PubMed Health⌕ Search

PubMed · 11776738

Knowledge-based and data-driven models in arrhythmia fuzzy classification.

Abstract

OBJECTIVES: Fuzzy rules automatically derived from a set of training examples quite often produce better classification results than fuzzy rules translated from medical knowledge. This study aims to investigate the difference in domain representation between a knowledge-based and a data-driven fuzzy system applied to an electrocardiography classification problem. METHODS: For a three-class electrocardiographic arrhythmia classification task a set of fifteen fuzzy rules is derived from medical expertise on the basis of twelve electrocardiographic measures. A second set of fuzzy rules is automatically constructed on thirty-nine MIT-BIH database's records. The performances of the two classifiers on thirteen different records are comparable and up to a certain extent complementary. The two fuzzy models are then analyzed, by using the concept of information gain to estimate the impact of each ECG measure on each fuzzy decision process. RESULTS: Both systems rely on the beat prematurity degree and the QRS complex width and neglect the P wave existence and the ST segment features. The PR interval is not well characterized across the fuzzy medical rules while it plays an important role in the data-driven fuzzy system. The T wave area shows a higher information gain in the knowledge based decision process, and is not very much exploited by the data-driven system. CONCLUSIONS: The main difference between a human designed and a data driven ECG arrhythmia classifier is found about the PR interval and the T wave.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

R Silipo, R Vergassola, W Zong, M R Berthold. 2001. Knowledge-based and data-driven models in arrhythmia fuzzy classification.. https://pubmed.health/record/pubmed%3A11776738/knowledge-based-and-data-driven-models-in-arrhythmia-fuzzy-classification

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite PubMed Health by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related citations

Safety of nerve conduction studies in patients with implanted cardiac devices.

Patients with implanted cardiac devices and their physicians may defer important electrodiagnostic testing because of anxiety about potential negative effects on the device. To determine the safety of routine nerve conduction studies (NCS) in this population, 10 patients with permanent dual-chamber pacemakers of various types and five patients with implanted cardiac defibrillators (ICD) underwent nerve stimulation at sites commonly used during NCS. The implanted cardiac device was interrogated before and after the study and there was continuous monitoring of the surface electrocardiogram (ECG) and atrial and ventricular electrograms. Electrical impulses generated during routine NCS were never detected by the sensing amplifier and did not affect the programmed settings of the implanted cardiac device. We conclude that routine NCS is safe in patients with implanted cardiac pacemakers with bipolar sensing configurations and defibrillators.

Arrhythmias, Cardiac↗

[Pulmonary diseases and heart function].

The most severe cardiac sequel to lung disease is the load on the right ventricle due to pulmonary hypertension with the development of a cor pulmonale. This is characterized by hypertrophy and/or dilatation of the right ventricle because of a primary impairment of lung function and/or lung structure. The most important pathomechanisms for the development of pulmonary hypertension are vessel obliteration, mechanical lesions, primary vascular or extra-vascular inflammation and hypoxic vasoconstriction. Chronic obstructive pulmonary disease (COPD) is one of the most important reasons for chronic cor pulmonale. A further very common reason is obstructive sleep apnea syndrome, especially if combined with a COPD. In this case, the prevalence of cor pulmonale can reach 80%. The development of a chronic cor pulmonale is the most striking negative prognostic factor for these patients. Only 30% of COPD patients with cor pulmonale survive longer than 5 years, and only early detection of the disturbances to respiration which might potentially lead to cor pulmonale and their subsequent therapy are able to improve the patient's prognosis. Furthermore, pulmonary diseases may also have an impact on the left heart side in terms of an impairment of left heart function or by inducing severe arrhythmias . Thus, lung diseases may have both a significant impact on right and left heart performance.

Arrhythmias, Cardiac↗