Related Experiment Videos
Potential of feature selection methods in heart rate variability analysis for the classification of different
Agnes Schumann1, Niels Wessel, Alexander Schirdewan
1University of Applied Sciences, Jena, Germany.
Insights
Heart rate variability (HRV) analysis effectively distinguishes cardiovascular diseases from healthy individuals using specific parameters. A general HRV marker shows promise for early heart disease detection, while distinct parameters are needed for classifying specific heart conditions.
Area of Science:
- Cardiology
- Biomedical Engineering
- Data Science
Background:
- Heart rate variability (HRV) analysis is a non-invasive method to assess autonomic nervous system function.
- Cardiovascular diseases (CVDs) like coronary heart disease (CHD), dilated cardiomyopathy (DCM), and myocardial infarction (MI) significantly impact cardiac health.
- Accurate discrimination between different CVDs and healthy controls (HC) is crucial for timely diagnosis and treatment.
Purpose of the Study:
- To apply HRV analysis for characterizing and discriminating between patients with CHD, DCM, MI, and HC.
- To identify optimal HRV parameter subsets for improved diagnostic value and physiological interpretation.
- To evaluate the generalizability of selected HRV parameters across different diagnostic tasks.
Main Methods:
- Feature selection and linear classification techniques were employed on a set of 33 HRV measures.
- Analysis included time-domain, frequency-domain, and non-linear dynamics parameters.
- Feature selection was performed separately for each diagnostic task (disease vs. HC, and inter-disease classification).
Main Results:
- A specific parameter set (set1: normalized low frequency LF/P and WPSUM13) demonstrated high performance in distinguishing diseased subjects from HC across all tasks.
- This set appears to be a general marker for pathological HRV changes, potentially aiding early heart disease detection.
- A different parameter set (set2: meanNN, sdaNN, and SEAR parameters) was optimal for classifying distinct heart diseases, with set1 showing reduced performance for this task.
Conclusions:
- HRV analysis, with carefully selected features, can effectively differentiate between various cardiovascular conditions and healthy states.
- A general HRV parameter set shows potential for early detection of cardiac pathology.
- Task-specific HRV parameter sets are necessary for accurate classification of different heart diseases, highlighting the complexity of HRV in disease severity assessment.
Abstract:
In this study heart rate variability (HRV) analysis was applied to characterize patients suffering from coronary heart disease (CHD), dilated cardiomyopathy (DCM) and patients who had survived an acute myocardial infarction (MI). On the basis of several HRV parameters, an optimal discrimination between the different kinds of cardiovascular diseases and between the diseases and healthy controls (HC) was derived by feature selection and linear classification. For each task a small favourable subset of a set of 33 potentially interesting HRV measures was selected with the intention of improving the diagnostic value and facilitating the physiological interpretation of HRV analysis. Time- and frequency-domain parameters as well as parameters from non-linear dynamics were included in the analysis. With the expectation that different diseases are characterized by different phenomena, feature selection was applied for each task separately. Using the features optimal for one task to another task can reveal a loss in performance, but it turned out that one specific parameter set (set1: normalized low frequency LF/P and a non-linear variability measure WPSUM13) was applicable for all tasks, where diseased and healthy subjects have to be distinguished, without significant reduction in performance. This set seems to be a general marker for pathologic changes in HRV and might be used for early detection of heart diseases. The classification between different heart diseases requires another parameter set (set2: meanNN and sdaNN, reflecting the steady state behaviour of the heart rate and long and short term SEAR describing the spectral composition). However, the use of set1 for the separation of different kinds of diseases, where set2 is appropriate, led to significant reduction in performance and vice versa. This observation may be important for future developments of HRV measures especially suitable for the assessment of disease severity.