************************************************ % Answers to Frequently Asked Questions on % % Artificial Intelligence in Medicine. % % AIM-FAQ % ************************************************ Version 0.9 Part 4 of 4 [7] AIM SYSTEMS IN ROUTINE CLINICAL USE (continued from part 3 of FAQ) [7.3] EDUCATIONAL SYSTEMS [7.3.1] CANCER, ME?? BRIEF DESCRIPTION: Expert system for automated delivery of personal advice on how to reduce risk of cancer. LOCATION: Videotext trial in Montreal, Canada, (1,000 Users); Disk based trials in Calgary, Alberta, Ongoing CONTACT: Ivan H. Zendel Foothills Hospital Division of Psychology l403 - 29 Street N.W. Calgary, Alberta T2N 2T9 403 670-4789 Canada IZendel@UNCAMULT.BITNET DATE COMMISSIONED: 1989 DESCRIPTION: Has been used by approx. 2,000 people `Cancer, Me??' provides users with personalized cancer prevention information. It addresses concerns such as: "What aspects of my lifestyle increase my risk of getting cancer?"; "What can I do to reduce that risk?"; and "How do I improve chances for early detection?". `Cancer, Me??' engages the user in an interview. It begins the consultation by asking the user introductory and demographic questions, then asks about the user's motivation for using `Cancer, Me??'. The main consultation is divided into four sections (Smoking and Smoke Exposure, Diet, Sun Exposure and Health Practices) which the user can choose in any order, and an Evaluation section. In each section the user is asked questions having to do with lifestyle, medical and personal background and family health history. Information gathered from the user's answers, either directly or by inference, is subsequently used throughout the consultation. Thus, the user is addressed by his/ her name; data such as the user's sex and age affect the inclusion as well as the content and phrasing of various sections. [7.3.2] DXPLAIN BRIEF DESCRIPTION: diagnosis in internal medicine LOCATION: CONTACT:Octo Barnett Lab of Computer Science Mass General Hospital Harvard Medical School 50 Staniford St Boston MA 02114 USA obarnett@hstbme.mit.edu DESCRIPTION: DXplain is a decision support system which acts on a set of clinical findings (signs, symptoms, lab data) to produce a ranked list of diagnoses which might explain (or be associated with) the clinical manifestations. DXplain uses a large data base of findings associated with over 2400 different diseases and a quasi Baysian logic. It was developed at the Laboratory of Computer Science at the Mass General Hospital and the program development was greatly influenced by Jack Myers and Randy Millers work on Internist/QMR which is similar in concept and execution. The program is available (through a license with MGH) for a nominal fee for execution on a PC (DOS) or on a network. In addition it is available over the US HealthLink Network (800-682-8770 for info on network access) DXplain is in routine use at between 20-50 hospitals and medical schools, in part for education of students, and in part for clinical consultation. It is very difficult to make generalization about the systems's penetration and impact - the evidence is mostly anecdotal and impact varies greatly from institution to institution [7.3.3] ILIAD BRIEF DESCRIPTION: medical diagnosis in internal medicine LOCATION: University of Utah School of Medicine's Dept. of Medical Informatics CONTACT: SKRISHNA@CC.UTAH.EDU DESCRIPTION: At the University of Utah School of Medicine's Dept. of Medical Informatics, an Expert System program called Iliad has been under development for the past several years. Iliad uses Bayesian reasoning to calculate the posterior probabilities of various diagnoses under consideration, given the findings present in a case. Iliad which was developed primarily for diagnosis in Internal Medicine, now covers about 1500 diagnoses in this domain, based on several thousand findings. The Iliad shell has also been used to develop knowledge bases for diagnosis in other domains. Iliad was developed initially for the Apple Mac; a version for the PC-AT running windows has also been released. Current use: primarily as a teaching tool for medical students. Particular cases can be simulated thru' this program and the students have to "diagnose" the case (i.e. extract all relevant useful information to make the diagnosis from the computer in the most efficient manner possible). This helps the students sharpen their skill in differential diagnosis. It