Assessing hemodynamics from the photoplethysmogram to gain insights into vascular age: a review from VascAgeNet.

The photoplethysmogram (PPG) signal is widely measured by clinical and consumer devices, and it is emerging as a potential tool for assessing vascular age. The shape and timing of the PPG pulse wave are both influenced by normal vascular aging, changes in arterial stiffness and blood pressure, and atherosclerosis. This review summarizes research into assessing vascular age from the PPG. Three categories of approaches are described: 1) those which use a single PPG signal (based on pulse wave analysis), 2) those which use multiple PPG signals (such as pulse transit time measurement), and 3) those which use PPG and other signals (such as pulse arrival time measurement). Evidence is then presented on the performance, repeatability and reproducibility, and clinical utility of PPG-derived parameters of vascular age. Finally, the review outlines key directions for future research to realize the full potential of photoplethysmography for assessing vascular age.

Diabetes Detection and Management through Photoplethysmographic and Electrocardiographic Signals Analysis: A Systematic Review.

(1) Background: Diabetes mellitus (DM) is a chronic, metabolic disease characterized by elevated levels of blood glucose. Recently, some studies approached the diabetes care domain through the analysis of the modifications of cardiovascular system parameters. In fact, cardiovascular diseases are the first leading cause of death in diabetic subjects. Thanks to their cost effectiveness and their ease of use, electrocardiographic (ECG) and photoplethysmographic (PPG) signals have recently been used in diabetes detection, blood glucose estimation and diabetes-related complication detection. This review's aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (2) Method: We performed a systematic review based on articles that focus on the use of ECG and PPG signals in diabetes care. The search was focused on keywords related to the topic, such as "Diabetes", "ECG", "PPG", "Machine Learning", etc. This was performed using databases, such as PubMed, Google Scholar, Semantic Scholar and IEEE Xplore. This review's aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (3) Results: A total of 78 studies were included. The majority of the selected studies focused on blood glucose estimation (41) and diabetes detection (31). Only 7 studies focused on diabetes complications detection. We present these studies by approach: traditional, machine learning and deep learning approaches. (4) Conclusions: ECG and PPG analysis in diabetes care showed to be very promising. Clinical validation and data processing standardization need to be improved in order to employ these techniques in a clinical environment.

Risk assessment of diabetic retinopathy with machine and deep learning models with PPG signals and PWV.

Retinopathy is one of the most common micro vascular impairments in diabetic subjects. Elevated blood glucose leads to capillary occlusion, provoking the uncontrolled increase in local growth of new vessels in the retina. When left untreated, it can lead to blindness. Traditional approaches for retinopathy detection require expensive devices and high specialized personnel. Being a microvascular complication, the retinopathy could be detected using the photoplethysmography (PPG) technology. In this paper we investigate the predictive value of the pulse wave velocity and PPG signal analysis with machine and deep learning approaches to detect retinopathy in diabetic subjects. PPG signals and pulse wave velocity (PWV) showed promising results in assessing the diabetic retinopathy. The best performances were scored by a LightGBM based model trained over a subset of the available dataset obtaining 80% of specificity and sensitivity.Clinical relevance- PPG based retinopathy detection could make the retinopathy detection more accessible since it does not need neither expensive devices for signal acquisition nor highly specialized personnel to be interpreted.

Clustered photoplethysmogram pulse wave shapes and their associations with clinical data.

Photopletysmography (PPG) is a non-invasive and well known technology that enables the recording of the digital volume pulse (DVP). Although PPG is largely employed in research, several aspects remain unknown. One of these is represented by the lack of information about how many waveform classes best express the variability in shape. In the literature, it is common to classify DVPs into four classes based on the dicrotic notch position. However, when working with real data, labelling waveforms with one of these four classes is no longer straightforward and may be challenging. The correct identification of the DVP shape could enhance the precision and the reliability of the extracted bio markers. In this work we proposed unsupervised machine learning and deep learning approaches to overcome the data labelling limitations. Concretely we performed a K-medoids based clustering that takes as input 1) DVP handcrafted features, 2) similarity matrix computed with the Derivative Dynamic Time Warping and 3) DVP features extracted from a CNN AutoEncoder. All the cited methods have been tested first by imposing four medoids representative of the Dawber classes, and after by automatically searching four clusters. We then searched the optimal number of clusters for each method using silhouette score, the prediction strength and inertia. To validate the proposed approaches we analyse the dissimilarities in the clinical data related to obtained clusters.

