Photoplethysmography-Based Technologies for Cardiovascular Disease Detection: Challenges and Opportunities

Photoplethysmography-Based Technologies for Cardiovascular Disease Detection: Challenges and Opportunities

Abedalrahamn Busati^*, Obadah Altabaa, and Osama Hamad

Information Technology Department, University of Fujairah, Fujairah, UAE

*Corresponding Author

DOI: https://doi.org/10.51244/IJRSI.2025.12030060

Received: 20 February 2025; Accepted: 03 March 2025; Published: 11 April 2025

ABSTRACT

Cardiovascular diseases (CVDs) remain the leading cause of death worldwide, underscoring the critical need for early detection and continuous monitoring. Traditional diagnostic methods, such as electrocardiograms (ECGs) and invasive blood pressure monitoring, are highly accurate but often limited by their cost, complexity, and reliance on clinical settings. Enter photoplethysmography (PPG), a groundbreaking, non-invasive, and cost-effective optical technology that is transforming cardiovascular monitoring. PPG works by measuring blood volume changes using light, offering valuable insights into key health metrics like heart rate, blood oxygen saturation, and arterial stiffness. Its simplicity and versatility have made it a cornerstone of wearable devices, such as smartwatches and fitness trackers, enabling continuous health monitoring outside of traditional medical environments. Beyond basic metrics, PPG’s ability to detect subtle changes in arterial pulse waveforms has proven invaluable in identifying conditions like hypertension, atrial fibrillation, and atherosclerosis. Research has further demonstrated its effectiveness in assessing arterial stiffness and early signs of atherosclerosis, particularly in high-risk populations. Despite its promise, PPG is not without challenges. The technology is susceptible to motion artifacts and environmental noise, which can compromise signal accuracy. Fortunately, advancements in signal processing and machine learning, such as wavelet transforms, adaptive filtering, and deep learning have significantly enhanced PPG’s reliability and diagnostic precision. These innovations are paving the way for more robust and accessible cardiovascular monitoring solutions. This paper provides a comprehensive review of PPG’s principles, applications, and challenges in cardiovascular disease detection. We explore its potential for real-world, continuous monitoring and discuss exciting future opportunities, including its integration with telemedicine platforms and multimodal sensing systems. While hurdles remain, PPG’s non-invasive nature, affordability, and compatibility with wearable devices position it as a game-changer in modern cardiovascular care. By enabling earlier detection, better management, and prevention of CVDs, PPG is poised to improve health outcomes for millions of people worldwide.

Keywords: Cardiovascular disease; PPG; Chronic disease; Preventive technique; Health informatics

