos de trabajos y servir de apoyo a quienes se integran al area. Debido a los objetivos de esta lista, el idioma oficial sera el castellano, aceptandose tambien contribuciones en ingles. Existe abundante literatura en este campo y se recomienda a los interesados revisar los trabajos del grupo PDP que estan ampliamente difundidos. Para subscribirse enviar el siguiente comando : TELL LISTSERV AT UTFSM SUB RNA nombre apellido en el caso de no poder mensajes interactivos, enviar una nota a LISTSERV@UTFSM.BITNET con el siguiente mensaje en el cuerpo de la nota: SUB RNA nombre apellido CONTACT: ?? [6.38] SIMULATION ADDRESSES: simulation@UFL.EDU comp.simulation (UseNet newsgroup) DESCRIPTION: All topics connected with simulation are welcome; some sample topics are: Real time simulation methods Flight simulation Parallel architectures for simulation analysis and modeling Simulation and training Distributed simulation Artificial intelligence and simulation Automatic generation and analysis of models Analog vs. digital methods, hybrids Continuous, discrete, and combined methods Qualitative modeling Application specific questions Theory of simulation and systems Queries and comments about available simulation software Announcements of simulation-related talks and seminars Graphics and image processing in simulation All requests to be added to or deleted from this list, problems, questions, etc., should be sent to simulation-request@UFL.EDU. CONTACT: Moderator: Paul Fishwick [6.39] SMDM-L [Last Updated 28-January-1992] ADDRESSES: LISTSERV@DARTCMS1.BITNET LISTSERV@DARTCMS1.DARTMOUTH.EDU DESCRIPTION: SMDM-L is a new electronic bulletin board service for members of The Society for Medical Decision Making and others interested in the theory and practice of decision making. The online community draws from a diversified group including physicians and other heath care professionals, students, hospital and health administrators, policy analysts, health economists, educators, computer analysts, psychologists and medical ethicists. Discussion topics include the analysis of decision making as it applies to clinical practice, to the establishment of health care policies, and to the administration of health care programs. In addition, the service will post announcements of general interest to the decision making community. SMDM-L is a moderated list with subscription open to all. To subscribe send the command SUB SMDM-L yourfistname yourlastname to LISTSERV@DARTCMS1 or to LISTSERV@DARTCMS1.DARTMOUTH.EDU. Questions should be directed to the list owner. CONTACT: Owner: James Levin, MD PhD [6.40] SNURSE-L [Last Update 3/93] ADDRESSES: LISTSERV@UBVM.BITNET LISTSERV@UBVM.CC.BUFFALO.EDU DESCRIPTION: This list has been established as an effort to initiate undergraduate nursing students to a world of electronic health data. SNURSE-L has a number of different goals lined up: 1. The collection and processing of health data. 2. Discussion of trends and issues in nursing. 3. Enhanced communication between undergraduate student nurses. 4. An area for communication among nursing student leaders. Any users who wish to join this list should send the following command to LISTSERV@UBVM or LISTSERV@UBVM.CC.BUFFALO.EDU via e-mail as the first line in the BODY of the mail message, not the subject line: SUB SNURSE-L your full name For example: SUB SNURSE-L Jane/John Doe Send the HELP or INFO commands to LISTSERV@UBVM.BITNET or LISTSERV@UBVM.CC.BUFFALO.EDU for more information. CONTACT: Owner: Dan Fisher, Senior BSN student FISHERD@SCSUD.CTSTATEU.EDU [6.41] SOUTHEAST FLORIDA AIDS INFORMATION NETWORK - NATIONAL LIBRARY OF MEDICINE ADDRESS: 129.171.78.1 DESCRIPTION: This database contains information on AIDS research organizations, and individuals working within these organizations located in southeastern Florida. Information also available includes educational and informational services on AIDS topics, health and social services, and research eligibility. This database was created with the help of the National Library of Medicine. Access: telnet 129.171.78.1 Login: library Select L on main menu Select 1 on next menu [6.42] TELEMED [Last Updated 3-March-1993] ADDRESS: listserv@leon.nrcps.ariadne-t.gr DESCRIPTION: The subject of this mailing list is the Greek Telemedicine project. To register, send a message to the previous address, containing in an empty line the following command : SUB TELEMED CONTACT: List owners: Dr