Conceptual Structures for Medical Diagnosis [Rutgers-AIM] Section 9.4.6

I.D. List of Relevant Publications

(1) B. Chandrasekaran, F. Gomez, S. Mittal and J. Smith, "An approach to
medical diagnosis based on conceptual structures," Proc. International
Joint Conference on AI, Tokyo, Japan, Aug. 1979.

(2) S. Mittal, B. Chandrasekaran and J. Smith, "Overview of MDX - a medical
diagnosis system," Proc. III Annual Symposium on Computer Applications
in Medical Care, Washington, D.C., October 1979.

(3) B. Chandrasekaran, S. Mittal and J. Smith, "RADEX - towards a computer-
based radiology consultant," invited paper to appear in Pattern
Recognition in Practice, Gelsema and Kanal, eds, North Holland, 1980
(exp).

(4) F. Gomez and B Chandrasekaran, "Knowledge organization and distribution
for medical diagnosis," to appear in IEEE Trans SM&C.

(5) S. Mittal and B. Chandrasekaran, "Conceptual representation of patient
databases," to appear in J. of Medical Systems.

(6) S. Mittal and B. Chandrasekaran, "Temporal Organization of events in a
medical data base," to appear in Proc. Am. Conf. Cybernetics &
Society, Boston, 1980.

I.E. Funding Support

1. Graduate Student Support: Jack Smith, M.D., is supported by NIH/NLM
Biomedical Computer and Information Science Training Grant to the
Ohio State University, Grant no. LM07023-02, total direct costs for
the entire year of 79-80 is 87,959 (direct), but only a portion goes
to support AIM Training for graduate students. The renewal proposal
for this Training Grant has been approved by NLM, and we are
awaiting funding.

2. NLM Research Support. A research proposal on "Conceptual Structures
for Medical Knowledge Representation," B. Chandrasekaran, P.I.,
Application no. 1 RO1 LM03500-01, submitted to the NLM Computers in
Medicine Program has been approved by the Review Committee in its
March, 80 meeting. We are awaiting funding. The approved level of
funding is 80/81: 71,370, 81/82: 75,711 & 82/83: 80,111.

II. INTERACTIONS WITH THE SUMEX AIM RESOURCE
II.A. Medical Collaboration and program dissemination via SUMEX.

Most of our actual research is being conducted on the RUTGERS
resource. We are aware that some researchers at Rutgers and elsewhere have
Studied the program in detail and exercised it. The ideas behind the
program have thus been comprehended more concretely. In particular,
several researchers at RUTGERS and our group have sat down at extended
sessions in the TALK mode and have run our program, analyzed and critiqued
it. Such an effort would be impossible without these resources.

E. A. Feigenbaum 326 Privileged Communication
Section 9.4.6 Conceptual Structures for Medical Diagnosis [Rutgers-AIM]

II.B. Sharing and Interaction with other SUMEX~AIM Projects.

(1) Prof. Chandrasekaran participated in the Vermont NIH-AIM Workshop
last year. This participation has been a major intellectual boost
to our efforts.

(2) Prof. Chandrasekaran, Dr. Jack Smith and Sanjay Mittal will be
attending the forthcoming NIH-AIM Workshop at Stanford in August
1980. They will be presenting a demonstration of the MDX system at
the workshop.

(3) An important benefit of our use of the Rutgers LCSR system has been
the availability of software like the Rutgers Lisp system, screen
text editors, documentation preparation programs etc. Some of the
programming language features we need for research into building
experts-based systems will be provided in the new Lisp system under
development at Rutgers. Our limited resources would have made it
difficult to make such extensions to lisp.

(4) The mail facilities of SUMEX and RUTGERS resources are invaluable to
us in exchanging ideas, and keeping track of AIM activities. There
is simply no cost-effective substitute for the benefits of such
communication for our research.

(5) There is a sense of cohesiveness and common purpose fostered by this
resource. We have been able to make a number of professional
contacts through the resource and engage in intellectual dialogs
about problems of common interest in medical knowledge
representation.

{1.C. Critique of Resource Management.

The Rutgers facility which is our major computer is excellently
managed and provides us adequate service. Our impression of the Stanford
machine is similar, even though it is not based on as extensive a use.

The major weakness and source of anxiety for us is the unreliability
and slowness of the TYMNET nodes. The unreliability of TYMNET has often
created problems in continuous use of the SUMEX facilities. The very slow
speed (currently onty 300 baud) has been a major impediment in our research
effort from the point of view of acceptable turnaround time. Anyone who has
tried to use run editors like EMACS; run programs with lots of output; or
print out large files, at 300 baud, would agree that it is a maddeningly
slow process.

ITT. RESEARCH PLANS (8/80 - 7/86)
III.A. Project goals and plans.
A.i. Near-term (8/80 - 7/81)

(1) Expansion of the MDX system to larger domains of medicine, first to
the whole of cholestasis, then to the domain of all liver diseases.

Privileged Communication 327 E. A. Feigenbaum
Conceptual Structures for Medical Diagnosis [Rutgers-AIM] Section 9.4.6

(2) Creation of facilities to understand and organize the temporal
aspects of patient data and case histories.

(3) Implementation of MDX-II, embodying a more advanced problem-solving
strategy, which will result in a more coherent unified diagnosis.
This will be done for the domain of liver diseases.

A.ii. Long-term (8/81-7/86)

(1) Increasing the capabilities of MDX for consultation, including a)
explanation of diagnosis, and b) ordering tests.

(2) Evaluation of MDX as a tool in a clinical environment.

