Application of higher-order spectra for automated grading of diabetic maculopathy

Diabetic macular edema (DME) is one of the most common causes of visual loss among diabetes mellitus patients. Early detection and successive treatment may improve the visual acuity. DME is mainly graded into non-clinically significant macular edema (NCSME) and clinically significant macular edema according to the location of hard exudates in the macula region. DME can be identified by manual examination of fundus images. It is laborious and resource intensive. Hence, in this work, automated grading of DME is proposed using higher-order spectra (HOS) of Radon transform projections of the fundus images. We have used third-order cumulants and bispectrum magnitude, in this work, as features, and compared their performance. They can capture subtle changes in the fundus image. Spectral regression discriminant analysis (SRDA) reduces feature dimension, and minimum redundancy maximum relevance method is used to rank the significant SRDA components. Ranked features are fed to various supervised classifiers, viz. Naive Bayes, AdaBoost and support vector machine, to discriminate No DME, NCSME and clinically significant macular edema classes. The performance of our system is evaluated using the publicly available MESSIDOR dataset (300 images) and also verified with a local dataset (300 images). Our results show that HOS cumulants and bispectrum magnitude obtained an average accuracy of 95.56 and 94.39 % for MESSIDOR dataset and 95.93 and 93.33 % for local dataset, respectively.

Low Complexity Spectral Analysis of Heart-Rate-Variability through a Wavelet based FFT

In this paper, a low complexity system for spectral analysis of heart rate variability (HRV) is presented. The main idea of the proposed approach is the implementation of the Fast-Lomb periodogram that is a ubiquitous tool in spectral analysis, using a wavelet based Fast Fourier transform. Interestingly we show that the proposed approach enables the classification of processed data into more and less significant based on their contribution to output quality. Based on such a classification a percentage of less-significant data is being pruned leading to a significant reduction of algorithmic complexity with minimal quality degradation. Indeed, our results indicate that the proposed system can achieve up-to 45% reduction in number of computations with only 4.9% average error in the output quality compared to a conventional FFT based HRV system.

Respiratory and non-respiratory sinus arrhythmia: implications for heart rate variability

The quantity of blood arriving at the left side of the heart oscillates throughout the breathing cycle due to the mechanics of breathing. Neurally regulated fluctuations in the length of the heart period act to dampen oscillations of the left ventricular stroke volume entering the aorta. We have reported that stroke volume oscillations but not spectral frequency variability stroke volume measures can be used to estimate the breathing frequency. This study investigated with the same recordings whether heart period oscillations or spectral heart rate variability measures could function as estimators of breathing frequency. Continuous 270 s cardiovascular recordings were obtained from 22 healthy adult volunteers in the supine and upright postures. Breathing was recorded simultaneously. Breathing frequency and heart period oscillation frequency were calculated manually, while heart rate variability spectral maximums were obtained using heart rate variability software. These estimates were compared to the breathing frequency using the Bland–Altman agreement procedure. Estimates were required to be \±10% (95% levels of agreement). The 95% levels of agreement measures for the heart period oscillation frequency (supine: -27.7 to 52.0%, upright: -37.8 to 45.9%) and the heart rate variability spectral maximum estimates (supine: -48.7 to 26.5% and -56.4 to 62.7%, upright: -37.8 to 39.3%) exceeded 10%. Multiple heart period oscillations were observed to occur during breathing cycles. Both respiratory and non-respiratory sinus arrhythmia was observed amongst healthy adults. This observation at least partly explains why heart period parameters and heart rate variability parameters are not reliable estimators of breathing frequency. In determining the validity of spectral heart rate variability measurements we suggest that it is the position of the spectral peaks and not the breathing

Effect of dietary omega-3 fatty acid deficiency on heart rate variability in hooded rats

Introduction: Recent reports in adult humans suggest that heart rate variability is modulated by the concentration of omega-3 polyunsaturated fatty acids (PUFA) contained in blood cell membranes. Material and methods: Hurst analysis of ECG data was conducted on 12 male adult hooded (Long-Evans) rats, representing the 3rd generation to be fed diets that were either deficient in, or supplemented with, omega-3 PUFA. ECG data were obtained from surface electrodes and 4000 beats were analyzed for each animal. Results: Dietary manipulation, despite leading to large changes in tissue omega- 3 PUFA levels, did not significantly affect the complexity of heart rate dynamics, with Hurst exponent (H) values of 0.15±0.02 and 0.12±0.03, for animals fed omega- 3 fatty acid-adequate and -deficient diets, respectively. Mean heart rate was also unaffected by the diets. A power calculation revealed that about one hundred animals per group would have been required to avoid a type II error. Conclusions: According to this model of dietary PUFA manipulation, omega-3 fatty acids are unlikely to exert a large effect on the autonomic functions that control heart rate variability. Prospective studies into the effect of omega-3 fatty acids on HRV should consider the need for large sample size as estimated by the results contained in this report.

Moderate-intensity resistance exercise training in patients with chronic heart failure improves strength, endurance, heart rate variability, and forearm blood flow

Thirty-nine CHF patients (New York Heart Association Functional Class = 2.3±0.5; left ventricular ejection fraction 28%±7%; age 65±11 years; 33:6 male:female) underwent 2 identical series of tests, 1 week apart, for strength and endurance of the knee and elbow extensors and flexors, VO_2peak, HRV, FBF at rest, and FBF activated by forearm exercise or limb ischemia. Patients were then randomized to 3 months of resistance training (EX, n = 19), consisting of mainly isokinetic (hydraulic) ergometry, interspersed with rest intervals, or continuance with usual care (CON, n = 20), after which they underwent repeat endpoint testing. Combining all 4 movement patterns, strength increased for EX by 21±30% (mean±SD, P<.01) after training, whereas endurance improved 21±21% (P<.01). Corresponding data for CON remained almost unchanged (strength P<.005, endurance P<.003 EX versus CON). VO_2peak improved in EX by 11±15% (P<.01), whereas it decreased by 10±18% (P<.05) in CON (P<.001 EX versus CON). The ratio of low-frequency to high-frequency spectral power fell after resistance training in EX by 44±53% (P<.01), but was unchanged in CON (P<.05 EX versus CON). FBF increased at rest by 20±32% (P<.01), and when stimulated by submaximal exercise (24±32%, P<.01) or limb ischemia (26±45%, P<.01) in EX, but not in CON (P<.01 EX versus CON).

