Self-organizing maps for translating health care knowledge: a case study in diabetes management

Authors:
Kumari Wickramasinghe;Damminda Alahakoon;Peter Schattner;Michael Georgeff
Affiliations:
Department of General Practice, Faculty of Medicine, Nursing and Health Sciences, Monash University, Australia;Faculty of Information Technology, Monash University, Australia;Department of General Practice, Faculty of Medicine, Nursing and Health Sciences, Monash University, Australia;Department of General Practice, Faculty of Medicine, Nursing and Health Sciences, Monash University, Australia
Venue:
AI'11 Proceedings of the 24th international conference on Advances in Artificial Intelligence
Year:
2011

Citing 7
Cited 1

Exploration mining in diabetic patients databases: findings and conclusions

Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining
Feature Selection via Supervised Model Construction

ICDM '04 Proceedings of the Fourth IEEE International Conference on Data Mining
Feature selection and classification model construction on type 2 diabetic patients' data

Artificial Intelligence in Medicine
Data mining for the diagnosis of type II diabetes from three-dimensional body surface anthropometrical scanning data

Computers & Mathematics with Applications
Healthcare knowledge management: the art of the possible

AIME'07 Proceedings of the 2007 conference on Knowledge management for health care procedures
Data mining a diabetic data warehouse

Artificial Intelligence in Medicine
Dynamic self-organizing maps with controlled growth for knowledge discovery

IEEE Transactions on Neural Networks

Improving classifications for cardiac autonomic neuropathy using multi-level ensemble classifiers and feature selection based on random forest

AusDM '12 Proceedings of the Tenth Australasian Data Mining Conference - Volume 134

Quantified Score

Hi-index	0.00

Visualization

Abstract

Chronic Disease Management (CDM) is an important area of health care where Health Knowledge Management can provide substantial benefits. A web-based chronic disease management service, called cdmNet, is accumulating detailed data on CDM as it is being rolled out across Australia. This paper presents the application of unsupervised neural networks to cdmNet data to: (1) identify interesting patterns in diabetes data; and (2) assist diabetes related policy-making at different levels. The work is distinct from existing research in: (1) the data; (2) the objectives; and (3) the techniques used. The data represents the diabetes population across the entire primary care sector. The objectives include diabetes related decision and policy making at different levels. The pattern recognition techniques combine a traditional approach to data mining, involving the Self-Organizing Map (SOM), with an extension to include the Growing Self-Organizing Map (GSOM).