is anticipated that in the coming years, the Iliad program will become a widely used adjunct for clinical diagnosis and patient data documentation in the setting of the physician's office or clinic (at least in the USA). REFERENCES: Journal of Medical Systems 15(1):93-110 1991 [7.4] QUALITY ASSURANCE AND ADMINISTRATION [7.4.1] APACHE III BRIEF DESCRIPTION: Acute Physiology and Chronic Health Evaluation LOCATION: 1/ Ann Arbor Catherine McAuley Health System Ann Arbor, Michigan 2/ Beaumont Hospital, Royal Oak, Michigan 3/ Ford Hospital, Detroit, Michigan CONTACT: Gary Gagnon (Senior Vice President APACHE Medical Systems) ggagnon@apa.com or Michelle Morin mlm@discovery.cl.msu.edu DESCRIPTION: The APACHE III system was designed to predict an individual's risk of dying in the hospital. It compares each individual's medical profile against nearly 18,000 cases in its memory before reaching a prognosis that is, on average, 95 percent accurate. There are 16 hospitals in the U.S. where APACHE III is in use or in the process of being installed. There are approximately another 40 hospitals worldwide where the APACHE III Methodology is used to generate reports which compare their actual average ICU outcomes to ones predicted by the APACHE III Methodology. The system was developed by William A. Knaus, an intensive-care physician at George Washington University. In 1978 he and several colleagues at GWU began collecting and computerizing the experience of intensive care patients from dozens of hospitals. The computer considered each patient as a complicated sum of several variables: diagnosis and physiological abnormalities on admission to the ICU, age, pre-existing medical problems, etc. The system was designed as a way to judge how the hospitals were doing in terms of the mortality rate of its patients. A physician can give the computer system 27 easily obtained facts, and the program would predict that patient's risk of dying in the hospital. The system is also useful in answering the question: Is treatment making a difference? Studies have shown that about half the deaths in American Intensive Care Units now occur after a deliberate decision has been made to stop "heroic" measures. While APACHE does not make such decisions, its advocates say it helps those who must make them ponder the issues in the fairest and most realistic way. [7.4.2] COLORADO MEDICAID UTILIZATION REVIEW SYSTEM BRIEF DESCRIPTION: An expert system which performs quality review of drug prescribing for Medicaid patients. LOCATION: Dept. of Preventive Medicine and Biometrics, Section on Medical Informatics, University of Colorado Health Sciences Center Denver, CO 80262, U.S.A. CONTACT: TED D. WADE UNIV. COLORADO HEALTH SCIENCES CENTER tedwade@tropiq.colorado.edu DATE COMMISSIONED: 1990 DESCRIPTION: The system has been in continuous operation since 1990. It reviews thousands of patient medical histories per month, looking for temporal patterns of events which indicate scenarios of either hazardous or unnecessarily expensive prescribing. The reviews are retrospective, based on clinical information extracted from billing data. The output reports are reviewed by a peer review panel before a decision is made to intervene in writing to the doctors or nursing homes involved in the problems. The panel agrees with the computer about 70% of the time overall, although for some problem scenarios agreement is virtually 100%. This contrasts with commercial systems, not using ES technology, who are lucky to get 10% agreement. Medicaid (the Colorado agency for indigent medical care) loves the system. It at least pays for itself in various kinds of savings, including some serendipitous discoveries of fraud and/or billing errors. We have a randomized trial which indicates that our intervention significantly changed prescribing behavior to less expensive non-steroidal anti-inflammatory drugs. The program cost $500,000 and 7-person-years to develop. It runs on about $200,000/year. Two physicians, one pharmacist and three informatics specialists were the development team. The operational director now is Patricia Byrns, MD, an internist and one of the developers. The local medical society and the American Medical Association believe that the program provides useful information to health-care providers about fragmentation of care, about the patient's drug-taking and care-seeking behavior, and about current standards of care. We have numerous