(3) Extension of the RADEX system to store and retrieve imaging
information over a much larger domain.

(4) Extension of conceptual patient data bases, and interpretive
reporting facilities.

(5) “Learning” of new diagnostic information by the system. We would
like to investigate how MDX can acquire new knowledge and skills,
either from episodic information, or productive problem solving
using underlying medical and commonsense knowledge structures.

(6) Use of MDX to evaluate the usefulness of particular symptoms,
manifestations and data in the diagnostic process. This can
currently be done only by a large expenditure of expert clinician
time.

TII.B. Justification and Requirements for Continued SUMEX Use.
I will talk more broadly of SUMEX/RUTGERS use.

a. Computing Facility: Our research will simply be crippled without
it. AIM work of the kind that we do requires very good LISP support anda
large machine. Our Department will shortly have a DEC20/20 which is
altogether too small for the kind of work that we need to get done.

Rutgers DEC20/50 has sufficient power for our immediate needs, even though
there are problems about disc space even there. Of course both SUMEX and
RUTGERS resources will probably need considerable enlargement if the number
of users and the sizes of the projects grows, as they almost surely will.

b, Training Facility: We not only need access to these resources for
research, but we need it for purposes of training graduate students in AIM
issues. for instance most of the graduate students in our AIM activity as
well as those associated with the NLM Biomedical Computing Training Grant
can now get hands on experience with other AIM programs through our access
to these resources. Thus as an educational tool in AIM, this resource is
an essential one for our Training activity also. It should be emphasized
that there are no viable alternatives to networking in this regard. AIM
programs are large, experimental and need substantial supporting resources.

E. A. Feigenbaum 328 Privileged Communication
Section 9.4.6 Conceptual Structures for Medical Diagnosis [Rutgers-AIM]

c. Community Building: We need to continue our interaction with the
centers of AIM activity, as well as individual researchers such as Ruven
Brooks at the University of Texas Medical Center (SUMEX-AIM user). We need
to feel part of this common AIM purpose, otherwise research groups like
ours which are very active but smal? would be rather isolated.

III.C. Needs and plans for other computing resources, beyond SUMEX-AIM

In the next five years, we anticipate a fairly substantial demand for
computing resources for our research projects. Our anticipated requirements
would be as follows:

1. Memory size - Within the next 2-3 years we would need a computer
System which can provide program memory size of the order of 2M bytes or
more, Untess DEC makes extensions to the Dec-10/Dec-20 architecture, we
would have to explore alternate systems, such as the VAX or IBM 370.

2. Computer usage - Our usage of the computer system at the Rutgers
LCSR has been steadily growing since we started using their system eight
months back. However, it is not clear how much more we would be able to
load their system in the next few years, without degrading the system
performance substantially. Our own department at Ohio State is currently
installing a new Dec 2020 system, which would help in providing additional
computer resource for our research, though only in a limited way. We would
be interested in exploring ways to upgrade this Dec2020 system with SUMEX
support,

3. Disk storage - Our experience of last year has shown that
development of knowledge-based systems in medicine require large amounts of
secondary disk storage, for keeping different versions of source codes,
compiled code, documentation etc. Currently we are using about 1500 pages
(1 page= 2.5K bytes) on the Rutgers system. We expect this to increase by
at least 100 percent in the next two years.

TIT.D. Recommendations for future community and resource development

Our experience in the past eight months as a member of the SUMEX
community has been quite rewarding, both in terms of availability of
computer and software resources, as well as contact with other researchers.

Our biggest source of frustration has been the slow communication
access to the SUMEX computing systems. The Tymnet node at Columbus provides
only a 300 baud line, which has proved to be a serious hindrance in our
effective use of the Rutgers system. We would be very interested in
exploring ways to upgrade this to at least 1200 baud, and if possible
higher. Any help from SUMEX, both technical and financial would be very
useful. We recommend that SUMEX explore ways to setup a nation wide network
access to SUMEX computing systems, which provide the following:

a. High speed access to the SUMEX computing nodes.

b. File transfer capability between the SUMEX facilities and the local
facilities of other members of the community.

Privileged Communication 329 E. A. Feigenbaum
Conceptual Structures for Medical Diagnosis [Rutgers-AIM] Section 9.4.6

The new technology in computer communications may enable the public
carriers to be used for fashioning such a network.

We feel that the dissemination of ideas and software among different
members of the AIM community may be enhanced by the introduction of a
quarterly SUMEX newsletter. Such a newsletter could be used to announce new
programs and utilities and provide a forum for discussion of work-in-
progress and other ideas not yet ready for formal publication.

E. A. Feigenbaum 330 Privileged Communication
Community Growth and Project Synopses Appendix A

Appendix A

Community Growth and Project Synopses

This appendix contains a graphical display of the development of the
SUMEX-AIM community over the years and brief synopses of currently active
projects. Figure 6 below illustrates the substantial growth in the
cumulative number of projects in the Stanford, national SUMEX, and Rutgers-
AIM communities since the resource began operation in 1974.

 

 

 

 

 

20 + Number of
Projects Rutgers Projects \
pn
aoe
15 4 ' ‘
é / ‘,
i é
é
, National Projects
= —__/
10 ff
mr
——_—__—_’ !
i -
! pe!
5 + ——
f_ Stanford Projects
a
Jan Jan Jan Jan Jan , Jan
1975 1976 1977 1978 1979 1980

Figure 6. SUMEX-AIM Growth by Community

Privileged Communication 331 E. A. Feigenbaum
Appendix A Community Growth and Project Synopses.