Vascular ageing: moving from bench towards bedside.

Prevention of cardiovascular disease (CVD) remains one of the largest public health challenges of our time. Identifying individuals at increased cardiovascular risk at an asymptomatic, sub-clinical stage is of paramount importance for minimizing disease progression as well as the substantial health and economic burden associated with overt CVD. Vascular ageing (VA) involves the deterioration in vascular structure and function over time and ultimately leads to damage in the heart, brain, kidney, and other organs. Vascular ageing encompasses the cumulative effect of all cardiovascular risk factors on the arterial wall over the life course and thus may help identify those at elevated cardiovascular risk, early in disease development. Although the concept of VA is gaining interest clinically, it is seldom measured in routine clinical practice due to lack of consensus on how to characterize VA as physiological vs. pathological and various practical issues. In this state-of-the-art review and as a network of scientists, clinicians, engineers, and industry partners with expertise in VA, we address six questions related to VA in an attempt to increase knowledge among the broader medical community and move the routine measurement of VA a little closer from bench towards bedside.

Assessment of the systolic rise time by photoplethysmography in peripheral arterial diseases: a comparative study with ultrasound Doppler.

Aims: Peripheral arterial disease (PAD) is a major public health burden requiring more intensive population screening. Ankle brachial index (ABI) using arm and ankle cuffs is considered as the reference method for the detection of PAD. Although it requires a rigorous methodology by trained operators, it remains time-consuming and more technically difficult in patients with diabetes due to mediacalcosis. Techniques based on the study of hemodynamic, such as the systolic rise time (SRT), appear promising but need to be validated. We retrospectively compared the reliability and accuracy of SRT using a photoplethysmography (PPG) technique to the SRT measured by ultrasound doppler (UD) in PAD patients diagnosed with the ABI (137 patients, 200 lower limbs). Methods and results: There was a significant correlation between SRT measured with UD (SRTud) compared with that with PPG (SRTppg, r = 0.25; P = 0.001). Best correlation was found in patients without diabetes (r = 0.40; P = 0.001). Bland and Altman analysis showed a good agreement between the SRTud and SRTppg. In contrast, there was no significant correlation between UD and PPG in diabetes patients. Furthermore, patients with diabetes exhibited a significant increase of SRTppg (P = 0.02) compared with patients without diabates but not with the SRTud (P = 0.18). The SRTppg was significantly linked to the arterial velocity waveforms, the type of arterial lesion but not vascular surgery revascularization technique. Conclusion: This monocentric pilot study shows that SRT measured with the PPG signal reliably correlates with SRT recorded with UD. The PPG is an easy to use technique in the hand of non-expert with a potential interest for general screening of PAD, especially in diabetes patients, due to its ease to use.

Transfer learning of CNN-based signal quality assessment from clinical to non-clinical PPG signals.

Photoplethysmography (PPG) is a non-invasive and cost-efficient optical technique used to assess blood volume variation inside the micro-circulation. PPG technology is widely used in a variety of clinical and non-clinical devices in order to investigate the cardiovascular system. One example of clinical PPG device is the pulse oxymeter, while non-clinical PPG devices include smartphones and smartwatches. Such a wide diffusion of PPG devices generates plenty of different PPG signals that differ from each other. In fact, intrinsic device characteristics strongly influence PPG waveform. In this paper we investigate transfer learning approaches on a Covolutional Neural Network based quality assessment method in order to generalize our model across different PPG devices. Our results show that our model is able to classify accurately signal quality over different PPG datasets while requiring a small amount of data for fine-tuning.Clinical relevance- A precise detection and extraction of high quality PPG segments could enhance significantly the reliability of the medical analysis based on the signal.