testimonial letters to that effect. REFERENCES: P.J. Byrns, D.C. Lezotte, and J. Bondy, "Influencing the cost- effectiveness of prescribing using claims-based information: a randomized trial", submitted to J. Am. Med. Assoc. T.D. Wade, P.J. Byrns, J.F. Steiner, and J. Bondy, "Finding temporal patterns -- a set-based approach", submitted to Artificial Intelligence in Medicine. [7.4.3] GERIATRIC DISCHARGE PLANNING SYSTEM BRIEF DESCRIPTION: LOCATION: CONTACT: Laurence Moseley Computer Science UC Swansea SA2 8PP UK cslaurie@pyramid.swansea.ac.uk DESCRIPTION: We have had a geriatric discharge planning system working, plus several training programs for nurses, plus a pressure area care one (which has a fascinating knowledge acquisition history). REFERENCES: [7.4.4] MANAGED SECOND SURGICAL OPINION (MSO) SYSTEM BRIEF DESCRIPTION: LOCATION: CONTACT: Tod Loofbourrow loofbour@husc.harvard.edu DATE COMMISSIONED: 1989 DESCRIPTION: Developed by Foundation Technologies, Inc. and Medical Intelligence, Inc. for Aetna Life and Casualty. The system has been in routine use since 1989. The expert system provides an automated second surgical opinion for areas where surgery is often overprescribed. That automated second surgical opinion is send to a second opinion physician, who can review both attending physician and expert system based comments to adjudicate several opinion and make the clinically best decision. The system has had a major impact on reducing the incidence of unnecessary surgery, and is helping its user to provide more consistent and higher quality care in its managed care networks. REFERENCES: presented at the Expert Systems in Insurance Conference in Boston in October of 1991 by Irene Scheibner of Aetna. You can obtain a copy of the proceedings from IBC at 508- 60-4700 or Fax them at 508-653-1627. [7.5] MEDICAL IMAGING [7.5.1] PERFEX BRIEF DESCRIPTION: expert system called automatic interpretation of Cardiac SPECT data LOCATION: Emory University Hospital CONTACT: Rakesh Mullick rakesh@cc.gatech.edu DESCRIPTION: At Georgia Tech., we have developed a rule based expert system called PERFEX, for automatic interpretation of Cardiac SPECT data. This system infers the extent and severity of coronary artery disease (CAD) from perfusion distributions, and provides as output a patient report summarizing the condition of the three main arteries and other pertinent information. The work on this project has been done in collaboration with Emory University Hospital. The overall goal is to assist in the diagnosis of coronary artery disease. The approach employs knowledge based methods to process and map the 3D visual information into symbolic representations, which are subsequently used to infer structure (anatomy) from function (physiology), as well as to interpret the temporal effects of perfusion redistribution, and assess the extent and severity of cardiovascular disease both quantitatively and qualitatively. The knowledge based system presents the resulting diagnostic recommendations in both visual and textual forms in an interactive framework, thereby enhancing overall utility. At present, PERFEX is implemented in an object oriented environment using Neuron Data's Nexpert Object). This object oriented framework provides a some advantages, including inheritance properties and C code. This software, however, has been extensively modified to incorporate the CF Model (which is intimately linked to inferencing) and to allow for a dynamic user interface. The system is undergoing extensive evaluation - Specially multi- centre testing, which will be followed by filing for FDA approval. The system itself has been already ported to a commercial clinical system and will be released as a demo or extension package in late May. REFERENCES: N. F.Ezquerra and R. Mullick and E. V. Garcia and C. D. Cooke and E. Kachouska, PERFEX: An Expert System for Interpreting 3D Myocardial Perfusion", Expert Systems with Applications, Pergamon Press, (1992) R. Mullick and N. F. Ezquerra and E. V. Garcia and C. D. Cooke, A Knowledge- Based System to Assist in the Diagnosis of Coronary Artery Disease, Proceedings of the Tenth Southern Biomedical Engineering Conference, 107-9, 1991 R. Mullick and N. F. Ezquerra, Research in Medical Informatics at Georgia Tech.: An Overview, Proceedings of the 1991 IEEE Region 10 International Conference on Energy, Computer, Communications, and Control Systems - TENCON `91 New