National AIM Project: ACQUISITION OF COGNITIVE PROCEDURES (ACT)

Principal Investigator: John R. Anderson, Ph.D.
Department of Psychology
Carnegie-Mellon University
Pittsburgh, Pennsylvania 16213
(412) 578-2788 (ANDERSONGSUMEX-AIM)

The ACT Project combines a semantic network data-base with a
production system to simulate human cognition. Prominent among the reasons
for using a production system architecture as a framework for developing
such a program is the possibility of modeling learning as the acquisition
of new productions. ACT possesses a number of learning mechanisms which
have been used to model the learning of procedural skills such as language
comprehension and geometry theorem proving. Some of these mechanisms have
the effect of either extending or restricting the set of circumstances in
which a particular behavior is performed so as to produce better
performance. Others have the effect of speeding up cognitive operations by
compressing the effects of a series of production applications into the
application of a single production. Out of this set of productions ACT
applies those that usually result in desirable outcomes. In this way it is
able to model the human ability to learn even when given unreliable
feedback. Another feature of ACT that reflects its psychological
orientation is its willingness to model human limitations. Here the hope
is that by being faithful to the human mind even in its failings, it
eventually may be possible to emulate its successes.

SOFTWARE AVAILABLE ON SUMEX

The ACT production system is available to GUEST users of SUMEX.

REFERENCES

Anderson, J.R.: Language, Memory, and Thought. Lawrence Erlbaum Associates,
Hillsdale, N.J., 1976.

Anderson, J.R., Kline, P.J. and Lewis, C.H.: A production system model of
language processing. IN M.A. Just and P.A. Carpenter (eds.), Cognitive
Processes in Comprehension. Lawrence Erlbaum Associates, Hillsdale,
N.J., 1977.

Anderson, J.R. and Kline, P.J.: A learning system and its psychological
implications. Proc. Sixth IJCAI, Tokyo, August, 1979.

E. A. Feigenbaum 332 Privileged Communication
Community Growth and Project Synopses Appendix A

National AIM Project: SIMULATION AND EVALUATION
OF CHEMICAL SYNTHESIS (SECS)

Principal Investigator: W. Todd Wipke, Ph.D.
Department of Chemistry
University of California at Santa Cruz
Santa Cruz, California 95064
(408) 429-2397 (WIPKE@SUMEX-AIM)

The SECS Project aims at developing practical computer programs to
assist investigators in designing syntheses of complex organic molecules of
biological interest. Key features of this research include the use of
computer graphics to allow chemist and computer to work efficiently as a
team, the development of knowledge bases of chemical reactions, and the
formation of plans to reduce the search for solutions. SECS is being used
by the pharmaceutical industry for designing syntheses of drugs.

A spin-off project, XENO, is aimed at predicting the plausible
metabolites of foreign compounds for carcinogenicity studies. First, the
metabolism is simulated; then the metabolites are evaluated for possible
carcinogenicity.

SOFTWARE AVAILABLE ON SUMEX

SECS~- Available with a reaction library of over 400 reactions. The user
needs a TTY or a DEC GT40 type graphics terminal.

XENO-- (for prediction of metabolites of xenobiotic compounds) is
available for preliminary exploration since the project is still in
the early development stages.

PRXBLD--(for building approximate molecular models from two-dimensional
molecular models) is an energy minimization approach which is
available both stand-alone and included within SECS.

REFERENCES

Spann, M.L., Chu, K.C., Wipke, W.T. and Ouchi, G.: Use of computerized
methods to predict metabolic pathways and metabolites. J. Env.
Pathology and Toxicology 2:123, 1978.

Wipke, W.T., Smith, G., Choplin, F. and Sieber, W.: SECS--Simulation and
Evaluation of Chemical Synthesis: Strategy and planning. IN Computer-
assisted Organic Synthesis Planning. ACS Symposium Series, 1977, pp.
97-127.

Wipke, W.T., Ouchi, G. and Krishnan, S.: Simulation and Evaluation of

Chemical Synthesis--SECS. An application of artificial intelligence
techniques. Artificial Intelligence 10:999, 1978.

Privileged Communication 333 £. A. Feigenbaum
Appendix A Community Growth and Project Synopses

Rutgers AIM Project: A CLINICAL DECISION-MAKING MODEL INCORPORATING
GOAL-SEEKING AND FOCUSING STRATEGIES

Principal Investigator: Robert A. Greenes, M.D.
Department of Radiology,
and Information Science
Peter Bent Brigham Hospital
Harvard Medical School
Boston, Massachusetts 02115
(617) 732-6281 (GREENES@RUTGERS)

Clinical decision-making in the model is viewed as a process which
involves: 1) formulation of a set of diagnostic hypotheses and estimation
of their likelihoods; 2) posing of patient management goals appropriate to
the diagnostic hypotheses; and 3) selection of tests to perform, based on
the relationship between the likelihoods of diagnosis and the certainty
levels, or threshold probabilities, required for adoption of corresponding
management goals. Focusing on particular diagnoses is accomplished by
requiring minimum certainty levels for consideration of the diagnostic
hypotheses. Probabilities are revised by Bayesian methods. The choice
among suitable tests involves a heuristic scoring process. The system is
being applied initially to the evaluation of upper abdominal pain.

SOFTWARE AVAILABLE ON SUMEX

Programs are in a developmental stage on the RUTGERS-AIM system and
not yet available for use.

REFERENCES

Greenes, R.A.: Investigations in clinical decision-making. NLM program
project grant application 1 P01 LM03401-01, 1979, pp. B27-31.

