Recipient Institution:
University of Science Malaysia (USM)

Project Leader:
Dr. LIM Chee Peng, Associate Professor

Amount and Duration: US$ 9,000 / 12 months

Commencement Date:
January 2005

Abstract of Project
The aim of the proposed project is to develop and implement a web-based Medical Information Repository (MIR) integrated with a computerized medical Decision Support System (DSS) to provide advanced, quality healthcare information and services for all people, especially the rural communities, through the use of Information and Communication Technology (ICT) as well as Artificial Intelligence (AI) methodology.

The main output of the proposed project is a web-based MIR and DSS software comprising:

1. anonymous medical records of patients, including physical symptoms, family history, and bio-chemical test results-useful for medical practitioners and researchers;
2. heuristic prognostic and diagnostic rules elicited from medical specialists as well as from the DSS-useful for junior and inexperienced clinicians;
3. disease statistics and facts-useful for healthcare administrators and policy makers

A prototype system comprising the MIR and DSS for acute stroke diagnosis will be implemented. The necessary data and information pertaining to stroke patients from a number of Asia countries are available for analysis as the applicants are involved in a pilot study on stroke diagnosis spearheaded by ASAP (Asia Stroke Advisory Panel).

Novelty of the proposed project lies in the inclusion of an AI-based DSS into the MIR. The Adaptive Resonance Theory (ART) family of neural networks will be utilized to design the DSS. Unlike other intelligent systems existed in the literature, innovation of the proposed system lies in the autonomous learning behaviors of ART-based neural networks. Once developed, the system is able to learn incrementally in real-time, non-stationary environments with minimum intervention from the system designer (computing or AI experts). With this autonomous learning capability, domain users (medical practitioners) are able to train and fine-tune the decision support system, and to assume "ownership" of the system, hence overcoming resistance by non-computing/AI users to apply such a computational tool in their work.