Delhi, INDIA, 2, 63-70, 1991 N. F. Ezquerra and E. V. Garcia, Artificial Intelligence in Nuclear Medicine Imaging, American Journal of Cardiac Imaging, 3, 2, 130-41, 1989 E. V. Garcia and M. D. Herbst and C. D. Cooke and N. F. Ezquerra and B. L. Evans and R. D. Folks and E. G. DePuey, Knowledge-based Visualization of myocardial perfusion tomographic images, vbc90, 157-61, 1990 [7.5.2] PHOENIX BRIEF DESCRIPTION: Radiology Consultant LOCATION: University of Chicago CONTACT: Charles Kahn ckahn@post.its.mcw.edu DESCRIPTION: The PHOENIX Radiology Consultant was developed at the University of Chicago to help referring physicians select the most appropriate radiologic procedures. The system saw quite frequent use during a two-year clinical trial, and appeared to help improve the process of selecting imaging procedures. The system was taken off-line because some of the knowledge has become out- of-date. REFERENCES: Kahn CE Jr. Validation, clinical trial and evaluation of a radiology expert system. Methods of Information in Medicine 1991; 30:268-274.) [7.5.3] THALLIUM DIAGNOSTIC WORKSTATION BRIEF DESCRIPTION: TDW learns to diagnose thallium myocardial scintigraphy from a training set of examples. LOCATION: USAF School of Aerospace Medicine. CONTACT: Rin Saunders RSAUNDER@opus.starlab.csc.com DESCRIPTION: The Thallium Diagnostic Workstation is an AIM application deployed at the USAF School of Aerospace Medicine. TDW learns to diagnose thallium myocardial scintigraphy from a training set of examples. Digitized images are acquired by a gamma camera and send to TDW via ethernet. TDW performs considerable low-level vision processing, then extracts features of diagnostic significance using template-based techniques. The physician can view the images and TDW's findings simultaneously on-screen. TDW uses induction to learn diagnostic rules. A rule learned from 150 cases diagnosed by cardiac catheter outperforms the best human diagnostician at the school by a few percentage points. Users can view imagery, enter their own findings and diagnosis, select a rule from a catalogue of rule sets (each rule is accompanied by performance statistics), and perform automated diagnosis. REFERENCES: TDW was published in SCAMC `89 and in IAAI-3. *********************************************************************** [8] SECTION: COMMERCIAL AND PUBLIC DOMAIN AIM SOFTWARE SECTION DESCRIPTION: This section of the FAQ deals with commercial and public domain software in the area of AI in Medicine. The information here is based on clippings received from members of the AI-medicine mailing list. Note that the relevance of each software to AIM has not been verified in each case. This section has two parts. [8A] includes software for which relatively complete information is available. In [8B], items generally from the public domain, with less information is listed. Send submissions and corrections to Sasikumar M.: sasi@saathi.ncst.ernet.in Recommended Submission Format: SOFTWARE NAME: CATEGORY: {provide one or two subject descriptors} NATURE: {Commercial or Public Domain} AVAILABLE FROM: {provide address, phone, email etc.} PRICE: LICENSING RESTRICTIONS: HARDWARE PLATFORMS : SUPPORTING SOFTWARE REQUIREMENTS : - INFORMATION SOURCE : {contact name} REFERENCES: OTHER COMMENTS (reviews, articles, details, etc): *********************************************************************** [8A]: Software for which relatively complete information is available. SUBSECTION INDEX. [8A.1] EXP EXPERT ADVICE SYSTEM DEVELOPMENT TOOL [8A.2] HUGIN REGULAR, HUGIN API [8A.3] KARDIO [8A.4] RTWORKS [8A.5] THE SLEEP CONSULTANT ************************************************************************ [8A.1] EXP EXPERT ADVICE SYSTEM DEVELOPMENT TOOL CATEGORY: Expert system development tool. NATURE: Commercial AVAILABLE FROM [ftp addr, email addr, organisation, mail server]: Dr. Ivan Zendel Artifin Software 120 Pump Hill Bay SW Calgary Alberta Canada EMAIL: zendel@bacs.hsc.ucalgary.ca PRICE (for non public domain systems): $3000 Can ; 2,500 USD LICENCING RESTRICTIONS : - HARDWARE PLATFORMS : IBM PC / Mac / Unix SUPPORTING SOFTWARE REQUIREMENTS : none INFORMATION SOURCE : S Wakefield [swakefie@bacs.hsc.ucalgary.ca] REFERENCES: - OTHER COMMENTS (reviews, articles, etc): Expert system development tool supports backward and forward chaining construction. Allows static "confidence level" weighting for inputs to rules. Great facility for interface