INTRODUCTION

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, accounting for approximately 17.9 million deaths annually, as reported by the World Health Organization (WHO, 2021). Early detection and continuous monitoring of cardiovascular conditions are critical to reducing morbidity and mortality rates. Traditional diagnostic methods, such as electrocardiograms (ECGs) and invasive blood pressure monitoring, are highly accurate but often require specialized equipment and clinical settings, limiting their accessibility and scalability. In recent years, Photoplethysmography (PPG) has emerged as a promising non-invasive, cost-effective, and wearable technology for cardiovascular monitoring. PPG is an optical technique that measures blood volume changes in the microvascular bed of tissue, typically using a light source and a photodetector. The PPG waveform contains valuable physiological information, including heart rate, blood oxygen saturation (SpO2), and arterial stiffness, making it a versatile tool for assessing cardiovascular health (Allen, 2007). The widespread adoption of PPG in consumer devices, such as smartwatches and fitness trackers, has further highlighted its potential for continuous health monitoring outside clinical environments. The application of PPG in cardiovascular disease detection has gained significant attention due to its ability to capture subtle changes in the arterial pulse waveform, which can indicate underlying conditions such as hypertension, atrial fibrillation, and atherosclerosis (Elgendi et al., 2019). For instance, Qawqzeh et al. (2010) demonstrated the utility of PPG contour analysis in assessing arterial stiffness and early atherosclerosis, particularly in subjects with erectile dysfunction (ED). Their study highlighted the association between PPG morphological changes and age, emphasizing the role of PPG in detecting age-related vascular alterations. Such findings underscore the potential of PPG as a diagnostic tool for early cardiovascular risk assessment. Further research by Qawqzeh et al. (2010) explored the relationship between PPG morphology and carotid intima-media thickness (CIMT), a marker of atherosclerosis, in ED patients. They calculated nine PPG indices and found significant correlations between PPG parameters and CIMT, suggesting that PPG can supplement existing methods for analyzing arterial conditions. Similarly, Qawqzeh (2012) investigated the use of the second derivative of PPG (b/a ratio) as a measure of atherosclerosis risk. Their logistic regression model, incorporating pulse pressure (PP), b/a index, and subject height, demonstrated promising sensitivity and specificity in predicting high-risk atherosclerosis. These studies collectively highlight the potential of PPG as a non-invasive tool for assessing arterial health and detecting early signs of cardiovascular disease. Despite its advantages, PPG signals are susceptible to motion artifacts and environmental noise, posing challenges for accurate interpretation. Advances in signal processing and machine learning have enabled researchers to extract more reliable features from PPG waveforms, enhancing its diagnostic capabilities. This review paper aims to provide a comprehensive overview of the current state of PPG technology in cardiovascular disease detection. We will explore the underlying principles of PPG, its applications in diagnosing various cardiovascular conditions, and the challenges associated with its use. Additionally, we will discuss recent advancements in signal processing techniques and their impact on improving the accuracy and reliability of PPG-based diagnostics.

SURVEY OF PPG IN CARDIOVASCULAR DISEASE DETECTION

Principles of PPG Technology

Photoplethysmography operates on the principle of measuring light absorption by blood vessels. A typical PPG device consists of a light-emitting diode (LED) that emits light into the skin and a photodetector that captures the reflected or transmitted light. The amount of light absorbed by the blood varies with the cardiac cycle, producing a waveform that reflects changes in blood volume (Allen, 2007). The PPG waveform comprises two main components: the AC component, which corresponds to pulsatile blood flow, and the DC component, which represents non-pulsatile blood volume and tissue absorption. The AC component of the PPG signal is particularly useful for cardiovascular monitoring, as it contains information about the arterial pulse. Key features of the PPG waveform, such as the systolic peak, diastolic peak, and dicrotic notch, can be analyzed to derive physiological parameters like heart rate variability (HRV), pulse wave velocity (PWV), and arterial stiffness (Elgendi et al., 2019). These parameters are critical for assessing cardiovascular health and detecting abnormalities. Figure 1 illustrates the PPG components.

Figure1. PPG waveform and its first and second derivatives.

Applications of PPG in Cardiovascular Disease Detection

Hypertension Detection

Hypertension, or high blood pressure, is a major risk factor for cardiovascular diseases. PPG-based devices have shown promise in estimating blood pressure non-invasively by analyzing the pulse transit time (PTT) and pulse wave analysis (PWA). PTT is the time taken for the arterial pulse to travel between two points in the arterial tree and is inversely related to blood pressure (Mukkamala et al., 2015). Recent studies have demonstrated the feasibility of using PPG signals to estimate blood pressure with reasonable accuracy, making it a potential tool for continuous hypertension monitoring (Slapničar et al., 2019).

Atrial Fibrillation Detection

Atrial fibrillation (AF) is a common arrhythmia associated with an increased risk of stroke and heart failure. PPG signals can be used to detect AF by analyzing irregularities in the pulse waveform and heart rate variability. Machine learning algorithms have been developed to classify PPG signals as normal or AF with high sensitivity and specificity (Tison et al., 2018). The integration of PPG-based AF detection into wearable devices has the potential to enable early diagnosis and reduce the burden of AF-related complications.