D. Sotiriou, S. Deftereos [6.43] VIRTU-L [Last Updated 28-January-1992] ADDRESS: LISTSERV@UIUCVMD.BITNET LISTSERV@VMD.CSO.UIUC.EDU DESCRIPTION: A bi-directional gateway for the Usenet newsgroup sci.virtual-worlds. This is a discussion of all aspects of virtual reality. The mailing list is not moderated. If you have access to the Usenet network of newsgroups, you probably do not need to subscribe to this mailing list. All notes to the mailing list are sent automatically for posting to sci.virtual-worlds, at the discretion of the newsgroup moderators. All sci.virtual-worlds posts are automatically sent to LISTSERV subscribers. Caution: Traffic on this mailing list is fairly high! Expect about 10-30 messages per day, some of which are lengthy. To subscribe: Send email to the Listserv address, either: LISTSERV@UIUCVMD (for Bitnet) or LISTSERV@VMD.CSO.UIUC.EDU (for Internet) with the following text: SUB VIRTU-L where is your 'True Name,' (NOT your email address!!!) To unsubscribe: Send email to the same Listserv address as above, with the text: UNSUB VIRTU-L Archives: Listserv does NOT maintain archives of this mailing list. Archives of all posts to sci.virtual-worlds are maintained by the newsgroup sponsors (see below). Archives are available via anonymous FTP to milton.u.washington.edu Sponsorship: The Usenet newsgroup sci.virtual-worlds is sponsored by the Human Interface Technology Laboratory at the University of Washington, Seattle. Although the Listserv redistribution is sponsored by the University of Illinois and Greg Newby, the HITL crew deserves most of the credit for this important forum. CONTACT: The List owner: Greg Newby Graduate School of Library and Information Science, and National Center for Supercomputing Applications, at the University of Illinois at Urbana-Champaign Email: gbnewby@vmd.cso.uiuc.edu or gbnewby@uiucvmd.bitnet Phone: 217-333-3280 [6.44] VISION-LIST ADDRESS: VISION-LIST@ADS.COM DESCRIPTION: Discussion group for artificial intelligence vision researchers. The list is intended to embrace discussion on a wide range of vision topics, including physiological theory, computer vision, artificial intelligence technology applied to vision research, machine vision algorithms, industrial applications, robotic eyes, implemented systems, ideas, profound thoughts -- anything related to vision and its automation is fair game. Previous messages are available on request to Vision-List-Request@ADS.COM. All requests to be added to or deleted from this list, problems, questions, etc., should be sent to Vision-List-Request@ADS.COM. CONTACT: Moderator: Tod Levitt ******************************************************************** [7] SECTION: AIM SYSTEMS IN ROUTINE CLINICAL USE SECTION DESCRIPTION: This list contains summaries of AI based clinical systems that are in routine clinical use. It attempts to exclude systems that are of an experimental or prototypic nature. Send submissions and corrections to Enrico Coiera: ewc@hplb.hpl.hp.com Recommended Submission Format: SYSTEM NAME: BRIEF DESCRIPTION: LOCATION: CONTACT:
DATE COMMISSIONED: DESCRIPTION: REFERENCES: SECTION INDEX. [7.1] ACUTE CARE SYSTEMS [7.1.1] ACORN [7.1.2] POEMS [7.1.3] VIE-PNN [7.2] LABORATORY SYSTEMS [7.2.1] BECTON DICKINSON SYSTEMS [7.2.2] GERMWATCHER [7.2.3] HEPAXPERT I, II [7.2.4] INTERPRETATION OF ACID-BASE DISORDERS [7.2.5] LIPORAP [7.2.6] PEIRS [7.2.7] PUFF [7.3] EDUCATIONAL SYSTEMS [7.3.1] CANCER, ME? [7.3.2] DXPLAIN [7.3.3] ILIAD [7.4] QUALITY ASSURANCE AND ADMINISTRATION [7.4.1] APACHE III [7.4.2] COLORADO MEDICAID UTILIZATION REVIEW SYSTEM [7.4.3] GERIATRIC DISCHARGE PLANNING SYSTEM [7.4.4] MANAGED SECOND SURGICAL OPINION (MSO) SYSTEM [7.5] MEDICAL IMAGING [7.5.1] PERFEX [7.5.2] PHOENIX [7.5.3] THALLIUM DIAGNOSTIC WORKSTATION Information is requested on the following systems: o QMR o AI/Rheum o Possum - recognizes genetic anomalies o University of Utah diagnostic system for Emergency Medical Procedures. TOTAL working systems = 20 Need info on = 4 TOTAL = 24 [7.1] ACUTE CARE SYSTEMS [7.1.1] ACORN (Admit to the Ccu OR Not) BRIEF DESCRIPTION: Hybrid rule-based & Bayesian system for advising on management of chest pain patients in the emergency room LOCATION: Accident & Emergency Department Westminster Hospital, London CONTACT: Jeremy Wyatt jeremy@biu.icnet.uk DATE COMMISSIONED: 1987 DESCRIPTION: Medical audits determined that 38% of patients attending with acute ischaemic heart disease were sent