screens. [8A.2] HUGIN REGULAR, HUGIN API CATEGORY: Expert System NATURE: Commercial AVAILABLE FROM [ftp addr, email addr, organisation, mail server]: demoversion anonymous ftp from hugin.dk (129.142.51.10) full version HUGIN EXPERT A/S Niels Jernes VEJ 10 DK-9220 Aalborg Denmark Phone: +45 9815 6644 FAX: +45 9815 8550 EMAIL: info@hugin.dk PRICE (for non public domain systems): ECU 6.000,00 - 15.000,00 USD 7.200,00 - 18.000,00 (more details below) LICENCING RESTRICTIONS: HARDWARE PLATFORMS: Sun workstations SUPPORTING SOFTWARE REQUIREMENTS: INFORMATION SOURCE: sven@hugin.dk (Sven Vestergaard) REFERENCES: 1. Steffen L Lauritzen and David J. Spiegelhalter. "Local computation with probabilities on graphical structures and their application to expert systems (with discussion)". Journal of the Royal Statistical Society, Series B, 50:157-224, 1988. 2. D.J. Spiegelhalter and S.L. Lauritzen. "Sequential updating of conditional probabilities on directed graphical structures". Networks, 20:579-605, 1990. 3. S.K. Andersen, K.G. Olesen, F.V. Jensen, and F. Jensen. "HUGIN - a shell for building Bayesian belief universes for expert systems." Proceedings of the Eleventh International Joint Conference on Artificial Intelligence (IJCAI), Detroit, MI, 1989. 4. F.V. Jensen, et al. "Bayesian methods for interpretation and control in multi-agent vision systems." Proceedings from Applications of Artificial Intelligence, X, Orlando, Florida, 1992. To appear. 5. F.V. Jensen, Steffen L Lauritzen, and K.G. Olesen. "Bayesian updating in causal probabilistic networks by local computation". Computational Statistics Quarterly, 4:269-282, 1990. OTHER COMMENTS (reviews, articles, details, etc): There are two products * HUGIN API (Application Program Interface) A C library with a large collection of function for compiling and running expert systems. * HUGIN Regular A graphical user interface build on top of the C library. And the current prices are: * HUGIN Regular/HUGIN API 1 user license ECU 7500 2 user license - 11250 site license - 15000 * HUGIN API 1 user license ECU 6000 2 user license - 9000 site license - 12000 All prices are quoted in ECU (European Currency Unit). April 7.,1993, the exchange rate was 1 ECU ~ 1.2 USD. Currently the graphical interface, HUGIN Regular, only runs on Sun workstations. The API C library can easily be ported to other platforms (NeXT, Apple, PC ...), as it is pure C code. The only thing needed is a decent C compiler and the necessary floating point libraries. An evaluation copy of HUGIN is available to allow investigation of the system in the context of specific problems. The only limitation in the evaluation copy is a time limit. In order to obtain this evaluation copy, the vendor needs the 'hostid' of the Sun Sparc station where the evaluation copy should run. You get the hostid by simply issuing the command `hostid' at the shell prompt (this will give you an 8 digit hexadecimal number). In addition, they are interested in a description of the work carried out during the evaluation period. [8A.3] KARDIO CATEGORY: Expert System NATURE: Public Domain AVAILABLE FROM [ftp addr, email addr, organisation, mail server]: anonymous ftp from ftp.ai.univie.ac.at (directory kardio) contact: Igor Mozetic Austrian Research Institute for Artificial Intelligence (ARIAI) Schottengasse 3 A-1010 Vienna Austria FAX: (+43 1) 532-0652 TELEPHONE: (+43 1) 533-6112 EMAIL: igor@ai.univie.ac.at PRICE (for non public domain systems): - LICENCING RESTRICTIONS : Any user should reference relevant publications (see README file in distribution) HARDWARE PLATFORMS: All (see next item) SUPPORTING SOFTWARE REQUIREMENTS: any standard Prolog (eg, Quintus, SISCtus, C-Prolog, ...) INFORMATION SOURCE: Igor Mozetic REFERENCES: - OTHER COMMENTS (reviews, articles, etc): The KARDIO system was designed to diagnose cardiac arrhythmias from symbolic descriptions of electrocardiograms. [8A.4] RTworks CATEGORY: Software Development Tools for Real Time Systems. NATURE: Commercial AVAILABLE FROM: Talarian Corporation 444 Castro Street, Suite 140 Mountain View, CA 94041 telephone: 415-965-8050 fax: 415-965-9077 email: info@talarian.com PRICE (for non public domain systems): --contact the organisation-- LICENCING RESTRICTIONS : -- not specified -- HARDWARE PLATFORMS : Unix, VMS, DOS, and Windows SUPPORTING SOFTWARE REQUIREMENTS : -- INFORMATION SOURCE : Don Gray REFERENCES: -- OTHER COMMENTS (reviews, articles, etc): RTworks is