Greenes, R.A.: A goal-directed method for investigation of thresholds for

medical action. Proc. Third Annual Symposium Computer Applications in
Medical Care, Washington, 0.C., 1979, pp. 47-51.

E. A. Feigenbaum 334 Privileged Communication
Community Growth and Project Synopses Appendix A

National AIM Project: HIERARCHICAL MODELS OF HUMAN COGNITION

Principal Investigators: Walter Kintsch, Ph.D. (KINTSCH@SUMEX-AIM)
Peter G. Polson, Ph.D. (POLSON@SUMEX-AIM)
Computer Laboratory for Instruction
in Psychological Research (CLIPR)
Department of Psychology
University of Colorado
Boulder, Colorado 80302
(303) 492-6991

Contact: Dr. James Miller (JMILLER@SUMEX-AIM)

The CLIPR Project is concerned with the modeling of complex
psychological processes. It is comprised of two research groups. The
prose comprehension group has completed a project that carries out the
microstructure text analysis described by Miller and Kintsch (1980),
yielding predictions of the recall and readability of that text by human
subjects. More recently, this group has been interacting with the
Heuristic Programming Project at Stanford, using the AGE and UNITS packages
to build a more complex model of the knowledge-based processes
Characteristic of prose comprehension. The planning group is working
toward a model of the planning processes used by expert computer software
designers. The initial development of this model requires the detailed
analysis of expert software design protocols for subsequent simulation.

SOFTWARE AVAILABLE ON SUMEX

A set of programs has been developed to perform the microstructure
text analysis described in Kintsch and van Dijk (Psychological Review,
1978) and Miller and Kintsch (1980). The program accepts a
propositionalized text as input, and produces estimates of the text's
recall and readability.

REFERENCES

Atwood, M.E., Polson, P.G., Jeffries, R. and Ramsey, H.R.: Planning as a
process of synthesis. Technical Report SAI-78-144-DEN. Science
Applications, Inc., Denver, Colorado, December, 1978.

Kintsch, W.: On modeling comprehension. Educ. Psychologist, 14:3-14, 1979.

Miller, J.R. and Kintsch, W.: Readability and recall of short prose

passages: A theoretical analysis. J. Experimental Psychology: Human
Learning and Memory, 1980. (In press)

Privileged Communication 335 E. A. Feigenbaum
Appendix A Community Growth and Project Synopses

National AIM Project: HIGHER MENTAL FUNCTIONS (HMF)

Principal Investigator: Kenneth M. Colby, M.D.
Departments of Psychiatry
and Computer Science
Neuropsychiatric Institute
University of California at Los Angeles (UCLA)
Los Angeles, California 90024
(213) 825-4626 (COLBY@SUMEX-AIM)

Contact: William FAUGHT@SUMEX-AIM
Roger PARKISON@SUMEX-AIM

The HMF Project contributes new knowledge and instruments to the
fields of psychiatry and neurology using concepts and techniques of
artificial intelligence. The research includes a model of paranoid
behavior, a cognitive psychiatric taxonomy, and the development of
intelligent speech prostheses for nonspeaking patients.

SOFTWARE AVAILABLE ON SUMEX

PARRY--An interactive program which can be interviewed in unrestricted
natural language and responds linguistically the way paranoid
patients respond in an initial psychiatric interview.

REFERENCES

Colby, K.M.: Mind models: An overview of current work. Mathematical
Biosciences 39:159-185, 1978.

Colby, K.M., Christinaz, D. and Graham, S.: A computer-driven personal,

portable and intelligent speech prosthesis. Computers and Biomedical
Research 11:337-343, 1978.

Colby, K.M.: Computer simulation and artificial intelligence in psychiatry.
IN E.A. Serafetinedes (ed.), Methods of Biobehavioral Research. Grune
and Stratton, New York, 1979.

E. A. Feigenbaum 336 Privileged Communication
Community Growth and Project Synopses Appendix A

National AIM Project: INTERNIST

Principal Investigators: Jack D. Myers, M.D. (MYERS@SUMEX-AIM)
Harry E. Pople, Ph.D. (POPLE@SUMEX-AIM)
University of Pittsburgh
Pittsburgh, Pennsylvania 15261
Dr. Pople: (412) 624-3490

The major goal of the INTERNIST Project is to produce a reliable and
adequately complete diagnostic consultative program in the field of
internal medicine. Although this program is intended primarily to aid
skilled internists in complicated medical problems, the program may have
spin-off as a diagnostic and triage aid to physicians' assistants, rural
health clinics, military medicine and space travel. In the design of
INTERNIST we have attempted to model the creative, problem-formulation
aspect of the clinical reasoning process. The program employs a novel
heuristic procedure that composes differential diagnoses, dynamically, on
the basis of clinical evidence. During the course of an INTERNIST
consultation, it is not uncommon for a number of such conjectured problem
foci to be proposed and investigated, with occasional major shifts taking
place in the program's conceptualization of the task at hand.

SOFTWARE AVAILABLE ON SUMEX

Versions of INTERNIST are available for experimental use, but the
project continues to be oriented primarily towards research and
development; hence, a stable production version of the system is not yet
available for general use.

REFERENCES

Pople, H.E., Myers, J.D. and Miller, R.A.: The DIALOG model of diagnostic
logic and its use in internal medicine. Proc. Fourth IJCAI, Tbilisi,
USSR, September, 1975.

Pople, H.E.: The formation of composite hypotheses in diagnostic problem
solving: An exercise in synthetic reasoning. Proc. Fifth IJCAI,
Boston, August, 1977.