home in error and the median time till CCU admission for the remainder was 115 minutes. ACORN, a hybrid backward- chaining rule-based and Bayesian system, was built for use by senior nurses to assist in the management of these patients. In a randomised controlled trial on 150 patients in 1987 the false negative rate in both control & ACORN cases fell to 20%; this may have been a carryover or Hawthorne effect. This trial also identified significant problems with ACORN, and it was subsequently revised and appeared to be effective at reducing the median time to CCU admission by 20 minutes, though this was an uncontrolled study. The system was in routine use at Westminster during 1987-90. In 1990: the mean usage rate per eligible case claimed by the 15 users was 77%, but when unequivocal evidence of use was looked for in the patient records, this was present in only 23% of eligible cases. There were approx. 15 eligible cases per week = 750 per year, so this scales up to between 175 and 580 uses of ACORN per annum. REFERENCES: Wyatt J. "The evaluation of clinical decision aids: a discussion of methodology used in the ACORN project", Lecture Notes in Medical Informatics 1987; 33: 15- 24. Wyatt J (1989). Lessons learned from the field trial of ACORN, an expert system to advise on chest pain. In: Barber B, Cao D, Qin D, eds. Proc. Sixth World Conference on Medical Informatics, Singapore. Amsterdam: North Holland 1989: 111-115 Emerson PA, Russell NR, Wyatt JC et al. (1989). An audit of the management of patients attending an accident and emergency department with chest pain. Quart J Med 1989; 70: 213-220 Wyatt J, Spiegelhalter D. Field trials of medical decision-aids: potential problems and solutions. In Clayton P (ed). Proc. 15th Symposium on Computer Applications in Medical Care, Washington 1991. New York: McGraw Hill Inc. 1991: 3-7 Wyatt J. "Computer-based knowledge systems". The Lancet 1991; 338: 1431-1436 Heathfield HA, Wyatt J. Philosophies for the design and development of clinical decision-support systems. Meth Inform Med 1993; 32:1-8 Wyatt J, Spiegelhalter D. The evaluation of medical expert systems. In: Evans D, Patel V (eds), Advanced models of cognition for medical training and practice. MIT Press, 1992 (NATO ASI series F97): 101-120 [7.1.2] POEMS (PostOperative Expert Medical System) BRIEF DESCRIPTION: Decision support system for Post-Operative care LOCATION: St. James University Hospital, Leeds, U.K. CONTACT: M. J. Sawar Computer Based Learning Unit Leeds University, U.K. sawar@cbl.leeds.ac.uk DATE COMMISSIONED: 1992 DESCRIPTION: Post-operative care can present considerable problems to medical staff who are relatively inexperienced. Deciding when to take a specific action based on monitoring signs and other available data, or distinguishing between major or minor changes of the monitoring signs and diagnostic expectations, are complex tasks. They are especially difficult when senior medical support is not readily available. During the last two years a collaborative expert system (POEMS: Post- Operative Expert Medical System), has been developed to give advisory and decision support to less experienced staff. POEMS interactively receives data obtained from the patients based on the standard strategy used by the medical staff: Past medical history, Operative history, History, Examination, and Investigative tests. From this data, POEMS presents an ordered list of very-likely, likely, possible and not-likely candidate diagnoses and can answer questions on how the diagnosis was reached, what treatment would be most suitable, and what further investigative action could be taken to focus on a particular diagnostic candidate. POEMS employs a temporal modeller to reason over real time which is very useful for on-ward decision support and advice. POEMS learns diagnostic knowledge from the patient cases presented to it for diagnosis. It employs a learning apprentice system to evaluate and learn from the patient cases, the diagnosis reached at by POEMS, and the confirmation or rejection advice provided by an expert. REFERENCES: M. J. Sawar, T. G. Brennan, A. J. Cole and J. Stewart "POEMS (PostOperative Expert Medical System)" in Proceedings of IJCAI91 one Day Workshop: "Representing Knowledge in Medical Decision Support Systems", Sydney, Australia, Aug. 1991. M. J.Sawar, T. G. Brennan, A. J. Cole and J. Stewart "An Expert System for PostOperative Care (POEMS)", in Proceedings