used to build applications that monitor and control complex real-time systems. Talarian Corporation provides significant new technology to make it easier to process and present information to operators of real-time systems. Our RTworks software products consist of a set of powerful tools designed to acquire data, distribute data through a network of workstations, process that data through a real-time inference engine and then present the data to the user through a sophisticated graphical user interface. RTworks is a set of application development tools for programmers, but if you so desire, our Systems Integration Division can provide you with turn-key solutions using the same technology. Training classes are also offered on a regular basis. Talarian is already successfully providing systems in many different customer applications, including the ground control station for NASA's Hubble Space Telescope. The NASA system allows an operator to easily monitor, analyze, and display sensor data and alarms, as well as perform remote commanding of the satellite. In the commercial world, RTworks is being used by a number of customers in applications such as utility distribution monitoring, process control, telecommunications network monitoring and transportation management. Evaluation copies are also available if you would like to have a closer look at the product. Talarian Corporation provides powerful and innovative software development tools that allow application developers to acquire, analyze, distribute and display real-time or time critical data. Resulting applications allow users of large, complex systems to more efficiently process and display real-time data in a meaningful way and to operate their business with greater efficiency, safety and lower operating costs. Talarian Corporation's flagship product, RTworks, combines several advanced technologies, including real-time inferencing, sophisticated graphical user interfaces, client-server data distribution across heterogeneous networks, high speed data archiving, and real-time data acquisition. RTworks' open architecture allows for easy integration with other commercial software packages such as relational databases or real-time operating kernels as well as existing customer programs for data collection, modeling or simulation. Version 2.1 has added many new features including two new products, RTarchive and RTplayback, support for users of the C++ language, hot restart of RTserver, enhanced alarm handling, and a number of new commands and callable functions. In addition to training, consulting and providing state-of-the-art development tools to application builders, Talarian also provides System Integration services to clients who prefer to purchase a turn-key system or need help in developing an application. Talarian has installed systems at customer sites in six target market segments: the utilities industry; process control and factory automation; telecommunications network monitoring; C3I/aerospace; transportation management; and real-time financial applications. The RTworks architecture is based on a client-server model that is inherently distributed. Clients can ensure that they receive the information they need from RTserver. An application is composed of multiple modules of various functionality working together across a network of heterogeneous workstations or PC's. This distributed architecture provides for maximum flexibility in deploying applications. By distributing the functions of an application over independent processes, an application can maximize throughput and response. RTworks currently consists of the following modules: Interprocess Communications Server which allows RTworks processes to communicate with each other, as well as with user defined processes, across a network. Inference Engine Process which uses rule-based inferencing, statistical analysis, trending functions, objects and classes to analyze data in real-time. Human-Computer Interface which provides a sophisticated point-and-click graphical user interface to the system operator. Data Acquisition Process which acquires, filters and groups the incoming sensor data and sends it to RTServer for distribution to other processes. Data Archive Process which rapidly records selected data or messages to disk for archival storage and historical logging purposes. Data Playback Process which retrieves data and messages from long-term storage for report