Discrimination between different degrees of coronary artery disease using time-domain features of the finger photoplethysmogram in response to reactive hyperemia

Machine Learning Techniques for the Performance Enhancement of Multiple Classifiers in the Detection of Cardiovascular Disease from PPG Signals

Photoplethysmography (PPG) signals are widely used in clinical practice as a diagnostic tool since PPG is noninvasive and inexpensive. In this article, machine learning techniques were used to improve the performance of classifiers for the detection of cardiovascular disease (CVD) from PPG signals. PPG signals occupy a large amount of memory and, hence, the signals were dimensionally reduced in the initial stage. A total of 41 subjects from the Capno database were analyzed in this study, including 20 CVD cases and 21 normal subjects. PPG signals are sampled at 200 samples per second. Therefore, 144,000 samples per patient are available. Now, a one-second-long PPG signal is considered a segment. There are 720 PPG segments per patient. For a total of 41 subjects, 29,520 segments of PPG signals are analyzed in this study. Five dimensionality reduction techniques, such as heuristic- (ABC-PSO, cuckoo clusters, and dragonfly clusters) and transformation-based techniques (Hilbert transform and nonlinear regression) were used in this research. Twelve different classifiers, such as PCA, EM, logistic regression, GMM, BLDC, firefly clusters, harmonic search, detrend fluctuation analysis, PAC Bayesian learning, KNN-PAC Bayesian, softmax discriminant classifier, and detrend with SDC were utilized to detect CVD from dimensionally reduced PPG signals. The performance of the classifiers was assessed based on their metrics, such as accuracy, performance index, error rate, and a good detection rate. The Hilbert transform techniques with the harmonic search classifier outperformed all other classifiers, with an accuracy of 98.31% and a good detection rate of 96.55%.

Modified photoplethysmography signal processing and analysis procedure for obtaining reliable stiffness index reflecting arteriosclerosis severity

Objective.This study aimed to describe a modified photoplethysmography (PPG) signal processing and analysis procedure to obtain a more reliable arterial stiffness index (SI).Approach.Three parameters were used to assess the PPG signal quality without prominent diastolic waves, which are similar to a sinusoidal waveform shape. The first parameter, sinusoidal ratio (S-value), was based on frequency-domain analysis: a higher S-value indicated the presence of PPG pulse wave with unapparent diastolic peak. The second parameter was the time difference between systolic peak-to-diastolic peak and the systolic peak-to-dicrotic notch. The third parameter was the percentage of sin-like waveform in the PPG signals. The applicability of these parameters was demonstrated in 40 participants, including 11 with apparent diastolic peaks in the PPG signals and 29 with unapparent diastolic peaks.Main results.An S-value of >3.5 indicated apparent diastolic peaks in the PPG signals. In addition, a systolic peak-to-diastolic peak time difference >80% and a sin-like waveform >55% may be associated with severity of vascular aging.Significance.These parameters successfully detected low-quality PPG signals with unapparent diastolic waveform before SI calculation, thereby ensuring the accuracy of subsequent evaluation of cardiovascular-related disease and clinical risk stratification.

Hypertension Assessment Using Photoplethysmography: A Risk Stratification Approach

Hypertension is a common chronic cardiovascular disease (CVD). Early screening and diagnosis of hypertension plays a major role in its prevention and in the control of CVDs. Our study discusses the early screening of hypertension while using the morphological features of photoplethysmography (PPG). Numerous morphological features of PPG and its derivative waves were defined and extracted. Six types of feature selection methods were chosen to screen and evaluate these PPG morphological features. The optimal features were comprehensively analyzed in relation to the physiological processes of the cardiovascular circulatory system. Particularly, the intrinsic relation and physiological significance between the formation process of systolic blood pressure (SBP) and PPG morphology features were analyzed in depth. A variety of linear and nonlinear classification models were established for the comparison trials. The F1 scores for the normotension versus prehypertension, normotension and prehypertension versus hypertension, and normotension versus hypertension trials were 72.97%, 81.82%, and 92.31%, respectively. In summary, this study established a PPG characteristic analysis model and established the intrinsic relationship between SBP and PPG characteristics. Finally, the risk stratification of hypertension at different stages was examined and compared based on the optimal feature subset.

Assessment of Post-Occlusive Reactive Hyperaemia in the Evaluation of Endothelial Function in Patients with Lower Extremity Artery Disease

Background: The aim was to assess endothelial function with photoplethysmography (PPG), by post-occlusive reactive hyperaemia (PORH) combined with alprostadil challenge test in patients with peripheral artery disease (PAD).

Methods: Forty-nine PAD patients stage II-III Fontaine (39 male, 10 female, mean age 68.45±5.86 years) and a control group of 49 healthy individuals (24 male, 25 female; mean age 25.1±3.8 for a young subgroup; 71.0±0.16 years for an elderly subgroup) were included. Ankle-brachial index (ABI) was assessed at baseline, peripheral perfusion (PP) and PORH were assessed at baseline and after the 30 minutes administration of parenteral alprostadil.

Results: After 3 minutes of arterial occlusion, peripheral perfusion increased from 0.69±0.94 mV/V to 2.27±2.42 mV/V (p<0.0001). After alprostadil challenge, peripheral perfusion increased from 0.84±1.24 mV/V to 4.52±3.52 mV/V (p<0.0001). In controls PP was 2.4±1.7 mV/V versus 3.8±1.5 mV/V, p<0.0001.

Conclusion: In patients with PAD, an increase in PORH after alprostadil challenge due to the release of nitric oxide (NO), provides information on the endothelial function and could reflect the presence of collaterals. In the healthy control group, the increase in PORH could reflect the integrity of main arterial branch. In PAD patients with an increase in PORH, conservative therapy should be preferred over surgical revascularisation.