Atherosclerosis and Arterial Stiffness

Atherosclerosis, characterized by the buildup of plaque in the arteries, leads to increased arterial stiffness and reduced blood flow. PPG can assess arterial stiffness by analyzing the shape and timing of the pulse waveform. The augmentation index (AIx), derived from the PPG waveform, is a widely used measure of arterial stiffness (Millasseau et al., 2006). Qawqzeh et al. (2010) conducted a study on 65 subjects with erectile dysfunction (ED) to investigate the relationship between PPG contour and arterial stiffness. Their findings revealed that PPG timing indices, such as the dicrotic notch and inflection point, are significantly influenced by age, with older subjects showing reduced arterial compliance. This study highlights the potential of PPG contour analysis in detecting early atherosclerosis and age-related vascular changes. In another study, Qawqzeh et al. (2010) examined the variation of PPG morphology in ED patients and calculated nine PPG indices alongside carotid intima-media thickness (CIMT). They found significant correlations between PPG parameters and CIMT, suggesting that PPG can supplement existing methods for analyzing arterial conditions. Similarly, Qawqzeh (2012) investigated the use of the second derivative of PPG (b/a ratio) as a measure of atherosclerosis risk. Their logistic regression model, incorporating pulse pressure (PP), b/a index, and subject height, demonstrated promising sensitivity and specificity in predicting high-risk atherosclerosis. These studies collectively highlight the potential of PPG as a non-invasive tool for assessing arterial health and detecting early signs of cardiovascular disease.

Aging and PPG Morphology

Aging significantly affects the morphology of PPG signals, as demonstrated by Qawqzeh et al. (2011). Their study investigated the effect of aging on PPG signals and the reflection index (RI), a measure of arterial stiffness. The results showed that PPG signals become more rounded with age, leading to the disappearance of the inflection point and dicrotic notch. The study concluded that RI could serve as a measure of small and medium artery stiffness, enabling early detection of atherosclerosis in subclinical settings. These findings underscore the importance of considering age-related changes when interpreting PPG signals for cardiovascular risk assessment.

Heart Failure Monitoring

Heart failure is a chronic condition that requires continuous monitoring to prevent exacerbations. PPG signals can provide insights into cardiac function by measuring parameters such as stroke volume and cardiac output. Researchers have explored the use of PPG in conjunction with other sensors, such as accelerometers, to monitor heart failure patients remotely (Ponikowski et al., 2016). These advancements have the potential to improve patient outcomes and reduce hospital readmissions.

Challenges and Limitations

Despite its potential, PPG technology faces several challenges that limit its widespread adoption in clinical practice. Motion artifacts, caused by patient movement, can distort the PPG signal and reduce its accuracy. Environmental factors, such as ambient light and skin pigmentation, can also affect signal quality (Tamura et al., 2014). Additionally, the interpretation of PPG waveforms requires advanced signal processing techniques, which may not be readily available in all healthcare settings.

Advances in Signal Processing and Machine Learning

Recent advancements in signal processing and machine learning have addressed many of the limitations associated with PPG technology. Techniques such as wavelet transform, adaptive filtering, and deep learning have been employed to enhance signal quality and extract meaningful features from PPG waveforms (Charlton et al., 2022). For example, convolutional neural networks (CNNs) have been used to classify PPG signals for arrhythmia detection with high accuracy (Rajan et al., 2021; Qawqzeh et al., 2023). These innovations have significantly improved the reliability and diagnostic capabilities of PPG-based systems.

DISCUSSIONS

The use of Photoplethysmography (PPG) in cardiovascular disease (CVD) prevention and detection represents a transformative shift in healthcare, offering a non-invasive, cost-effective, and accessible alternative to traditional diagnostic methods. The studies reviewed in this paper highlight the immense potential of PPG in assessing arterial health, detecting early signs of atherosclerosis, and monitoring cardiovascular conditions such as hypertension, atrial fibrillation, and heart failure. However, while PPG technology has made significant strides, several challenges and opportunities must be addressed to fully realize its potential in clinical practice.

