Key result
A Support Vector Machine classifier using combined time domain, frequency domain, and nonlinear heart rate variability features achieved 100% accuracy and 100% sensitivity in distinguishing normal from hypertensive subjects.
Why the study?
Does a combined linear and nonlinear HRV feature-based SVM classifier accurately distinguish between normal and hypertension cases?
Cross-Sectional (n=113)
No
Does a combined linear and nonlinear HRV feature-based SVM classifier accurately distinguish between normal and hypertension cases?
Combining linear and nonlinear heart rate variability features with a support vector machine classifier provides highly accurate discrimination between normal subjects and patients with hypertension.
May aid noninvasive hypertension detection; leaves open prospective validation before clinical adoption.
The aim of this study is to analyse and compare the heart rate variability (HRV) of normal and hypertension cases using time domain, frequency domain, and nonlinear methods. For short term HRV analysis, a five-minute electrocardiogram (ECG) of 57 normal and 56 hypertension subjects were recorded with prior verification of their clinical status by a cardiologist. Most time domain features of hypertension cases have clearly reduced values over normal subjects, frequency domain features, like power in different spectral bands, also have the distinguishable decreased values, whereas sympathovagal balance has clear edge over hypertension cases than normal cases. Nonlinear parameters of Poincare plot, approximate entropy and sample entropy, have higher values in normal cases when compared with hypertension cases. Support vector machine-based binary system classifies these two classes with 100 per cent accuracy and 100 per cent sensitivity when all time domain, frequency domain, and nonlinear features were used. It may work as a better predictor for in patients with hypertension. Science Journal, Vol. 64, No. 6, November 2014, pp.542-548, DOI:http://dx.doi.org/10.14429/dsj.64.7867
No takes yet. Share an insight, caveat, or question.
Poddar et al. (2014) conducted a cross-sectional in Hypertension (n=113). Support Vector Machine (SVM) classifier using combined linear and nonlinear HRV features vs. SVM classifier using individual feature sets (time domain, frequency domain, or nonlinear alone) was evaluated on Classification accuracy. A Support Vector Machine classifier using combined time domain, frequency domain, and nonlinear heart rate variability features achieved 100% accuracy and 100% sensitivity in distinguishing normal from hypertensive subjects.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: