Search

The most common clinical sign in pediatric cardiology is heart murmur, which can often be uncharacteristic. The aim of this research was to present the results of development of a classifier based on machine learning algorithms whose purpose is to classify organic murmur that occur in congenital heart defect (CHD). The study is based on the data collected at Pediatric Clinic, Clinical Center University of Sarajevo during three-year period. Totally, 116 children aged from 1 to 15 years were enrolled in the study. Input parameters for classification are parameters obtained during basic physical examination and assessment of patient. First, analysis of relevance of the feature for classification was done using InfoGain, GainRatio, Relief and Correlation method. In the second step, classifiers based on Naive Bayes, Logistic Regression, Decision Tree, Random Forest and Support Vector Machine were developed and compared by performance. The results of this research suggest that high accuracy (90%) classifier for detection of CHD based on 16 parameters can be developed. Such classifier with appropriate user interface would be valuable diagnostic aid to doctors and pediatricians at primary healthcare level for diagnostic of heart murmurs.

Background: A significant number of patients who underwent surgical myocardial revascularization (CABG) have various comorbidities, including left ventricular diastolic dysfunction (LVDD). Objective: The aim of this paper is to show that patients with preoperative LVDD are at an increased risk of postoperative adverse events and have a worse prognosis compared to patients without LVDD. Methods: The study included 116 patients who underwent myocardial revascularization (CABG) performed at Medical Institute Bayer in Tuzla over a period of 1 year. None of the patients had previously undergone CABG or valvular surgery, or undergone stent implantation (PCI). The presence of LV diastolic dysfunction was detected by echocardiography, and the patients were divided into two groups: with and without LVDD, and further classified into three degrees of LVDD. Results: Of the total number of subjects who underwent surgical revascularization of the myocardium without echocardiographically detected LVDD, 24.1% were patients, and 75.9% were patients with LVDD. In the group with LVDD, the range of days spent in the intensive care unit (ICU) is significantly higher compared to patients without LVDD. Also, patients with LVDD had a significantly higher number of hours of inotropic support, a significantly higher number of cases of tachycardia, predominantly atrial fibrillation (POAF). In this group of patients, a greater number of other adverse events were observed, such as myocardial infarction, cardiac or renal failure, TIA or CVI. Of the total number of patients in the study, 107 patients survived surgical myocardial revascularization and had a satisfactory recovery while 9 (7.8%) survived, all from the group with LVDD. Conclusion: Patients with preoperative diastolic dysfunction of the left ventricle, especially with III degree of dysfunction, are exposed to a higher postoperative risk of adverse events such as: atrial fibrillation, prolonged stay in the intensive care unit, the need for longer-term support with inotropes, and the fatal outcome was recorded exclusively in patients with LV diastolic dysfunction.