Related Experiment Videos
Pattern recognition in evaluation of haemorheological and haemodynamical measurements in the cardiological
11st Internal Med. Clinic, Department of Cardiology, University Medical School, Pécs.
Insights
Diagnosing ischemic heart disease (IHD) and myocarditis is challenging. A multivariate statistical method using haemorheological data achieved over 80% accuracy in differentiating these cardiac conditions.
Area of Science:
- Cardiology
- Medical Diagnostics
- Biostatistics
Background:
- Non-invasive differentiation between ischemic heart disease (IHD) and myocarditis/secondary cardiomyopathy is clinically challenging.
- Standard diagnostic methods like ECG and nuclear imaging have limitations in distinguishing these conditions.
Purpose of the Study:
- To evaluate a multivariate pattern recognition algorithm (PRIMA) for the differential diagnosis of IHD and myocarditis.
- To assess the diagnostic utility of haemodynamic and haemorheological parameters in differentiating critical cardiac conditions.
Main Methods:
- Examined 192 patients with cardiac complaints in two steps, including routine parameters, haemodynamic, and haemorheological measurements.
- Utilized a multivariate pattern recognition algorithm (PRIMA) for patient classification into subgroups (myocardial infarction, IHD, myocarditis, chronic cor pulmonale).
- Analyzed the discrimination power of various parameters, focusing on haemorheological vs. haemodynamic features.
Main Results:
- The PRIMA algorithm demonstrated an average effectiveness exceeding 80% in patient classification.
- Recognition abilities for specific subgroups ranged from 71% to 100%.
- Haemorheological features proved more characteristic than haemodynamic ones in distinguishing between diagnostically critical groups.
Conclusions:
- The developed multivariate statistical method shows significant potential for computer-aided decision-making in cardiology.
- Haemorheological measurements are valuable for differentiating between IHD and myocarditis.
- This approach can aid in the non-invasive differential diagnosis of complex cardiac diseases.
Abstract:
The non-invasive differential diagnosis of ischaemic heart disease (IHD) and acute myocarditis or secondary cardiomyopathy following myocarditis can be difficult on the basis of the complaints, resting and exercise ECG and nuclear cardiological tests. 92 patients (mean age: 46 years) in the first step and 100 patients (mean age: 44 years) in the second step all with heart troubles, were examined. Besides determination of the routine parameters, nuclear haemodynamical and haemorheological measurements were carried out. Then each group of the patients was classified into 4 subgroups: 1) myocardial infarction /n:9/, 2) IHD /52/, 3) myocarditis /28/, 4) chronic cor pulmonale (CCP) /3/ subgroups in the first group and 1) normal /n:20/, 2) IHD /50/, 3) myocarditis /16/, 4) chronic cor pulmonale /14/ subgroups in the second group. The patients were reclassified by our multivariate pattern recognition algorithm (PRIMA). The average effectiveness of our method was over 80%, the recognition abilities for the subgroups (classes) ranged between 71 and 100%. An analysis of the discrimination power of the properties has made it evident that the haemorheological features were more characteristic than the haemodynamic ones in distinguishing the two differential-diagnostically critical groups. Our results show that our multivariate statistical method can be useful for the computer-aided decision in cardiological diagnostics.