Home|Journals Follow on Twitter| Subscribe to List

Directory for Medical Articles
 

Open Access

Original Research

Acta Inform Med. 2008; 16(4): 178-182


The Role of KDD Support-Interpretation Tools in the Conceptualization of Medical Profiles: An Application to Neurorehabilitation

Karina Gibert, Alejandro García-Rudolph, Gustavo Rodríguez-Silva.

Abstract
Purpose: The work presents the usefulness of Traffic lights panel for assisting the interpretation of clustering results and includes an application to a real case of discovering response patterns to a rehabilitation treatment for brain damage patients. Work Method: A KDD framework where first, descriptive statistics of every variable was done, data cleaning and selection of relevant variables. Then data was mined using Exogen based on rules (ClBR), a hybrid AI and Statistics technique which combines inductive learning (AI) and clustering (Statistics). A prior Knowledge Base (KB) is considered to properly bias the clustering; semantic constraints implied by the KB hold in final clusters, guaranteeing interpretability of the results. Class panel graph, previously used for interpretation is abstracted and transformed to a Traffic lights panel to assist the expert in a final process of conceptualizing the obtained classes. Work Results: A set of 4 classes was recommended by the system and interpretation permitted profiles labeling. From the medical point of view, composition of classes is well corresponding with different patterns of increasing level of response to rehabilitation treatments. The Traffic lights panel is confirmed as a very useful tool to approach the results of the clustering to the expert, making the final interpretation easier Discussion: All the patients initially assessable conform a single group. Severe impaired patients are subdivided in three profiles which clearly distinct response patterns. Particularly interesting the partial response profile, where patient could not improve executive functions. Traffic lights panel is clearly representing the profiles, so the expert can very quickly label them. Conclusions: Meaningful classes were obtained and, from a semantics point of view, the results were sensibly improved regarding classical clustering, according to our opinion that hybrid AI&Stats techniques are more powerful for KDD than pure ones. Interpreting the results upon the Traffic lights panel is much easier an quick than presenting the CPG directly to the expert

Key words: decision support and knowledge management, rehabilitation, clinical test, TBI, knowledge discovery, interpretation-oriented tools, class panel graphs, traffic lights panel, exogenous clustering based on rules, knowledge-based applications in medicine.



Share this Article


Advertisement
Journal of Molecular Pathophysiology

SUBMIT YOUR ARTICLE NOW


ScopeMed.com
ScopeMed Home
Follow ScopeMed on Twitter
BiblioCAM
Author Tools
eJPort Journal Hosting
About ScopeMed
License Information
Terms & Conditions
Privacy Policy
Contact Us

The articles in Scopemed are open access articles licensed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (https://creativecommons.org/licenses/by-nc-sa/4.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.
ScopeMed is a Database Service for Scientific Publications. Copyright © ScopeMed® Information Services.
Scopemed Buttons