🚀 go-pugleaf

CORRECTED DATE: MONDAY, December 5
**********************************************************************
*                                                                    *
*                                                                    *
*                                                                    *
*                 CASE-BASED REASONING IN MEDICINE                   *
*                                                                    *
*                                                                    *
*                                                                    *
*                      KEVIN D. ASHLEY, PhD.                         *
*                                                                    *
*                   Associate Professor of Law                       *
*     Co-Director of the Graduate Program in Intelligent Systems     *
* Research Scientist at the Learning Research and Development Center *
*                    University of Pittsburgh                        *
*                                                                    *
*                     ashley+@pitt.edu                               *
*                                                                    *
*                                                                    *
*    A CBR Knowledge Representation for a Practical Ethics Domain:   *
*               Toward Modeling Medical Ethical Reasoning            *
*                                                                    *
*                       2:30 PM, Monday, December 5                  *
*                          276 Ryerson Hall                          *
*                         1100 E. 58th Street                        *
*                          Chicago, Illinois                         *
*                                                                    *
*                                                                    *
**********************************************************************


                            Abstract

TRUTH-TELLER, a program for testing a Case-Based Reasoning (CBR)
knowledge representation in practical ethics, compares cases
presenting ethical dilemmas about whether to tell the truth. Its
comparisons list ethically relevant similarities and differences
(i.e., reasons for telling or not telling the truth which apply to
both cases, and reasons which apply more strongly in one case than
another or which apply only to one case).  The program reasons about
reasons in generating context-sensitive comparisons.  The reasons may
invoke ethical principles or selfish considerations.

In this talk, we describe a knowledge representation for this
practical ethical domain including representations for reasons and
principles, truth telling episodes, contextually important scenarios,
and comparison rules.  In a preliminary evaluation, a professional
ethicist scored the program's output for randomly-selected pairs of
cases.

The preliminary evaluation shows that we have developed an AI CBR
knowledge representation which can very nearly simulate intelligent
comparisons of practical ethical problems, at least for 23 cases in
the field of truth telling. We anticipate a final case base of between
50 and 75 cases in this domain. We plan to use this knowledge
representation for a cognitive science investigation of the
differences between novice and experienced reasoning about ethical
dilemmas. We are collecting and analyzing protocols of high school and
medical ethics graduate students' arguments about the same cases as in
TRUTH-TELLER's database. We hope to use our knowledge representation
to duplicate and explain some of the observed differences in novice
and experienced reasoning and to model some of the arguers' specific
differences of opinion. We also hope to model arguments that a
proposed resolution is inconsistent with an arguer's previous
arguments about similar cases. This investigation will lead, we hope,
to a realistic model of ethical decision-making or, at least, of
reasonable ethical case-based argumentation upon which to base a
tutoring system to improve novices' abilities to recognize and analyze
practical ethical dilemmas.

The work contributes to AI CBR efforts to integrate general principles
and context-sensitive information in symbolically assessing case
similarity and to model comparing problems to paradigmatic cases. It
also furthers research on cognitive and philosophical models of
ethical judgement and decision-making. While the program does not
currently deal with a medical ethical domain, it was developed in the
light of recent discussions of casuistic models of ethical decision
making in the medical ethical literature and suggests some preliminary
approaches to tackling medical ethical domains.


Background reading: (not currently available)
 

This talk is part of a series focused on the use of case-based
reasoning in medicine. For a schedule of the autumn portion of the
series:

Email:
To: listproc@cs.uchicago.edu
Subject: <blank line>
get cbr-med speakers-aut94
--

Or, see the Web page:
http://cs-www.uchicago.edu/~berger/speakers.html

---------------------------------------------------------------------
For more information: Jeff Berger <berger@cs.uchicago.edu>
--
--
Jeff Berger			       |USmail:	Ryerson 256
berger@cs.uchicago.edu	               |	Artificial Intelligence Lab
PH: (312) 702-8584		       |	1100 East 58th Street
FX: (312) 702-8487                     |        University of Chicago
WWW http://cs-www.uchicago.edu/~berger |        Chicago, IL  60637