AIMDM'99 -- Call for Participation
Workshop: Prognostic Models in Medicine --
Artificial Intelligence and Decision Analytic Approaches
during the
Joint European Conference on Artificial Intelligence
in Medicine and Medical Decision Making (AIMDM'99)
in Aalborg, Denmark, 20th - 24th June 1999
(WWW version of this CFP: http://www.cs.uu.nl/~lucas/ipm-aimdm99.html)
Important dates
- Submission of final papers: 29 May 1999
- Conference: 20th - 24th June 1999
- Workshop: Sunday, 20th June 1999
-
Invitation for authors of best papers to submit an extended version of
the paper to the special issue of the international journal Methods
of Information in Medicine: June 1999
Scope
Prognostic models are increasingly used in medicine to predict the natural
course of disease, or the expected outcome after treatment. Prognosis forms
an integral part of systems for treatment selection and treatment planning.
In evaluating quality of care, prognostic models are used for predicting
outcome, such as mortality, which is compared with the actual measured
outcome. Furthermore, prognostic models may play an important role in guiding
diagnostic problem solving, e.g. by only requesting information concerning
tests, of which the outcome affects knowledge of the prognosis. (See the
following introductory paper on prognosis, which
was presented during CESA'98.)
In recent years several methods and techniques from the fields of artificial
intelligence, decision theory and statistics have been introduced into
models of the medical management of patients (diagnosis, treatment, follow-up);
in some of these models, assessment of the expected prognosis constitutes
an integral part. Typically, recent prognostic methods rely on explicit
(patho)physiological models, which may be combined with traditional models
of life expectancy. Examples of such domain models are causal disease models,
and physiological models of regulatory mechanisms in the human body. Such
model-based approaches have the potential to facilitate the development
of actual systems, because the medical domain models can be (partially)
obtained from the medical literature.
Various methods have been suggested for the representations of such
domain models ranging from quantitative and probabilistic approaches to
symbolic and qualitative ones. Semantic concepts such as time, e.g. for
modelling the progressive changes of regulatory mechanisms, have formed
an important and challenging modelling issue. Moreover, automatic learning
techniques of such models have been proposed. When model construction is
hard, less explicit domain models have been studied such as the use of
case-based and neural network representations and their combination with
more explicit domain models. In medical decision analysis, where the theories
of probability and utility are combined, various representations and techniques
are suggested such as decision trees, regression models, and representations
in which advantage is taken from the Markov assumption (such as in Markov
decision problems).
This workshop aims at bringing together various theoretical and practical
approaches to computational prognosis that comprise the state of the art
in this field. This workshop is a follow up on the initiative started with
the successful invited session on "Intelligent
Prognostic Methods in Medical Diagnosis and Treatment Planning" in
1998 during the conference "Computational Engineering in Systems Applications
1998" (CESA'98) which has resulted in a special issue on prognosis of the
journal Artificial Intelligence in Medicine.
Papers are sought that describe medical prognosis applications using
methods and techniques from artificial intelligence, decision theory, and
statistics as well as papers proposing theoretical foundations of such
methods. The workshop will also include one or more invited talks (details
will appear in due time on the corresponding WWW-page of this workshop
and the AIMDM'99 pages).
Topics of interest
-
Modelling and Reasoning:
-
the specification of prognostic models, possibly as part of diagnostic
or therapy-planning applications
-
representation and reasoning about (multiple) model types such as empirical,
anatomical and (patho)physiological ones
-
representation of and reasoning with time
-
qualitative representation and reasoning
-
decision modelling and analysis
-
(dynamic) probabilistic networks
-
function-based representation and reasoning
-
case-based representation and reasoning
-
Knowledge Acquisition:
-
acquisition of the medical prognostic models
-
automated learning of domain or task models using machine learning and
data-mining techniques
-
Formalisation:
-
use of logical, set-theoretical or probabilistic methods to formalise various
aspects of prognosis and therapy planning
-
Medical Applications:
-
clinical context of actual prognostic models
-
role of prognostic models in diagnosis or treatment planning of a specific
disease
-
evaluation of prognostic models
Submissions have been refereed by at least two members of the programme
committee. Accepted papers will appear in the working notes of the workshop
"Prognostic Models in Medicine: Artificial Intelligence and Decision Analytic
Approaches". Authors of the best papers are invited to contribute to a
special issue on prognostic models in medicine of the international journal
Methods
of Information in Medicine.
