Document Detail

Identification of echocardiographic indices for the early detection of left-ventricular systolic dysfunction in beta-thalassaemia via Self-Organizing Maps: a data-exploration study.
MedLine Citation:
PMID:  16036629     Owner:  NLM     Status:  MEDLINE    
Congestive heart failure (CHF) remains the primary cause of death in patients suffering from beta-thalassaemia major. Its early detection allows the prompt initiation of aggressive chelation therapy, when the condition can still be reversed. We aimed at identifying echocardiographic indices for the early detection of left ventricular (LV) systolic dysfunction, the physiological abnormality underlying CHF, in these patients. We used Self-Organizing Maps (SOMs)--an artificial neural network--for identifying novel correlations within our Electronic Healthcare Record (EHCR) database on beta-thalassaemia. We sought echocardiographic parameters that are correlated to future deterioration of the LV ejection fraction and therefore constitute early signs of LV systolic dysfunction. At the same time, we evaluated SOMs as tools for exploring clinical datasets and make recommendations on the setup of the SOM algorithm that is appropriate for such tasks. We found that high values of the LV end-systolic diameter index and of the E/A ratio are early indications of LV systolic dysfunction. From a technical point of view, zero-mean unit-variance normalization of the input data, a large initial neighbourhood radius and a rectangular SOM grid produced optimal maps for the purpose of detecting clinical correlations. We have successfully used SOMs for exploring a clinical dataset and for creating novel medical hypotheses. A clinical study has been launched to confirm these hypotheses, and initial results are encouraging.
Spyros Deftereos; Dimitra Georgonikou; Andreas Persidis; Christos Andronis; Athanassios Aessopos
Related Documents :
15589639 - Myocardial performance index, a doppler-derived index of global left ventricular functi...
11807739 - Left ventricular reconstruction by endoventricular circular patch plasty repair: a 17-y...
16352219 - Myocardial tissue velocities in the normal left and right ventricle: relationships and ...
19952479 - A case of iron overload cardiomyopathy: beneficial effects of iron chelating agent and ...
8279379 - Systolic time intervals after phenylephrine administration for early stratification of ...
18215719 - Chronic xanthine oxidase inhibition following myocardial infarction in rabbits: effects...
11984749 - The renin-angiotensin system does not contribute to the endothelial dysfunction and inc...
6840119 - Does exercise testing with invasive measurements of cardiac output and pressure really ...
24844719 - Toronto heart attack collaborative: an administrative model that facilitated a successf...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Medical informatics and the Internet in medicine     Volume:  30     ISSN:  1463-9238     ISO Abbreviation:  Med Inform Internet Med     Publication Date:  2005 Mar 
Date Detail:
Created Date:  2005-07-22     Completed Date:  2005-08-11     Revised Date:  2007-11-15    
Medline Journal Info:
Nlm Unique ID:  100883495     Medline TA:  Med Inform Internet Med     Country:  England    
Other Details:
Languages:  eng     Pagination:  37-53     Citation Subset:  IM    
University of Athens Medical School, Laiko Hospital, Athens, Greece.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Early Diagnosis
Heart Failure / physiopathology
Image Interpretation, Computer-Assisted / methods*
Medical Records Systems, Computerized
Middle Aged
Quality Assurance, Health Care
Ventricular Dysfunction, Left / complications,  diagnosis*
beta-Thalassemia / complications*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  ECG and XML: an instance of a possible XML schema for the ECG telemonitoring.
Next Document:  Attitudes and skills of Hong Kong Chinese medicine practitioners towards computerization in practice...