Privileged Communication 337 E. A. Feigenbaum
Appendix A Community Growth and Project Synopses.

National AIM Project: BIOMEDICAL KNOWLEDGE ENGINEERING
IN CLINICAL MEDICINE (PUFF/VM)

Principal Investigators: John J. Osborn, M.D.
The Institutes of Medical Sciences
Pacific Medical Center
San Francisco, California 94115
(415) 567-0900 (OSBORNGSUMEX-AIM)

Edward A. Feigenbaum, Ph.D.
Department of Computer Science
Stanford University

The PUFF/VM Project has produced two knowledge-based programs for the
interpretation of physiologic measurements made in clinical medicine. The
interpretations are intended to aid in diagnostic decision-making and in
selecting therapeutic actions. The programs are: PUFF--the evaluation of
pulmonary function laboratory data, and VM--the evaluation and management
of respiratory status for patients in the intensive care unit.

The task of the PUFF PROGRAM is to interpret standard measures of
pulmonary function. In the laboratory at the Pacific Medical Center (PMC),
about 50 parameters are calculated from measurement of lung volumes, flow
rates, and diffusion capacity. In addition to these measurements, patient
history and referral diagnosis also are used to interpret the test results.
PUFF produces a report for the patient record, explaining the clinical
significance of measured test results. It also provides a diagnosis of the
presence and severity of pulmonary disease. The interpretation process is
accomplished by examination of expert knowledge represented by a set of
production rules. Each rule relates physiologic measurements or states to
a conclusion about the physiologic significance of the measurement or
state. A version of the PUFF program is used daily at the PMC,

The VENTILATOR MANAGER (VM) PROGRAM is designed to interpret on-line
physiologic data in the intensive care unit (ICU). These data are used to
manage post-surgical patients receiving mechanical assistance in breathing.
VM ts an extension of a physiologic monitoring system, and is designed to
perform 5 specialized tasks in the ICU: 1) to detect possible measurement
errors; 2) to recognize untoward events in the patient/machine system and
suggest corrective action; 3) to summarize the patient’s physiologic
Status; 4) to suggest adjustments to therapy based on the patient's status
over time, and long-term therapeutic goals; and 5) to maintain a set of
patient-specific expectations and goals for future evaluation by the
program. The program produces interpretations of the physiologic
measurements over time, using a model of the therapeutic procedures in the
ICU and clinical knowledge about the diagnostic implications of the data.

SOFTWARE AVAILABLE ON SUMEX

The PUFF and VM programs will be available to GUEST users for use on
pre-existing (non-identifiable) cases. No packages currently exist for
program development.

E. A. Feigenbaum 338 Privileged Communication
Community Growth and Project Synopses Appendix A

REFERENCES

Fagan, L.M., Kunz, J.C., Feigenbaum, E.A. and Osborn, J.J.: A symbolic
processing approach to measurement interpretation in the intensive
care unit. Proc. Third Annual Symposium Computer Applications in
Medical Care, Silver Spring, Maryland, October, 1979, pp. 30-33.

Fagan, L.M., Shortliffe, E.H. and Buchanan, B.G.: Computer-based medical
decision making: From MYCIN to VM. Automedica 3(2), 1980.

Kunz, J.C., Fallat, R.J., McClung, D.H., et al: A physiological rule based
system for interpreting pulmonary function test results. Heuristic
Programming Project Report HPP-78-164, Computer Science Dept.,
Stanford Univ., November, 1978.

Osborn, J.J., Fagan, L.M., Fallat, R.J., et al: Managing the data from

respiratory measurements. Med. Instrumentation, November-December,
1979,

Privileged Communication 339 E. A. Feigenbaum
Appendix A Community Growth and Project Synopses

Rutgers AIM Project: RUTGERS RESEARCH RESOURCE -
COMPUTERS IN BIOMEDICINE

Principal Investigator: Saul Amarel, Ph.D.
Department of Computer Science
Rutgers University
New Brunswick, New Jersey 08903
(201) 932-3546 (AMAREL@RUTGERS)

The broad objective of the Resource is to apply advanced methods in
computer science, particularly in artificial intelligence (AI), to
biomedical problems. The Resource has three major areas of study: 1)
Medical Modeling and Decision Making in several medical domains with
emphasis on collaborative development of consultation systems in
rheumatology and ophthalmology; 2) Modeling of Belief Systems and
Commonsense Reasoning with emphasis on the psychology of plan recognition
and handling of stereotypes; and 3) Artificial Intelligence studies with
emphasis on Representations, Interpretation processes, and problems of
knowledge and expertise acquisition. The studies in Medical Modeling and
Decision Making are performed jointly by computer and medical scientists at
Rutgers and elsewhere in the Country and abroad.

The Resource also sponsors national Artificial Intelligence in
Medicine (AIM) Workshops for the AIM community.

SOFTWARE AVAILABLE ON SUMEX
CASNET--System for consultation in the diagnosis and treatment of glaucoma.

EXPERT--System for designing and applying consultation models using a
relatively simple language to describe the models.

REFERENCES

Amarel, S.: Computer-based interpretation and modeling in medicine and
psychology: The Rutgers Research Resource. IN Siler and Lindberg
(eds.), Computers in Life Science Research. Foseb and Planum, 1975,

Schmidt, C.F., Sridharan, N.S., and Goodson, J.L.: The plan recognition
problem: An intersection of psychology and artificial intelligence.
AI Journal 11(1,2), August, 1978 (special issue on applications to the
sciences and medicine).