of MEDINFO-92, Geneva, Switzerland, Sept. 1992. [7.1.3] VIE-PNN BRIEF DESCRIPTION: Expert System for composition of parenteral nutrition of neonates in Intensive Care Units (ICUs). LOCATION: VIE-PNN (Vienna Expert System for Parenteral Nutrition of Neonates) was developed in cooperation with the Austrian Research Institute for Artificial Intelligence (OeFAI), the Department of Medical Cybernetics and Artificial Intelligence and the Department of Pediatrics, University of Vienna (Austria). CONTACT:Silvia Miksch Austrian Research Institute for Artificial Intelligence (OeFAI) Schottengasse 3 A-1010 Vienna, Austria tel: +43-1-5353281-0 fax: +43-1-5320652 email: silvia@ai.univie.ac.at DESCRIPTION: The planning of an adequate nutritional support for meeting the metabolic requirements of sick neonates is a tedious and time consuming calculation, needs practical expert knowledge and involves the risk of introducing possibly fatal errors. The interactive support system VIE-PNN was developed to calculate the composition of parenteral nutrition solutions (PNS) for neonates in intensive care units. The aims were to avoid errors within certain limits, to save time, and to keep data for further statistical analysis. Daily requirements are determined in units per kilogram body weight and are adjusted according to the patient's age, body weight, and clinical conditions (e.g. specific diseases, past and present-day blood analysis). The system uses default values and strategies of estimation in the absence of real values. The physician may accept or adjust proposed values. VIE- PNN offers the facility to adjust compositions of the PNS to the total fluid intake, which is often difficult when total fluid allowance is restricted. This task is time consuming if done by hand. Finally, the PNS may be reduced according to the proportion of oral feedings. The final output is a PNS schedule form, which can directly be used in the case history of neonates. Textbook rules of nutrition planning are combined with the knowledge of experienced physicians. The dynamic and static knowledge is represented in a frame structure and backward chaining rules. A knowledge acquisition module supports the input of new bypasses and new oral feeding products. A technical, empirical and subjective evaluation of the system was performed. It proved VIE-PNN's soundness, its ability to provide a standard for the composition of parenteral nutrition, and its clinical applicability. VIE-PNN implements a standard for the composition of parenteral nutrition of neonates, eliminates possible errors and frees the physician from time-consuming calculations. One benefit of our evalution was the isolation of a standard PNS for not severe ill neonates. The standard PNS is a premixtured parenteral nutrition infusion. Currently, VIE-PNN is used for severe ill neonates and the standard PNS for the other neonates. This minimizes the nurses' daily amount of mixtures of parenteral nutrition infusions, which is time-consuming and dangerous. REFERENCES: Miksch S., Popow C., Horn W., Dobner M.: Struktur und Funktionalitaet von VIE-PNN: Ein Expertensystem zur Berechnung der parenteralen Ernaehrung von intensiv behandelten Frueh- und Neugeborenen, Oesterreichisches Forschungsinstitut fuer Artificial Intelligence, Wien, TR-92-17, 1992. Miksch S., Dobner M., Horn W., Popow C.: VIE-PNN: An Expert System for Parenteral Nutrition of Neonates, Proc. Ninth IEEE Conference on Artificial Intelligence for Applications (CAIA-93), Orlando Florida, March 1-5, 1993. Miksch S., Dobner M., Horn W., Popow C.: An Interactive Support System for Neonate-Specific Nutrition Planning at Intensive Care Units (VIE-PNN), AISB Quarterly, 82,24-30, 1993. [7.2] LABORATORY SYSTEMS [7.2.1] BECTON DICKINSON LABORATORY SYSTEMS BRIEF DESCRIPTION: 1. QBC (TM) haematology analyser 2. The Sceptor (TM) MIC interpreter LOCATION: CONTACT: Joan Curry Becton Dickinson Research Centre 21 Davis Drive RTP, NC 27709 Tel. (919) 990-2110 Fax (919) 549-7572 curry@bdrc.bd.com DESCRIPTION: Becton Dickinson, an international health care technology company, has two systems that were developed at the corporate R&D centre and are in routine use by customers. 1. QBC (TM) Reference System. This system is integrated into the QBC haematology analyser product line and provides possible medical interpretations of a patient's haematologic test results. It is used primarily in physicians' office laboratories. 