PPG as a Tool for Early Detection and Prevention

One of the most promising applications of PPG is its ability to detect early signs of cardiovascular abnormalities, particularly in asymptomatic individuals. The work by Qawqzeh et al. (2010, 2012) demonstrates the utility of PPG in assessing arterial stiffness and atherosclerosis risk, particularly in high-risk populations such as patients with erectile dysfunction (ED). By analyzing PPG waveform features such as the dicrotic notch, inflection point, and second derivative (b/a ratio), researchers have been able to correlate PPG-derived indices with established markers of atherosclerosis, such as carotid intima-media thickness (CIMT). These findings suggest that PPG could serve as a screening tool for early detection of subclinical atherosclerosis, enabling timely interventions to prevent disease progression. Moreover, the integration of PPG into wearable devices offers unprecedented opportunities for continuous monitoring of cardiovascular health. For instance, the ability to estimate blood pressure non-invasively using pulse transit time (PTT) and pulse wave analysis (PWA) could revolutionize hypertension management, allowing patients to monitor their blood pressure in real-time without the need for cumbersome cuffs or clinical visits (Mukkamala et al., 2015). Similarly, the use of PPG for detecting atrial fibrillation (AF) in wearable devices has shown promising results, with machine learning algorithms achieving high sensitivity and specificity in classifying PPG signals (Tison et al., 2018). These advancements underscore the potential of PPG as a preventive tool, enabling early diagnosis and reducing the burden of CVD-related complications.

Challenges in PPG Signal Interpretation

Despite its advantages, PPG technology faces several challenges that must be addressed to improve its accuracy and reliability. One of the primary limitations is the susceptibility of PPG signals to motion artifacts and environmental noise, which can distort the waveform and lead to erroneous interpretations (Tamura et al., 2014; Otoom et al., 2019). For example, physical activity, ambient light, and skin pigmentation can significantly affect the quality of PPG signals, limiting their utility in real-world settings. Advanced signal processing techniques, such as adaptive filtering and wavelet transform, have been employed to mitigate these issues, but further research is needed to develop robust algorithms that can reliably extract meaningful features from noisy PPG data. Another challenge lies in the interpretation of PPG waveforms, particularly in populations with varying physiological characteristics. For instance, the study by Qawqzeh et al. (2011) highlights the significant impact of aging on PPG morphology, with older individuals showing more rounded waveforms and diminished inflection points. These age-related changes must be accounted for when interpreting PPG signals, as they can affect the accuracy of derived indices such as the reflection index (RI) and augmentation index (AIx). Developing age-specific reference ranges and algorithms could improve the diagnostic accuracy of PPG in diverse populations.

Integration with Machine Learning and Artificial Intelligence

The integration of machine learning (ML) and artificial intelligence (AI) into PPG analysis has opened new avenues for improving the diagnostic capabilities of this technology. ML algorithms, such as convolutional neural networks (CNNs) and support vector machines (SVMs), have been used to classify PPG signals for arrhythmia detection, blood pressure estimation, and atherosclerosis risk prediction with high accuracy (Rajan et al., 2021; Qawqzeh, 2012). These algorithms can analyze complex patterns in PPG waveforms that may not be discernible to the human eye, enabling more precise and personalized diagnostics. However, the development of ML-based PPG systems requires large, high-quality datasets for training and validation. The lack of standardized protocols for PPG signal acquisition and annotation poses a significant barrier to the development of robust models. Collaborative efforts between researchers, clinicians, and industry stakeholders are needed to establish standardized datasets and benchmarks, ensuring the generalizability and reproducibility of ML-based PPG systems.

Future Directions and Opportunities

The future of PPG in CVD prevention and detection lies in its integration with other sensing modalities and healthcare technologies. For example, combining PPG with electrocardiography (ECG), accelerometry, and bioimpedance could provide a more comprehensive assessment of cardiovascular health, enabling the detection of complex conditions such as heart failure and coronary artery disease (Charlton et al., 2022). Additionally, the integration of PPG into telemedicine platforms could facilitate remote monitoring of high-risk patients, reducing the need for frequent clinical visits and improving access to care in underserved areas. Another promising direction is the development of personalized PPG-based risk prediction models. By incorporating demographic, clinical, and lifestyle data, these models could provide individualized risk assessments and tailored interventions, enhancing the effectiveness of preventive care. For instance, the logistic regression model developed by Qawqzeh (2012), which incorporates pulse pressure (PP), b/a index, and subject height, demonstrates the potential of PPG-based models in predicting high-risk atherosclerosis. Expanding such models to include additional variables, such as genetic markers and environmental factors, could further improve their predictive accuracy.