Weiss, S., Kulikowski, C.A., Amarel, S$. and Safir, A.: A model-based method
for computer-aided medical decision-making. AI Journal 11(1,2),
August, 1978 (special issue on applications to the sciences and
medicine).

E. A. Feigenbaum 340 Privileged Communication
Community Growth and Project Synopses Appendix A

National AIM Project: SIMULATION OF COGNITIVE PROCESSES (SCP)

Principal Investigators: James G. Greeno, Ph.D. (GREENO@SUMEX-AIM)
Alan M. Lesgold, Ph.D. (LESGOLD@SUMEX-AIM)
Learning Research and Development Center
University of Pittsburgh
Pittsburgh, Pennsylvania 15260
Dr. Lesgoltd: (412) 624-4901

The general purpose of the SCP Project is to develop increased
understanding of normal and deficient cognitive functions, especially in
reading and mathematics. Earlier work included simulations of interactive
processes of grapheme-phoneme decoding and word recognition, and of
semantic processes in comprehension of quantitative information in
arithmetic word problems. The main emphasis at this time is on a
collaboration with John Anderson, using the ACTF system to explore
mechanisms of learning in the domain of geometry proofs. The SCP part of
this work includes development of a system that learns by reading example
proofs. The goal is to identify conceptual structures that are required
for a learner to acquire planning strategies.

SOFTWARE AVAILABLE ON SUMEX

Programs are in a developmental stage and not yet available for use.

REFERENCES

Greeno, J.G., Magone, M.E. and Chaiklin, S.: Theory of constructions and
set in problem solving. IN Memory and Cognition (In press). (Also
available as Technical Report 1979/9, Learning Research and
Development Center, Univ. Pittsburgh.)

Greeno, J.G.: Preliminary steps toward a cognitive model of learning
primary mathematics. IN K. Fuson and W. Geeslin (eds.), Models of
Children's Mathematical Learning, ERIC Information Center. (In press)

Lesgotd, A.M. and Curtis, M.E.: Learning to read words efficiently. IN A.

Lesgold and C. Perfetti (eds.), Interactive Processes in Reading,
Eribaum, Hillsdale, N.J. (In progress)

Privileged Communication 341 E. A. Feigenbaum
Appendix A Community Growth and Project Synopses

Stanford Project: GENERALIZATION OF AI TOOLS (AGE)

Principal Investigators: H. Penny Nii (NII@SUMEX-AIM)
Edward A. Feigenbaum, Ph.D.
Department of Computer Science
Stanford University
Stanford, California 94305
H.P. Nii: (415) 497-2739

The long-range objective of AGE, a SUMEX CORE RESEARCH Project, is to
build a software laboratory for building knowledge-based, application
programs. It is an attempt to define and accumulate knowledge-engineering
tools, wftth rules to guide in the use of these tools. The design and
implementation of the AGE program wil] be based primarily on the
experiences gained in building knowledge-based programs by the Stanford
Heuristic Programming Project in the last decade (The programs that have
been or are being built are: DENDRAL, META-DENDRAL, MYCIN, HASP, AM,
MOLGEN, GUIDON, CRYSALIS, PUFF, VM and SACON.). The initial AGE program
contains a collection of tools suitable for constructing user programs
based on the Blackboard paradigm {used in HASP and CRYSALIS). In addition,
AGE has facilities to aid the user in the construction, debugging, and
running of his program.

SOFTWARE AVAILABLE ON SUMEX

AGE-1 is available on an experimental basis to a limited number of users.
A public version of the programs, together with reference manuals and
user guides, is planned for July, 1980.

REFERENCES

Nii, H.P. and Feigenbaum, E.A.: Rule-based understanding of signals. IN
D.A. Waterman and F. Hayes-Roth (eds.), Pattern-directed Inference
Systems. Academic Press, 1978, pp. 483-501.

Nii, H.P. and Aiello, N.: AGE: A knowledge-based program for building
knowledge-based programs. Proc. Sixth IJCAI, Tokyo, August, 1979, pp.
645-655.

E. A. Feigenbaum 342 Privileged Communication
Community Growth and Project Synopses Appendix A

Stanford Project: HANDBOOK OF ARTIFICIAL INTELLIGENCE

Principal Investigator: Edward A. Feigenbaum, Ph.D.
Avron Barr, Research Associate (BARR@SUMEX-AIM)
Department of Computer Science
Stanford University
Stanford, California 94305

The AI Handbook Project is a part of SUMEX CORE RESEARCH aimed at
making the important results of AI research accessible to the large, multi-
disciplinary community of scientists who want to build AI systems in their
own problem areas. Students and researchers at Stanford and other AI
laboratories have prepared over 300 short articles describing the
fundamental ideas, useful techniques, and exemplary programs developed in
the field over the last 20 years. These articles have been written for
computer-literate scientists and engineers in other fields who are
unfamiliar with AI research and jargon. The Handbook will provide a
scientist who, for instance, might want to know what a "heuristic" is or
how to build a "natural language” front end, with information about all of
the relevant AI techniques and existing systems, as well as abundant
pointers into the field's literature.

