Data Mining with Combined Use of Optimization Techniques and Self-Organizing Maps for Improving Risk Grouping Rules: Application to Prostate Cancer Patients.

Author List: Churilov, Leonid; Bagirov, Adyl; Schwartz, Daniel; Smith, Kate; Dally, Michael;
Journal of Management Information Systems, 2005, Volume 21, Issue 4, Page 85-100.
Data mining techniques provide a popular and powerful tool set to generate various data-driven classification systems. In this paper, we investigate the combined use of self-organizing maps (SOM) and nonsmooth nonconvex optimization techniques in order to produce a working case of a data-driven risk classification system. The optimization approach strengthens the validity of SOM results, and the improved classification system increases both the quality of prediction and the homogeneity within the risk groups. Accurate classification of prostate cancer patients into risk groups is important to assist in the identification of appropriate treatment paths. We start with the existing rules and aim to improve classification accuracy by identifying inconsistencies utilizing self-organizing maps as a data visualization tool. Then, we progress to the study of assigning prostate cancer patients into homogenous groups with the aim to support future clinical treatment decisions. Using the case of prostate cancer patients grouping, we demonstrate strong potential of data-driven risk classification schemes for addressing the risk grouping issues in more general organizational settings.
Keywords: classification; data mining; optimization; prostate cancer; risk grouping
Algorithm:

List of Topics

#215 0.288 data classification statistical regression mining models neural methods using analysis techniques performance predictive networks accuracy method variables prediction problem measure
#97 0.150 set approach algorithm optimal used develop results use simulation experiments algorithms demonstrate proposed optimization present analytical distribution selection number existing
#77 0.124 information systems paper use design case important used context provide presented authors concepts order number various underlying implementation framework nature
#264 0.089 risk risks management associated managing financial appropriate losses expected future literature reduce loss approach alternative mitigate failures failure cause mitigation
#34 0.088 negotiation negotiations using potential power agreement paper bases partners ending negotiators offers visualization messaging instant audio e-marketplaces provide positions agents
#196 0.078 health healthcare medical care patient patients hospital hospitals hit health-care telemedicine systems records clinical practices physician electronic physicians longitudinal outcomes
#193 0.056 time use size second appears form larger benefits combined studies reasons selected underlying appear various significantly result include make attention
#233 0.050 group gss support groups systems brainstorming research process electronic members results paper effects individual ebs using used anonymity ideas discussion