Integration with Telemedicine and Remote Monitoring

The integration of PPG technology with telemedicine platforms represents a significant advancement in remote patient monitoring. Telemedicine has gained traction, especially in the wake of the COVID-19 pandemic, as a means to provide healthcare services to patients without the need for physical visits to clinics. PPG-based wearable devices can continuously monitor cardiovascular parameters such as heart rate, blood oxygen saturation, and blood pressure, transmitting this data in real-time to healthcare providers. This capability is particularly beneficial for managing chronic conditions like hypertension, atrial fibrillation, and heart failure, where continuous monitoring can lead to early detection of exacerbations and timely interventions. For instance, patients with heart failure can use PPG-enabled wearable devices to monitor their cardiac function remotely. Data collected from these devices can be analyzed using machine learning algorithms to detect early signs of decompensation, prompting healthcare providers to adjust treatment plans proactively. This approach not only improves patient outcomes but also reduces the frequency of hospital readmissions, thereby lowering healthcare costs. Moreover, the integration of PPG with telemedicine can enhance access to cardiovascular care in underserved and rural areas. Patients in these regions often face barriers to accessing specialized healthcare services due to geographical and logistical challenges. PPG-based remote monitoring can bridge this gap by enabling healthcare providers to monitor patients’ cardiovascular health from a distance, ensuring timely and effective care.

Ethical and Regulatory Considerations

As PPG technology becomes more integrated into clinical practice and consumer devices, several ethical and regulatory considerations must be addressed. One of the primary concerns is data privacy and security. PPG devices collect sensitive health data, which, if compromised, could lead to privacy violations and misuse of personal information. Ensuring robust data encryption and secure transmission protocols is essential to protect patient data. Another ethical consideration is the potential for health disparities. While PPG-based wearable devices offer significant benefits, they may not be equally accessible to all populations. Socioeconomic factors, such as the cost of devices and access to technology, can create disparities in who benefits from these advancements. Policymakers and healthcare providers must work towards making PPG technology affordable and accessible to diverse populations to ensure equitable health outcomes. Regulatory frameworks also need to evolve to keep pace with the rapid advancements in PPG technology. Regulatory bodies must establish guidelines for the validation and approval of PPG-based devices and algorithms to ensure their safety and efficacy. This includes setting standards for data accuracy, device reliability, and clinical validation. Collaborative efforts between regulatory agencies, researchers, and industry stakeholders are crucial to developing a regulatory environment that fosters innovation while protecting public health. To further contextualize the advantages of PPG technology and its potential to address these ethical and regulatory challenges, Table 1 provides a detailed comparison of PPG with traditional diagnostic methods, such as electrocardiograms (ECGs) and invasive blood pressure monitoring. This comparison highlights the cost-effectiveness, accessibility, and ease of use of PPG, underscoring its potential to democratize cardiovascular health monitoring and reduce disparities in healthcare access.