generation or playback to other RTworks processes. Data Generation Process which allows a user to generate simulated signals for testing purposes. [8A.5] THE SLEEP CONSULTANT CATEGORY: Tool for training and education. NATURE: Commercial AVAILABLE FROM [ftp addr, email addr, organisation, mail server]: Knowledge Industries 350 Cambridge Avenue, Suite 385 Palo Alto CA 94306 TELEPHONE: 415-321-0400 or CNS, Inc. 1250 Park Road Chanhassen, MN 55317-9260 TELEPHONE: 800-843-2978 PRICE (for non public domain systems): USD 495.00 LICENCING RESTRICTIONS : none HARDWARE PLATFORMS : 80286, 386, or 486 PCs SUPPORTING SOFTWARE REQUIREMENTS : INFORMATION SOURCE : Mike Shwe REFERENCES: OTHER COMMENTS (reviews, articles, etc): An interactive software tool for training and education in sleep-related disorders. Uses a large, causal probabilistic network to compute the posterior probabilities of over 100 disorders, given any combination of over 200 symptoms. Other features include recommendations for the next finding to pursue, extensive libraries of definitions for disorders and symptoms, and case archiving and retrieval. ************************************************************************** [8B]: Software for which minimal information is available. SUBSECTION DESCRIPTION: This section lists software available generally in public domain, about which detailed information is not available. Wherever available, filename, directory, ftp address, etc are included. The relevance of these programs to AIM has not been verified so expect to see changes in this section as more information is received. Contributions towards this are solicited from the readership. SUBSECTION INDEX [8B.1] 3-D DISPLAY/ROTATION OF MOLECULES [8B.2] ACID/BASE DIFFERENTIAL DIAGNOSIS [8B.3] ANTHROPOMETRIC ANALYSIS PACKAGE [8B.4] DECISION & LITERATURE ANALYSIS [8B.5] LONGEVITY (MEDICAL AGE) TEST [8B.6] SELECTION OF ANTIBIOTICS **************************************************************************** [8B.1] DESCRIPTION: 3-D DISPLAY/ROTATION OF MOLECULES LOCATION: university of texas medical school at houston INTERNET ADDRESS: DEAN.MED.UTH.TMC.EDU in MSDOS/3DCHEM.EXE ccsun.unicamp.br in pub/medicine/3dchem.zip MODE: Anonymous FTP OTHER INFORMATION: [see footnote #@-1] [8B.2] DESCRIPTION: ACID/BASE DIFFERENTIAL DIAGNOSIS LOCATION: UNIVERSITY OF TEXAS MEDICAL SCHOOL AT HOUSTON INTERNET ADDRESS: DEAN.MED.UTH.TMC.EDU in MSDOS/ACDBAS.EXE ccsun.unicamp.br in pub/medicine/acidbas.zip MODE: Anonymous FTP OTHER INFORMATION: [see footnote #@-1] [8B.3] DESCRIPTION: ANTHROPOMETRIC ANALYSIS PACKAGE LOCATION: UNIVERSITY OF TEXAS MEDICAL SCHOOL AT HOUSTON INTERNET ADDRESS: DEAN.MED.UTH.TMC.EDU 129.106.23.3 in MSDOS/ANTHROPO.EXE ccsun.unicamp.br in pub/medicine/anthropo.zip MODE: Anonymous FTP OTHER INFORMATION: [see footnote #@-1] [8B.4] DESCRIPTION: DECISION & LITERATURE ANALYSIS LOCATION: UNIVERSITY OF TEXAS MEDICAL SCHOOL AT HOUSTON INTERNET ADDRESS: DEAN.MED.UTH.TMC.EDU 129.106.23.3 in MSDOS/ANALIT.EXE ccsun.unicamp.br in pub/medicine/analyzer.zip MODE: Anonymous FTP OTHER INFORMATION: [see footnote #@-1] [8B.5] DESCRIPTION: LONGEVITY (MEDICAL AGE) TEST LOCATION: UNIVERSITY OF TEXAS MEDICAL SCHOOL AT HOUSTON INTERNET ADDRESS: DEAN.MED.UTH.TMC.EDU 129.106.23.3 in MSDOS/AGETST.EXE ccsun.unicamp.br in pub/medicine/agetest.zip MODE: Anonymous FTP OTHER INFORMATION: [see footnote #@-1] [8B.6] DESCRIPTION: SELECTION OF ANTIBIOTICS LOCATION: UNIVERSITY OF TEXAS MEDICAL SCHOOL AT HOUSTON INTERNET ADDRESS: DEAN.MED.UTH.TMC.EDU 129.106.23.3 in MSDOS/ANTIMICR.EXE ccsun.unicamp.br in pub/medicine/antimicr.zip MODE: Anonymous FTP OTHER INFORMATION: [see footnote #@-1] ************************************************************************ [9] SECTION: MISCELLANEOUS. Send submissions and corrections to Serdar Uckun: uckun@hpp.stanford.edu BibTeX style guide for AI in Medicine Journal. File name: aimj.bst BibTeX style guide for IEEE Transactions. File name: ieeetr.bst LaTeX style guide for SCAMC. File name: scamc.sty The above three style guides are available at the ai-medicine archives. To access the AI-Medicine archives: Connect via ftp to lhc.nlm.nih.gov (130.14.1.128). Login as 'ftp', use your username as password, cd to pub/ai-medicine. Use 'get filename' to copy files to your system. Alternatively, you can access the list archives via an e-mail server. For instructions, send a message to with a subject line of HELP and a blank message body.