Instructions to authors
The final versions of the papers (up to 5 pages) are to be sent as a Postscript
file by e-mail before 29 May 1999 to both co-chairs and should
be written in English with a brief abstract. Formatting instructions are
as follows: the abstract should be formatted in two-column format, with
Times Roman type face, pointsize 10, with title and names of the authors
in bold font. Left and right margins should be 2 cm, text height 23 cm,
and text width 16.9 cm; the two columns should be separated by 0.5 cm white
space. A sample paper is available: Sample paper.
Preferably the papers are produced using either LaTeX or MS-Word; there
is a style file available for each of these text processing systems:
\documenclass[two-columns]{article}
\usepackage{aimdm-ws}
The MS-Word style
file needs to be slightly changed according to the specifications given
above.
Registration fee
Workshop only 750 DKK, for participants of AIMDM'99: 500 DKK. The fee includes
light refreshments and lunch.
Preliminary programme
Morning session
Chair: Ameen Abu-Hanna
- 09.00 - 09.15 Coffee
- 09.15 - 09.30 Ameen Abu-Hanna and Peter Lucas: Introduction
- 09.30 - 10.15 J. Wyatt: invited talk - prognostic models in medicine
- 10.15 - 10.45 J.D.F. Habbema: Building prognostic models - statistical
aspects
- 10.45 - 11.15 S.S. Anand, P.W. Hamilton, J.G. Hughes and D.A. Bell:
Utilising censored neighbours in prognostication.
- 11.15 - 11.35 Coffee break
- 11.35 - 11.55 I. Zelic, N. Lavrac, P. Najdenov, Z. Rener-Primec:
Impact of machine learning to the diagnosis and prognosis of
first cerebral paroxysm.
- 11.55 - 12.25 R. Schmidt, B. Pollwein and L. Gierl: Prognoses for
multiparametric time course of the kidney function.
12.25 - 14.00 Lunch
Afternoon session
Chair: Peter Lucas
- 14.00 - 14.45 K.G. Olesen: invited talk - medical models and Bayesian networks
- 14.45 - 15.15 H. Dreau, I. Colombet, P. Degoulet, G. Chatellieri:
Identification of patients at high cardiovascular risk using
a critical appraisal of statistical risk prediction models.
- 15.15 - 15.35 N. Peek: A specialised POMDP form and algorithm for clinical
patient management.
- 15.35 - 15.55 Coffee break
- 15.55 - 16.25 M. Ramoni, P. Sebastian and R. Dybowski: Robust outcome
prediction for intensive-care patients.
- 16.25 - 16.45 S. Antel, L.M. Li, F. Cendes, Z. Caramanos, A. Olivier,
F. Andermann, F. Dubeau, R.E. Kearney, R. Shinghai, D.L. Arnold:
A naive Bayesian classifier for the prediction of surgical
outcome in patients with temporal lobe epilepsy.
- 16.45 - 17.00 Ameen Abu-Hanna and Peter Lucas: Conclusion
Workshop organization
Co-Chairs:
Ameen Abu-Hanna, University of Amsterdam, The Netherlands
Peter Lucas, Utrecht University, The Netherlands
Programme committee
A. Abu-Hanna, The Netherlands
S.S. Anand, UK
S. Andreassen, Denmark
P.M.M. Bossuyt, The Netherlands
J. Fox, UK
L.C. van der Gaag, The Netherlands
J.D.F. Habbema, The Netherlands
P. Haddawy, USA
P. Hammond, UK
E. Keravnou, Cyprus
N. Lavrac, Slovenia
J. van der Lei, The Netherlands
P.J.F. Lucas, The Netherlands
L. Ohno-Machado, USA
M. Ramoni, UK
M. Stefanelli, Italy
Th. Wetter, Germany
J. Wyatt, UK
For more information about the workshop please contact one of the co-chairs.
Ameen Abu-Hanna
Dept. of Medical Informatics
Academic Medical Center
University of Amsterdam
Meibergdreef 15
1105 AZ Amsterdam
The Netherlands
Telephone: +31 20 5664511
Fax : +31 20 6912432
A.Abu-Hanna@amc.uva.nl
|
Peter Lucas
Dept. of Computer Science
Utrecht University
Padualaan 14
3584 CH Utrecht
The Netherlands
Telephone: +31 30 2534094
Fax: +31 30 2513791
lucas@cs.uu.nl
|