2. The Sceptor (TM) MIC interpreter. This system is integrated into the Data Management Centre for the Sceptor line of microbial detection instruments. The instrument determines the Minimum Inhibitory Concentration values (i.e. the minimum amount of an antibiotic needed to kill bacteria) for a variety of drugs; from these values, the expert system generates a clear interpretation of whether the drugs will be effective against the organism. The rules for this system are based on the National Committee on Clinical Laboratory Standards' guidelines for MIC interpretation. The Sceptor system is used primarily by hospital microbiology labs. [7.2.2] GERMWATCHER BRIEF DESCRIPTION: GermWatcher is a system for analysis of nosocomial infections. LOCATION: Barnes Hospital, St. Louis, Missouri CONTACT: Dr. Michael Kahn kahn@informatics.wustl.edu or Sherry Steib sherry@informatics.wustl.edu Washington University School of Medicine Department of Internal Medicine Division of Medical Informatics 660 South Euclid Campus Box 8005 St. Louis, Missouri 63110 USA DATE COMMISSIONED: 1993 DESCRIPTION: GermWatcher is a rule-based expert system which applies both local Barnes Hospital and NNIS (National Nosocomial Infection Surveillance System) culture-based criteria for detecting potential hospital-acquired infections. It works by monitoring microbiology culture data (which reside on the Hospital's Microbiology Laboratory Information System) and then reporting its findings to the Barnes Hospital Infection Control nursing staff. It has been in use by the four Infection Control nurses since February, 1993. GermWatcher and a companion expert system called `GermAlert' were developed jointly with the Barnes Hospital Infection Control nursing staff and the Washington University School of Medicine. Each day, the hospital Microbiology Lab reports an average of 650 positive cultures, and that culture data is examined by both expert systems. Approximately 80 of those cultures need no further processing by the lab, and are termed "final," because they will not be reported again. The remaining 580 cultures are being monitored by lab technicians, and will be reported each day until they become final. GermWatcher scans the final cultures, identifying those which represent possible nosocomial infections. GermAlert scans all the cultures, identifying those which require immediate attention on the part of the nurses. Both expert systems use the same culture data, but different rule bases. Both run in batch mode at night. An interactive user interface, which runs on a PC in the Infection Control Department, allows the nurses to view the expert system results. Currently no measurements of cost reduction or quality improvement are available, but one manual data entry job was made obsolete by the new systems. REFERENCES: M. Kahn, S. Steib, V. Fraser, W. Dunagan, An Expert System for Culture-Based Infection Control Surveillance, Proc. SCAMC-93 (to appear). [7.2.3] HEPAXPERT I, II BRIEF DESCRIPTION: Automatic Interpretation of tests for Hepatitis A and B. LOCATION: Hepatitis Lab University of Vienna Medical School CONTACT: Klaus-Peter Adlassnig Dept. of Medical Computer Science University of Vienna Garnisongasse 13 A - 1090 Vienna Austria DATE COMMISSIONED: 1989 DESCRIPTION: Automatic Interpretation of tests for Hepatitis A and B. Developed using a rule based representation on the RULEMASTER shell the system consists of over 100 rules. The system has been in routine at the Hepatitis Lab of University of Vienna Medical school since Sept. 1989. Prior to use the system was tested with about 25,000 cases and the acceptance by the doctors has been found to be quite high. REFERENCES: KP Adlassnig, W Horak, Routinely-used, automated interpretive analysis of hepatitis A and B serology findings by a medical expert system, Proc. Medical Informatic Europe `90, R. O'Moore et al. (eds), Lecture Notes in Medical Informatics, 40, Springer-Verlag, 313-318. KP Adlassnig, W Horak, Hepaxpert I: Automatic interpretation of Tests for Hepatitis A and B, MD Computing, 8,2,(1991),118-119. [7.2.4] INTERPRETATION OF ACID-BASE DISORDERS BRIEF DESCRIPTION: Expert system for interpretation of acid-base disorders LOCATION: University Hospital CONTACT: Dr. Pince Hilde Department of Medical Informatics University Hospital Gasthuisberg Herestraat 49 B - 3000 Leuven Belgium EARN address: feeee03@blekul11.bitnet email: FEEEE03%BLEKUL11.BITNET@pucc.Princeton.EDU