Table 1. Comparison of PPG with Traditional Methods

CONCLUSIONS

Photoplethysmography (PPG) technology represents a transformative advancement in the field of cardiovascular disease (CVD) prevention and detection. Its non-invasive nature, cost-effectiveness, and compatibility with wearable devices make it a powerful tool for continuous health monitoring and early diagnosis. The studies reviewed in this paper underscore the immense potential of PPG in assessing arterial health, detecting early signs of atherosclerosis, and monitoring critical cardiovascular conditions such as hypertension, atrial fibrillation, and heart failure. By leveraging the rich physiological information embedded in PPG waveforms, researchers and clinicians can identify subtle changes in cardiovascular function, enabling timely interventions that can significantly reduce morbidity and mortality rates (Allen, 2007; Elgendi et al., 2019). However, the widespread adoption of PPG in clinical practice is not without challenges. The susceptibility of PPG signals to motion artifacts, environmental noise, and variations in skin pigmentation poses significant hurdles to accurate signal interpretation (Tamura et al., 2014). These limitations necessitate the development of robust signal processing techniques and machine learning algorithms capable of extracting reliable features from noisy data. Advances in adaptive filtering, wavelet transforms, and deep learning have already demonstrated promising results in enhancing the diagnostic capabilities of PPG-based systems (Charlton et al., 2022; Rajan et al., 2021). Yet, further research is needed to refine these techniques and ensure their applicability across diverse populations and real-world settings. The integration of PPG with other sensing modalities, such as electrocardiography (ECG), accelerometry, and bioimpedance, offers exciting opportunities for a more comprehensive assessment of cardiovascular health. Multimodal sensing can provide a holistic view of a patient’s condition, enabling the detection of complex cardiovascular abnormalities that may not be discernible through PPG alone (Charlton et al., 2022). Additionally, the integration of PPG into telemedicine platforms has the potential to revolutionize remote patient monitoring, particularly for individuals with chronic conditions or those living in underserved areas. By enabling real-time data transmission and analysis, PPG-based telemedicine can facilitate proactive healthcare interventions, reducing the need for frequent clinical visits and improving access to care (Ponikowski et al., 2016).

Ethical and regulatory considerations also play a critical role in the future of PPG technology. Ensuring data privacy and security is paramount, given the sensitive nature of the health data collected by PPG devices. Policymakers and industry stakeholders must collaborate to establish robust regulatory frameworks that ensure the safety, efficacy, and reliability of PPG-based devices and algorithms. Furthermore, efforts must be made to address potential health disparities by making PPG technology affordable and accessible to diverse populations, thereby promoting equitable health outcomes (Tison et al., 2018). Looking ahead, the future of PPG lies in its ability to deliver personalized and preventive healthcare. By incorporating demographic, clinical, and lifestyle data into PPG-based risk prediction models, healthcare providers can offer individualized risk assessments and tailored interventions. These models, enhanced by machine learning and artificial intelligence, have the potential to predict cardiovascular risks with unprecedented accuracy, enabling early interventions that can prevent disease progression (Qawqzeh, 2012; Rajan et al., 2021). In conclusion, PPG technology is poised to become a cornerstone of modern cardiovascular care. Its ability to provide continuous, non-invasive monitoring outside clinical settings makes it an invaluable tool for early detection and prevention of cardiovascular diseases. While challenges related to signal quality, interpretation, and standardization remain, ongoing advancements in signal processing, machine learning, and multimodal sensing offer promising solutions. As research in this field continues to evolve, PPG has the potential to significantly reduce the global burden of cardiovascular diseases, improving health outcomes and quality of life for millions of individuals worldwide. Collaborative efforts between researchers, clinicians, industry stakeholders, and policymakers will be essential to fully realize the transformative potential of PPG in cardiovascular healthcare.