Comparison of the Polar S810i monitor and the ECG for the analysis of heart rate variability in the time and frequency domains

The aim of the present study was to compare heart rate variability (HRV) at rest and during exercise using a temporal series obtained with the Polar S810i monitor and a signal from a LYNX® signal conditioner (BIO EMG 1000 model) with a channel configured for the acquisition of ECG signals. Fifteen healthy subjects aged 20.9 ± 1.4 years were analyzed. The subjects remained at rest for 20 min and performed exercise for another 20 min with the workload selected to achieve 60% of submaximal heart rate. RR series were obtained for each individual with a Polar S810i instrument and with an ECG analyzed with a biological signal conditioner. The HRV indices (rMSSD, pNN50, LFnu, HFnu, and LF/HF) were calculated after signal processing and analysis. The unpaired Student t-test and intraclass correlation coefficient were used for data analysis. No statistically significant differences were observed when comparing the values analyzed by means of the two devices for HRV at rest and during exercise. The intraclass correlation coefficient demonstrated satisfactory correlation between the values obtained by the devices at rest (pNN50 = 0.994; rMSSD = 0.995; LFnu = 0.978; HFnu = 0.978; LF/HF = 0.982) and during exercise (pNN50 = 0.869; rMSSD = 0.929; LFnu = 0.973; HFnu = 0.973; LF/HF = 0.942). The calculation of HRV values by means of temporal series obtained from the Polar S810i instrument appears to be as reliable as those obtained by processing the ECG signal captured with a signal conditioner.

Fractal correlation property of heart rate variability in chronic obstructive pulmonary disease

Background: It was reported that autonomic nervous system function is altered in subjects with chronic obstructive pulmonary disease (COPD). We evaluated short-and long-term fractal exponents of heart rate variability (HRV) in COPD subjects.Patients and methods: We analyzed data from 30 volunteers, who were divided into two groups according to spirometric values: COPD (n = 15) and control (n = 15). For analysis of HRV indices, HRV was recorded beat by beat with the volunteers in the supine position for 30 minutes. We analyzed the linear indices in the time (SDNN [standard deviation of normal to normal] and RMSSD [root-mean square of differences]) and frequency domains (low frequency [LF], high frequency [HF], and LF/HF), and the short-and long-term fractal exponents were obtained by detrended fluctuation analysis. We considered P < 0.05 to be a significant difference.Results: COPD patients presented reduced levels of all linear exponents and decreased short-term fractal exponent (alpha-1: 0.899 +/- 0.18 versus 1.025 +/- 0.09, P = 0.026). There was no significant difference between COPD and control groups in alpha-2 and alpha-1/alpha-2 ratio.Conclusion: COPD subjects present reduced short-term fractal correlation properties of HRV, which indicates that this index can be used for risk stratification, assessment of systemic disease manifestations, and therapeutic procedures to monitor those patients.

Nonlinear methods of heart rate variability analysis in diabetes

Background: The autonomic dysfunction stands out among the complications associated to diabetes mellitus (DM) and may be evaluated through the heart rate variability (HRV), a noninvasive tool to investigate the autonomic nervous system that provides information of health impairments and may be analyzed by using linear and nonlinear methods. Several studies have shown that HRV measured in a linear form is altered in DM. Nevertheless, a few studies investigate the nonlinear behavior of HRV. Therefore, this study aims at gathering information regarding the autonomic changes in subjects with DM identified by nonlinear analysis of HRV.Methods: For that, searches were performed on Medline, SciELO, Lilacs and Cochrane databases using the crossing between the key-words: diabetic autonomic neuropathy, autonomic nervous system, diabetes mellitus and heart rate variability. As inclusion criteria, articles published on a period from 2000 to 2010 with DM type land type II population which assessed the autonomic nervous system by nonlinear indices HRV were considered.Results: The electronic search resulted in a total of 1873 references with the exclusion of 1623 titles and abstracts and from the 250 abstracts remaining, 8 studies were selected to the final analysis that completed the inclusion criteria.Conclusions: In general, the analysis showed that the nonlinear techniques of HRV allowed detecting autonomic changes in DM. The methods of nonlinear analysis are indicated as a possible tool to be used for early diagnosis and prognosis of autonomic dysfunction in DM.

A snoring classifier based on heart rate variability analysis

The effect of snoring on the cardiovascular system is not well-known. In this study we analyzed the Heart Rate Variability (HRV) differences between light and heavy snorers. The experiments are done on the full-whole-night polysomnography (PSG) with ECG and audio channels from patient group (heavy snorer) and control group (light snorer), which are gender- and age-paired, totally 30 subjects. A feature Snoring Density (SND) of audio signal as classification criterion and HRV features are computed. Mann-Whitney statistical test and Support Vector Machine (SVM) classification are done to see the correlation. The result of this study shows that snoring has close impact on the HRV features. This result can provide a deeper insight into the physiological understand of snoring. © 2011 CCAL.