The Handbook is being published in report and book form. It also
will be made available to the SUMEX community via an on-line information
retrieval system. Following is a TOPIC OUTLINE for Volumes I and IT:
HANDBOOK OF ARTIFICIAL INTELLIGENCE

INTRODUCTION: The Handbook of Artificial Intelligence; Overview of AI
Research; History of AI; An Introduction to the AI Literature

SEARCH: Overview; Problem Representation; Search Methods for State
Spaces, AND/OR Graphs, and Game Trees; Six Important Search
Programs

REPRESENTATION OF KNOWLEDGE: Issues and Problems in Representation
Theory; Survey of Representation Techniques; Seven Important
Representation Schemes;

Al PROGRAMMING LANGUAGES: Historical Overview of AI Programming

Languages; Comparison of Data Structures and Control Mechanisms
in AI Languages; LISP

NATURAL LANGUAGE UNDERSTANDING: Overview - History and Issues:
Grammars; Parsing Techniques; Text Generation Systems; Machine

Translation; The Early NL Systems; Six Important Natural Language
Processing Systems

SPEECH UNDERSTANDING SYSTEMS: Overview - History and Design Issues;
Seven Major Speech Understanding Projects

Privileged Communication 343 E. A. Feigenbaum
Appendix A Community Growth and Project Synopses

APPLICATIONS-ORIENTED AI RESEARCH--SCIENCE AND MATHEMATICS: Overview;
TEIRESIAS - Issues in Expert Systems Design; Research on AI
Applications in Mathematics (MACSYMA and AM); Research on AI
Applications in Chemistry (DENDRAL, CRYSALIS, etc.); Other
Scientific Applications Research

APPLICATIONS-ORIENTED AI RESEARCH--MEDICINE: Overview of Medical
Applications Research; Six Important Medical Systems

APPLICATIONS-ORIENTED AI RESEARCH--EDUCATION: Historical Overview of
AI Research in Educational Applications; Issues and Components of
Intelligent CAI Systems; Seven Important ICAI Systems

AUTOMATIC PROGRAMMING: Overview; Techniques for Program Specification;
Approaches to AP; Eight Important AP Systems

The following sections of the Handbook are still in preparation and
will appear in Volume III: Theorem Proving; Vision; Robotics; Information
Processing Psychology; Learning and Inductive Inference; Planning and
Related Problem-solving Techniques.

E. A. Feigenbaum 344 Privileged Communication
Community Growth and Project Synopses Appendix A

Stanford Project: DENDRAL--RESOURCE RELATED RESEARCH -
COMPUTERS IN CHEMISTRY

Principal Investigator: Carl Djerassi, Ph.D.
Department of Chemistry
Stanford University
Stanford, California 94305

Contact: Dr. Dennis SMITH@SUMEX-AIM
(415) 497-3144

The DENDRAL Project involves research in computer-assisted structure
elucidation of unknown organic compounds of biological importance. This
research has three major components: 1) program development; 2) biochemical
applications; and 3) resource-sharing.

Recent program developments have been directed toward building more
powerful interactive programs to assist chemists in the three major areas
of structure elucidation: analysis of data to yield substructural
information about an unknown ("planning"), advanced methods for assembly of
Substructures into complete structures ("structure generation"), and the
prediction of data for structural candidates to rank-order the candidates
by comparison of predicted and observed data ("testing"). Important
problems of structure representation have been solved which have enabled
dealing with stereochemical (three-dimensional) aspects of structure
throughout the procedures.

Major areas of application of the programs in the research of this
group and other collaborative projects include: a) marine natural products,
particularly marine steroids and halogenated compounds which display
biological activity; b) antibiotics and other derivatives of known or
potential drugs; c) terpene alkaloids; d) photoproducts related to vitamin
A; and e) conformational studies of narcotic analogs and polypeptides.

These programs are shared among a community of collaborators and
guest users at SUMEX, with communication via computer network from a
variety of sites in the U.S., Europe and Australia. Exportable versions of
some programs are maintained. These versions have been installed
successfully in more than 10 research laboratories throughout the world.

SOFTWARE AVAILABLE ON SUMEX

CONGEN--An interactive program for structure generation to yield candidate
structures for an unknown based on inferred substructural components
(exportable).

GENOA~-An advanced structure generator capable of handling overlapping
substructural information; uses CONGEN as a core component
(exportable).

Meta-DENDRAL--An INTSUM, RULEGEN and RULEMOD sequence for automatic rule

formation to relate observed data to substructures in mass
Spectrometry and carbon magnetic resonance spectroscopy.

Privileged Communication 345 E. A. Feigenbaum
Appendix A Community Growth and Project Synopses

REACT--A program for carrying out a complex sequence of chemical reactions
and exploration of the consequences of those reactions.

NMR--For substructural inference and spectrum prediction in carbon magnetic
resonance spectroscopy (will be exportable).

REFERENCES

Carhart, R.E., Varkony, T.H. and Smith, D.H.: Computer assistance for the
structural chemist, IN D.H. Smith (ed.), Computer-Assisted Structure

Elucidation. American Chemical Society, Washington, D.C., 1977, p.
126.

Djerassi, C., Smith, D.H. and Varkony, T.: A novel role of computers in the
natural products field. Naturwiss. 66:9, 1979.

Nourse, J.G., Carhart, R.E., Smith, D.H. and Djerassi, C.: Exhaustive

generation of stereoisomers for structure elucidation. J. Am. Chem.
Soc. 101:1216, 1979.