Competing of Interest

Authors declare no competing interest

REFERENCES

1. Allen, J. (2007). Photoplethysmography and its application in clinical physiological measurement. Physiological Measurement, 28(3), R1–R39. https://doi.org/10.1088/0967-3334/28/3/R01
2. Bayoumy, K., Gaber, M., Elshafeey, A., Mhaimeed, O., Dineen, E. H., Marvel, F. A., … & Elshazly, M. B. (2021). Smart wearable devices in cardiovascular care: Where we are and how to move forward. Nature Reviews Cardiology, 18(8), 581–599. https://doi.org/10.1038/s41569-021-00522-7
3. Charlton, P. H., Bonnici, T., Tarassenko, L., Clifton, D. A., Beale, R., & Watkinson, P. J. (2022). An assessment of algorithms to estimate respiratory rate from the electrocardiogram and photoplethysmogram. Physiological Measurement, 43(2), 025001. https://doi.org/10.1088/1361-6579/ac4b9a
4. Elgendi, M., Norton, I., Brearley, M., Abbott, D., & Schuurmans, D. (2019). Detection of atrial fibrillation using a PPG signal. Frontiers in Physiology, 10, 927. https://doi.org/10.3389/fphys.2019.00927
5. Elgendi, M., Haugg, F., Fletcher, R. R., Allen, J., Shin, H., Alian, A., & Menon, C. (2024). Recommendations for evaluating photoplethysmography-based algorithms for blood pressure assessment. Communications Medicine, 4(1), 140. https://doi.org/10.1038/s43856-024-00555-2
6. Fahoum, A. A., Al Omari, A., Al Omari, G., & Zyout, A. (2024). Development of a novel light-sensitive PPG model using PPG scalograms and PPG-NET learning for non-invasive hypertension monitoring. Heliyon, 10(21), e39745. https://doi.org/10.1016/j.heliyon.2024.e39745
7. Karapinar, E., & Sevinc, E. (2024). A non-invasive heart rate prediction method using a convolutional approach. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-024-03217-6
8. Lan, E. (2023, January). Performer: A novel PPG-to-ECG reconstruction transformer for a digital biomarker of cardiovascular disease detection. In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)(pp. 1990–1998). IEEE. https://doi.org/10.1109/WACV56688.2023.00203
9. Millasseau, S. C., Kelly, R. P., Ritter, J. M., & Chowienczyk, P. J. (2006). Determination of age-related increases in large artery stiffness by digital pulse contour analysis. Clinical Science, 103(4), 371–377. https://doi.org/10.1042/CS20060041
10. Mukkamala, R., Hahn, J. O., Inan, O. T., Mestha, L. K., Kim, C. S., Töreyin, H., & Kyal, S. (2015). Toward ubiquitous blood pressure monitoring via pulse transit time: Theory and practice. IEEE Transactions on Biomedical Engineering, 62(8), 1879–1901. https://doi.org/10.1109/TBME.2015.2441951
11. Pal, P., & Mahadevappa, M. (2024). Meta-learning based cardiopathy detection from PPG signals using GAN and 1D CNN. Circuits, Systems, and Signal Processing. https://doi.org/10.1007/s00034-024-02941-6
12. Panda, A., Anand, A., Pinisetty, S., & Roop, P. (2024). An explainable and formal framework for hypertension monitoring using ECG and PPG. IEEE Embedded Systems Letters, 16(4), 405–408. https://doi.org/10.1109/LES.2024.3443449
13. Ponikowski, P., Voors, A. A., Anker, S. D., Bueno, H., Cleland, J. G. F., Coats, A. J. S., … & van der Meer, P. (2016). 2016 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure. European Heart Journal, 37(27), 2129–2200. https://doi.org/10.1093/eurheartj/ehw128
14. Qawqzeh, Y. K., Reaz, M. B. I., & Ali, M. A. M. (2010). The analysis of PPG contour in the assessment of atherosclerosis for erectile dysfunction subjects. WSEAS Transactions on Biology and Biomedicine, 7(4), 306–315.
15. Qawqzeh, Y. K., Mohd, A. M. A., Reaz, M. B. I., & Maskon, O. (2010, May). Photoplethysmography analysis of artery properties in patients presenting with established erectile dysfunction. In 2010 2nd International Conference on Electronic Computer Technology(pp. 165–168). IEEE. https://doi.org/10.1109/ICECTECH.2010.5480006