Pulse wave velocity is lower in trained than in untrained sickle cell trait carriers.

BACKGROUND: Sickle cell trait (SCT) is a benign condition of sickle cell disease. Nevertheless, previous reports showed that SCT carriers have increased blood viscosity and decreased vascular reactivity compared to non-SCT carrier. The benefit of regular exercise on vascular function has been well documented in the general population but no study focused on the SCT population. PURPOSE: The aim of our study was to compare arterial stiffness and blood viscosity between trained and untrained SCT carriers, as well as a group of untrained non-SCT. METHODS: Arterial stiffness (finger-toe pulse wave velocity) and blood viscosity were evaluated in untrained non-SCT carriers (n = 10), untrained SCT carriers (n = 23) and trained SCT carriers (n = 17) who reported at least 10 hours of physical exercise per week. RESULTS: Untrained SCT carriers had higher pulse wave velocity (p = 0.032) and blood viscosity (p < 0.001) than their trained counterparts. In addition, untrained SCT carriers had higher blood viscosity (p < 0.001) than the untrained non-SCT group. A positive association was noted between blood viscosity and pulse wave velocity in the whole study population. CONCLUSION: Our study suggests that regular exercise may be beneficial for the vascular function of SCT carriers.

Evaluation of arterial stiffness by finger-toe pulse wave velocity: optimization of signal processing and clinical validation.

BACKGROUND: Carotid-femoral pulse wave velocity (PWV) (cf-PWV) is the gold standard for measuring aortic stiffness. Finger-toe PWV (ft-PWV) is a simpler noninvasive method for measuring arterial stiffness. Although the validity of the method has been previously assessed, its accuracy can be improved. ft-PWV is determined on the basis of a patented height chart for the distance and the pulse transit time (PTT) between the finger and the toe pulpar arteries signals (ft-PTT). METHOD: The objective of the first study, performed in 66 patients, was to compare different algorithms (intersecting tangents, maximum of the second derivative, 10% threshold and cross-correlation) for determining the foot of the arterial pulse wave, thus the ft-PTT. The objective of the second study, performed in 101 patients, was to investigate different signal processing chains to improve the concordance of ft-PWV with the gold-standard cf-PWV. Finger-toe PWV (ft-PWV) was calculated using the four algorithms. RESULTS: The best correlations relating ft-PWV and cf-PWV, and relating ft-PTT and carotid-femoral PTT were obtained with the maximum of the second derivative algorithm [PWV: r = 0.56, P < 0.0001, root mean square error (RMSE) = 0.9 m/s; PTT: r = 0.61, P < 0.001, RMSE = 12 ms]. The three other algorithms showed lower correlations. The correlation between ft-PTT and carotid-femoral PTT further improved (r = 0.81, P < 0.0001, RMSE = 5.4 ms) when the maximum of the second derivative algorithm was combined with an optimized signal processing chain. CONCLUSION: Selecting the maximum of the second derivative algorithm for detecting the foot of the pressure waveform, and combining it with an optimized signal processing chain, improved the accuracy of ft-PWV measurement in the current population sample. Thus, it makes ft-PWV very promising for the simple noninvasive determination of aortic stiffness in clinical practice.

Outpatient measurement of arterial stiffness in patients with type 2 diabetes and obesity.