DATE COMMISSIONED: 1989 DESCRIPTION: In routine use in the intensive care unit and the emergency department of the university hospital since end 1989 producing about 7500 reports per year Hardware: SUN 3/160 Software: BIM-Prolog Input: Blood gas data and serum electrolytes Output: a single, double or triple acid-base disorder. Two versions were developed: an interactive version (with explanation facilities, requested lists of causes...), and a version integrated in the Laboratory Information System (this version is in routine use) REFERENCES: Pince H, Verberckmoes R, Willems JL, Computer aided interpretation of acid-base disorders, Int. J. Biomed. Comp. 25:177-192, 1990. [7.2.5] LIPORAP BRIEF DESCRIPTION: Automatic Phenotyping of dyslipoproteinemia LOCATION: University Hospital Gasthuisberg CONTACT: Dr. Pince Hilde Department of Medical Informatics University Hospital Gasthuisberg Herestraat 49 B - 3000 Leuven Belgium EARN address: feeee03@blekul11.bitnet email: FEEEE03%BLEKUL11.BITNET@pucc.Princeton.EDU DATE COMMISSIONED: 1987 DESCRIPTION: In routine use in central laboratory since July 1987. Outputs about 1000 reports per year Hardware: IBM-PC Software: LPA-Prolog Input parameters: Total cholesterol, TG, HDL,LDL,VLDL, Phospholipids, Interpretation of the serum lipoprotein electrophoresis, Interpretation of the "standing plasma test" Output:-classification of the lipoprotein pattern as a Frederickson type or as a more rare disease (Tangier, LP-X...) -background information: chronic diseases and drugs which might explain the lipoprotein pattern of the patient [7.2.6] PEIRS (Pathology Expert Interpretative Reporting System) BRIEF DESCRIPTION: Interpretative reporting of chemical pathology reports LOCATION: Department of Chemical Pathology, St Vincent's Hospital, Sydney CONTACT: Dr Glenn Edwards Department of Chemical Pathology St Vincent's Hospital Sydney, New South Wales AUSTRALIA Telephone: (612) 361 2156 glenn@cs.unsw.oz.au DATE COMMISSIONED: May 1991. DESCRIPTION: PEIRS (Pathology Expert Interpretative Reporting System) appends interpretative comments to pathology reports. The knowledge aqusition strategy is the Ripple Down Rules method, which has allowed a pathologist to build over 1900 rules without knowledge engineering or programming support. New rules are added in minutes, and maintenance tasks are a trivial extension to the pathologist's routine duties. PEIRS currently comments on about 100 reports/day. Domains covered include thyroid function tests, arterial blood gases, glucose tolerance tests, hCG, catecholamines and a range of other hormones. REFERENCES: Edwards G, Compton P, Malor R, Srinivasan A, Lazarus L. PEIRS: a pathologist maintained expert system for the interpretation of chemical pathology reports. Pathology 1993;25:27-34 Compton P, Edwards G, Srinivasan A, Malor R, Preston P, Kang B, Lazarus, L. Ripple down rules: turning knowledge acquisition into knowledge maintenance. Artificial Intelligence in Medicine 1992;4(6):463-475 Compton P. A philosophical basis for knowledge acquisition. Knowledge Acquisition 1990;2:241-257. [7.2.7] PUFF BRIEF DESCRIPTION: The PUFF system diagnoses the results of pulmonary function tests. LOCATION: Pacific Presbyterian Medical Center CONTACT: John Kunz kunz@cive.STANFORD.EDU DATE COMMISSIONED: 1977 DESCRIPTION: PUFF went into production at Pacific Presbyterian Medical Center in San Francisco in 1977. Several implementations and many thousands of cases later, it is still in routine use. The PUFF technology was originally developed in the late-19070's by researchers from and Pacific Presbyterian Medical Center and Stanford. The PUFF basic knowledge base was incorporated into the commercial "Pulmonary Consult" product. Several hundred copies have been sold and are in use around the world. REFERENCES: Kunz, J.C., R.J. Fallat, D.H. McClung, et. al., "Automated interpretation of pulmonary function test results". Proceedings of Computers in Critical Care and Pulmonary Medicine, IEEE Press, 1979. Aikins, J.S., Kunz, J.C., Shortliffe, E.H., Fallat, R.J., "PUFF: An expert system for interpretation of pulmonary function data", Computers in Biomedical Research, 16, pp. 199-208, 1983. Snow, M.G., Fallat, R.J., Tyler, W.R., Hsu, S.P., "Pulmonary Consult: Concept to Application of an Expert System", Journal of Clinical Engineering 13:3, pp. 201- 205, 1988. [7] AIM SYSTEMS IN ROUTINE CLINICAL USE (continued in part 4 of FAQ)