16. Qawqzeh, Y. (2012). Assessment of atherosclerosis in erectile dysfunction subjects using second derivative of photoplethysmogram. Scientific Research Essays, 7(3), 340–348.
17. Qawqzeh, Y. K., Reaz, M. B. I., Maskon, O., Chellappan, K., & Ali, M. A. M. (2011). Photoplethysmogram reflection index and aging. In International Conference on Graphic and Image Processing (ICGIP 2011)(Vol. 8285, p. 82852R). SPIE. https://doi.org/10.1117/12.913587
18. Sadek, T., Ahmad, J., Khoury, F., Badawe, H., & Khraiche, M. (2023, December). Detecting cardiovascular disease from PPG signals using machine learning. In 2023 IEEE 4th International Multidisciplinary Conference on Engineering Technology (IMCET)(pp. 203–208). IEEE. https://doi.org/10.1109/IMCET59736.2023.10368256
19. Sahoo, R. R., Ghosh, S., Mani, S., & Kundu, P. K. (2024). Prediction of ECG fiducial parameters from PPG signals for the analysis of cardiovascular diseases: A novel Gaussian process regression-based approach. Biomedical Signal Processing and Control, 90, 105838. https://doi.org/10.1016/j.bspc.2023.105838
20. Otoom, M. M., Jemmali, M., Qawqzeh, Y., SA, K. N., & Al Fay, F. (2019). Comparative analysis of different machine learning models for estimating the population growth rate in data-limited area. International Journal of Computer Science and Network Security (IJCSNS), 19(12), 96.
21. Sanches, I., Gomes, V. V., Caetano, C., & Gamboa, H. (2024). MIMIC-BP: A curated dataset for blood pressure estimation. Scientific Data, 11(1), 1233. https://doi.org/10.1038/s41597-024-04041-1
22. Saranya, K., Karthikeyan, U., Kumar, A. S., & Rajesh, M. (2025). DenseNet-ABiLSTM: Revolutionizing multiclass arrhythmia detection and classification using hybrid deep learning approach leveraging PPG signals. International Journal of Computational Intelligence Systems, 18(1), 33. https://doi.org/10.1007/s44196-025-00765-z
23. Sivasubramaniam, S., & Balamurugan, S. P. (2024). Early detection and prediction of heart disease using wearable devices and deep learning algorithms. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-024-19127-6
24. Slapničar, G., Mlakar, N., & Luštrek, M. (2019). Blood pressure estimation from photoplethysmogram using a spectro-temporal deep neural network. Sensors, 19(15), 3420. https://doi.org/10.3390/s19153420
25. Tang, H., Ma, G., Qiu, L., & Zhang, Y. (2024). Blood pressure estimation based on PPG and ECG signals using knowledge distillation. Cardiovascular Engineering and Technology, 15(1), 39–51. https://doi.org/10.1007/s13239-023-00695-x
26. Tamura, T., Maeda, Y., Sekine, M., & Yoshida, M. (2014). Wearable photoplethysmographic sensors—past and present. Electronics, 3(2), 282–302. https://doi.org/10.3390/electronics3020282
27. Tison, G. H., Sanchez, J. M., Ballinger, B., Singh, A., Olgin, J. E., Pletcher, M. J., … & Marcus, G. M. (2018). Passive detection of atrial fibrillation using a commercially available smartwatch. JAMA Cardiology, 3(5), 409–416. https://doi.org/10.1001/jamacardio.2018.0136
28. Wang, M., & Ji, X. (2024, March). Design of deep learning-based PPG blood pressure prediction model. In 2024 5th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE)(pp. 414–418). IEEE. https://doi.org/10.1109/ICBASE63199.2024.10762662
29. World Health Organization. (2021). Cardiovascular diseases (CVDs). Retrieved from https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)
30. Qawqzeh, Y.K., Alourani, A., Ghwanmeh, S (2023). An improved breast cancer classification method using an enhanced AdaBoost classifier. Int. J. Adv. Comput. Sci, 14, 473–478.
31. Xu, H., Zhao, Z., Wang, H., Zhou, L., Wang, J., Ji, J., & Zhang, S. (2024). Enhanced blood pressure estimation based on PPG and ECG signals. In Proceedings of the 2024 International Conference on Smart Healthcare and Wearable Intelligent Devices (SHWID ’24)(pp. 41–45). Association for Computing Machinery. https://doi.org/10.1145/3703847.3703855