E. A. Feigenbaum 346 Privileged Communication
Community Growth and Project Synopses Appendix A

Stanford Project: MOLGEN--AN EXPERIMENT PLANNING SYSTEM
FOR MOLECULAR GENETICS

Principal Investigators: Edward A. Feigenbaum, Ph.D.
Department of Computer Science
Stanford University

Laurence H. Kedes, M.D. (KEDES@SUMEX-AIM)
Department of Medicine

Stanford University

Stanford, California 94305

(415) 497-5897

Contact: Or. Peter FRIEDLAND@SUMEX-AIM
(415) 497-1740

The goal of the MOLGEN Project is to apply the techniques of
artificial intelligence to the domain of molecular biology with the aim of
providing assistance to the experimental scientist. The most substantial
problem under consideration is the task of experiment design. Two major
approaches to this problem have been explored, one which instantiates
abstracted experimental strategies with specific laboratory tools, and one
which creates plans in toto, heavily influenced by the role played by
interactions between plan steps. As part of the effort to build an
experiment design system, a knowledge representation and acquisition
package--the UNITS System, has been constructed. A large knowledge base,
containing information about nucleic acid structures, laboratory
techniques, and experiment-design strategies, has been developed using this
tool. Smaller systems, such as programs which analyze primary sequence
data for homologies and symmetries, have been built when needed.

SOFTWARE AVAILABLE ON SUMEX
Knowledge-based Experiment Design system (Friedland).
Meta-planning with Constraints experiment design system (Stefik).
UNITS system for knowledge representation and acquisition.
Interactive KORN Program for DNA sequence analysis.
GA1 program for restriction map construction.

SAFE program for gene excision.

REFERENCES

Friedland, P.E.: Knowledge-based experiment design in molecular genetics

(Ph.D. thesis). Computer Science Dept. Report, CS-79-771, Stanford
Univ.

Privileged Communication 347 E. A. Feigenbaum
Appendix A Community Growth and Project Synopses

Friedland, P.E.: Knowledge-based experiment design in molecular genetics.
Proc. Sixth IJCAI, Tokyo, August, 1979, pp. 285-287.

Stefik, M.J.: An examination of a frame-structured representation system.
Proc. Sixth IJCAI, Tokyo, August, 1979, pp. 845-852.

Stefik, M.J.: Planning with constraints (Ph.D. thesis). Computer Science
Dept. Report, Stanford Univ. (In progress)

E. A. Feigenbaum 348 Privileged Communication
Community Growth and Project Synopses Appendix A

Stanford Project: MYCIN~-KNOWLEDGE ENGINEERING
FOR MEDICAL CONSULTATION

Principal Investigators: Bruce G. Buchanan, Ph.D.
Department of Computer Science
Stanford University
Stanford, California 94305
(415) 497-0935 (BUCHANAN@SUMEX-AIM)

Edward H. Shortliffe, M.D., Ph.D.
Departments of Medicine,

and Computer Science (by courtesy)
Stanford University

Stanford, California 94305

(415) 497-5821 (SHORTLIFFE@SUMEX-AIM)

Subproject Directors: MYCIN: Dr. Shortliffe, and A. Carlisle Scott
EMYCIN: Dr. Buchanan, and William van Melle
GUIDON: Drs. Buchanan, and William J. Clancey
ONCOCIN: Dr. Shortliffe, and A. Carlisle Scott

The MYCIN Project is a collaborative group of physicians and computer
scientists who are developing intelligent systems using the techniques of
knowledge engineering. The research focus includes knowledge acquisition,
inexact reasoning, explanation, education, and the representation of time
and of expert thinking patterns. Project members currently are working in
a variety of medical domains including infectious disease therapy
selection, intelligent computer-aided instruction, and the management of
cancer chemotherapy protocols. Recent emphasis in the research has
included intensive work regarding human engineering, in an effort to
implement the cancer therapy system for physicians to use in the near
future. There is also a heightened interest in gearing representation,
knowledge acquisition, and explanation more to the way that an expert
actually thinks.

SOFTWARE AVAILABLE ON SUMEX

MYCIN--A consultation system designed to assist physicians with the
selection of antimicrobial therapy for severe infections. It has
achieved expert level performance in formal evaluations of its ability
to select therapy for bacteremia and meningitis. The program
continues to provide a powerful research environment for developing
new approaches to the basic questions involved in knowledge
engineering.

EMYCIN--The "essential MYCIN” system is a generalization of the MYCIN
knowledge representation and control structure. It is designed to
facilitate the development of new expert consultation systems for both
clinical and non-medical domains.

GUIDON--A system developed for intelligent computer-aided instruction.
Although it is being developed in the context of MYCIN's infectious

Privileged Communication 349 E. A. Feigenbaum
Appendix A Community Growth and Project Synopses

disease knowledge base, the techniques are generalizable to any EMYCIN
domain. The current research emphasis has been on an improved
understanding of how the expert thinks so as to optimize the learning
experience for the student.

ONCOCIN--This newest subproject is a system designed to assist oncologists
with the management of cancer chemotherapy protocols. Because the
knowledge in this domain is already well-specified, the research
emphasis is on human engineering and achieving clinical acceptance of
the program.

REFERENCES

Clancey, W.J., Shortliffe, E.H. and Buchanan, B.G.: Intelligent computer-
aided instruction for medical diagnosis. Proc. Third Conference
Computer Applications in Medical Care, Silver Spring, Maryland,
October, 1979, pp. 175-183.

Shortliffe, E.H., Buchanan, B.G. and Feigenbaum, E.A.: Knowledge
engineering for medical decision making: A review of computer-based
clinical decision aids. Proc. IEEE 67:1207-1224, 1979.

van Melle, W.: A domain-independent production rule system for consultation
programs. Proc. Sixth IJCAI, Tokyo, August, 1979, pp. 923-925.

Yu, V.L., Fagan, L.M., Wraith, S.M., et al: Antimicrobial selection by a

computer - A blinded evaluation by infectious disease experts. JAMA
242:1279-1282, 1979.

E. A. Feigenbaum 350 Privileged Communication