BACKGROUND: Pulse wave velocity (PWV) is a marker of arterial stiffness. The aim of the present study was to compare PWV in patients with type 2 diabetes mellitus (T2DM) or obesity and healthy subjects in an outpatient setting. METHODS: A cross-sectional study was conducted in patients with obesity without T2DM (n = 37), T2DM without obesity (n = 40), T2DM plus obesity (n = 43), and healthy controls (n = 114). Outpatient measurements of the finger-toe PWV (ftPWV) were made. RESULTS: Mean (± SD) ftPWV was higher in men than in women (10.57 ± 5.02 vs 9.14 ± 3.68 m/s, respectively P = 0.006) and was positively correlated with age (r2 = 0.31, P < 0.0001), body mass index (r2 = 0.03, P = 0.01), systolic blood pressure (SBP; r2 = 0.06, P < 0.0001), and right (r2 = 0.03, P = 0.01) and left (r2 = 0.03, P = 0.01) ankle-brachial index (ABI). Age, SBP and ABI remained significantly correlated with ftPWV in the stepwise regression analysis. Mean ftPWV in controls and in patients with obesity, T2DM, and T2DM plus obesity was 8.32 ± 2.68, 9.50 ± 3.38, 11.29 ± 4.34, and 12.36 ± 6.67 m/s, respectively (P < 0.0001). These differences remained significant after adjustments for sex, age, SBP, and ABI (P = 0.008). Although ftPWV was higher in patients with than without macrovascular complications (13.11 ± 6.25 vs 10.40 ± 4.54 m/s, respectively; P = 0.006) in univariate analysis, this was not so in the multivariate-adjusted model. CONCLUSIONS: Outpatient-measured ftPWV was correlated with age, SBP, and ABI. It was higher in patients with T2DM and obesity compared with healthy controls. The highest ftPWV was observed in patients with both T2DM and obesity.

A novel device for measuring arterial stiffness using finger-toe pulse wave velocity: Validation study of the pOpmètre®.

BACKGROUND: The finger-toe pathway could be a good alternative for assessing arterial stiffness conveniently. AIM: To evaluate the accuracy of the pOpmètre®--a new device that measures finger-toe pulse wave velocity (ft-PWV). METHODS: The pOpmètre has two photodiode sensors, positioned on the finger and the toe. Pulse waves are recorded continuously for 20 seconds, and the difference in pulse wave transit time between toe and finger (ft-TT) is calculated. The travelled distance is estimated using subject height. Study 1 compared ft-PWV with carotid-femoral PWV (cf-PWV) obtained by the reference method (SphygmoCor®) in 86 subjects (mean age 53±20 years), including 69 patients with various pathologies and 17 healthy normotensives. Study 2 compared changes in ft-PWV and cf-PWV during a cold pressor test in 10 healthy subjects. Study 3 assessed repeatability in 45 patients. RESULTS: ft-PWV correlated significantly with cf-PWV (R2=0.43; P<0.0001). A better correlation was found in terms of transit time (R2=0.61; P<0.0001). The discrepancy between transit times was related to age. The cold pressor test induced parallel changes in cf-PWV and ft-PWV, with increased aortic stiffness that was reversible during recovery. Intra-session repeatability was very good, with a coefficient of variation of 4.52%. CONCLUSION: The pOpmètre® allows measurement of arterial stiffness in routine clinical practice. The greatest advantages of ft-PWV are simplicity, rapidity, feasibility, acceptability by patients and correct agreement with the reference technique. Further studies are needed to adjust for bias and to validate the pOpmètre in larger populations.

[Arterial stiffness a new risk factor to measure]. / La rigidité artérielle, un nouveau facteur de risque à mesurer.

We revue the epidemiology of cardiovascular disease in the elderly, their relationship to arterial stiffness. The measurement of arterial stiffness is of considerable increasing interest in this early 21 century. This paper is focusing on modeling, in different measurement methods. Several measurement techniques are presented. A review of the bibliography that explain the link between cardiovascular risk factors and arterial stiffness is summarized, as are the relationships between the various risk factors and arterial stiffness. The current role of these measurement methods seems to be time consuming although the European consensus recommends the measure once a year in the management of vascular patients. New techniques for the assessment of the arterial stiffness, more reproducible and easy to use, could ultimately trivialize this measurement, contributing in medical practice to the assessment and the management of the vascular risk.