PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 9357617

Modelling cardiac patient set residuals using rough sets.

A Ohrn·S Vinterbo·P Szymański·J Komorowski
View original source ↗Export metadata ↓

Abstract

Many medical studies deal with the assessment of the prognostic or diagnostic power of some particular test with respect to some particular medical condition. However, even though a test is deemed to be powerful in this respect, the test may not be strictly needed to perform for everyone. If the test is costly or invasive, this issue is of particular interest. This paper presents a methodology based on rough set theory and Boolean reasoning that can be used to identify those patients for whom performing the test is redundant or superfluous. Furthermore, the methodology enables one to automatically construct a set of descriptive and minimal if-then rules that model the patient group in need of the test. A reanalysis of a previously published real-world dataset of patients with chest pain is used as a case study.

Explore related subjects

Coronary DiseaseDecision Making, Computer-AssistedDecision Support TechniquesHumansInformation TheoryMyocardial InfarctionProbabilityPrognosisSensitivity and SpecificityTomography, Emission-Computed, Single-PhotonJournal ArticleResearch Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

A Ohrn, S Vinterbo, P Szymański, J Komorowski. 1997. Modelling cardiac patient set residuals using rough sets.. https://pubmed.ncbi.nlm.nih.gov/9357617/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2007

Update on PPAR agonists: the clinical significance of FIELD and PROACTIVE.

The peroxisome proliferator-activated receptor (PPAR) family of genes plays a major role in metabolic regulation. Unfortunately, the results of two recent, large event trials of PPAR agonists have been mixed. High rates of crossover to statin use confound the interpretation of the Fenofibrate Intervention and Event Lowering in Diabetes (FIELD) trial, which found a less than expected reduction in coronary and stroke events with fenofibrate. Of concern, nonsignificant increases in coronary and sudden deaths, thrombotic events, and pancreatitis occurred in the fenofibrate group. The PROspective pioglitAzone Clinical Trial In macroVascular Events (PROACTIVE) also found a reduction in coronary and stroke events with pioglitazone compared with placebo in a population with diabetes and cardiovascular disease, but this benefit was counterbalanced by an increase in congestive heart failure as well as symptomatic edema. Further research is needed to determine the role of PPAR agonists in the prevention of cardiovascular disease.

Coronary Disease↗
PubMed2007

Depressive symptoms and sex affect completion rates and clinical outcomes in cardiac rehabilitation.

Symptoms of depression are often seen in patients with coronary heart disease. Symptoms appear more commonly in women and are negatively associated with measures of cardiovascular health. Using multiple logistic regression analyses, the authors evaluated the independent effects of depression (as measured by the Beck Depression Inventory [BDI-II]) and sex on cardiac rehabilitation (CR) completion. In addition, in those who completed CR, the authors evaluated whether depressive symptoms and sex affected clinical outcomes. Women as well as participants with enrollment BDI-II scores > or =14 had significantly higher rates of CR noncompletion. Patients with BDI-II scores > or =14 who completed CR achieved significant improvements in lipid profile, body mass index, and exercise capacity regardless of sex. Women and individuals with BDI-II scores > or =14 are at risk for CR noncompletion and should be encouraged to complete CR, because cardiovascular benefits comparable to those seen in men and individuals with low BDI-II scores were achieved when these patients completed the CR program.

Coronary Disease↗