INTELLIGENT DATA ANALYSIS IN MEDICINE AND PHARMACOLOGY (IDAMAP-97)

Nagoya, Japan, August 23, 1997

A Workshop at the 15th International Joint Conference on Artificial Intelligence IJCAI-97, Nagoya, Japan, Saturday, August 23-29, 1997

This is the second workshop on Intelligent data analysis in medicine and pharmacology. The first IDAMAP Workshop was held at Budapest in August, 1996. Abstracts of the papers are available at IDAMAP-96 web page.

Schedule

Each paper is allocated 30 mins, of which 20 mins are allocated for presentation, 5 mins for discussion, and 5 mins on commentators' report.

9:00 Welcome by Workshop Chair
9:05 - 10:35 Part I: Intelligent data analysis: The temporal dimension
Chair: Elpida Keravnou
9:05 Riccardo Bellazzi, Cristiana Larizza, and Albert Riva:
Temporal abstractions for pre-processing and interpreting diabetes monitoring time abstractions (Abstract)
9:35 Anders Hansson and Silvia Miksch:
On-line identification of a patient-disease model for mechanical ventilation (Abstract)
10:05 Yuval Shahar:
Knowledge-based interpolation of time-oriented clinical data (Abstract)
10:35 - 11:00 Coffee Break
11:00 - 13:00 Part II: Intelligent data analysis: The probabilistic and classification dimensions
Chair: Riccardo Bellazzi
11:00 Cungen Cao, Tze-Yun Leon, Adrian Pheng Kheong Leong, and Francis Seow Choen:
Learning conditional probabilities for dynamic influence views (Abstract)
11:30 Du Junping, K.L. Rasmussen, J. Aagaard, Brian H. Mayoh, and Tom Sorensen:
Applications of machine learning: A medical follow up study (Abstract)
12:00 Bing Liu, Wynne Hsu, and Shu Chen:
Discovering conforming and unexpected classification rules (Abstract)
12:30 Igor Zelic, Igor Kononenko, Nada Lavrac, and Vanja Vuga:
Induction of decision trees and Bayesian classification applied to diagnosis of sport injuries (Abstract)
13:00 - 14.30 Lunch
14:30 - 15:00 Part III: Intelligent data analysis: What are the targets?
Chair: Nada Lavrac
14:30 Nada Lavrac, Elpida Keravnou, and Blaz Zupan:
Intelligent data analysis in medicine (Abstract)
15:00 - 15:30 General discussion: What has been achieved so far?
15:30 - 16:00 Coffe Break
16:00 - 17:00 General discussion: Where should we head?
17:00 - 17:10 Summing up: 2-3 minute concluding remarks from every part

General information

IDAMAP-97, a one day IJCAI-97 workshop, will be held in Nagoya, Japan, on Saturday, August 23, 1997 prior to the start of the main IJCAI conference.

Gathering in an informal setting, workshop participants will have the opportunity to meet and discuss selected technical topics in an atmosphere which fosters the active exchange of ideas among researchers and practitioners. To encourage interaction and a broad exchange of ideas, the workshop will be kept small, preferably under 30 participants and certainly under 40. Attendance will be limited to active participants only. The workshop is intended to be a genuinely interactive event and not a mini-conference, thus ample time will be allotted for general discussion. The workshop will last one full day. Attendees at the workshop will have to register for the main IJCAI conference.

Topic

The gap between data generation and data comprehension is widening in all fields of human activity. In medicine and pharmacology overcoming of this gap is particularly crucial since medical decision making needs to be supported by arguments, based on basic medical and pharmacological knowledge as well as knowledge, regularities and trends extracted from data by intelligent data analysis techniques.

Computational methods for intelligent data analysis are aimed at narrowing the gap between data gathering and data comprehension. For example, effective machine learning tools exist that can be used to generate understandable diagnostic and prognostic rules. One of the main topics of the workshop are techniques for intelligent data mining and knowledge discovery, focused on applications of intelligent data analysis in medical and pharmacological databases. Further main topics of the workshop are applications of clustering, data visualization, interpretation of time-ordered data (derivation and revision of temporal trends and other forms of temporal data abstraction), learning with case bases, discovery of new diseases, new drug compounds, predicting drug activity, etc. Special emphasis will be given to solving problems which result from the automated data collection in modern hospitals, such as analysis of computer-based patient records (CPR), analysis of data from patient-data management system (PDMS), intelligent alarming, as well as effective and efficient monitoring.

Organizing Committee

Further information

For requests on further information, please send an e-mail to idamap97@ijs.si or contact us on:

Nada Lavrac, Blaz Zupan
J. Stefan Institute
Jamova 39
SI-1000 Ljubljana
Slovenia
tel. +386 61 177 3272, 177 3380
fax. +386 61 125 1038, 219 385

page maintained by Blaz Zupan, last update Sep 5, 1997