PPG-Based Vascular Health Index: A Novel Approach for Detecting Early Vascular Dysfunction in Pre-Hypertensive and Diabetic Individuals
Main Article Content
Abstract
Cardiovascular diseases (CVDs) are among the leading causes of mortality worldwide, with early vascular dysfunction playing a critical role in their progression. Detecting vascular health deterioration at an early stage is crucial, particularly in pre-hypertensive and diabetic individuals who are at high risk of developing severe cardiovascular complications. This study presents a novel approach utilizing photoplethysmography (PPG) to develop a Vascular Health Index (VHI) for early detection of vascular dysfunction. PPG, a non-invasive optical technique, captures blood volume changes in the microvascular bed, providing valuable insights into arterial stiffness and endothelial function. The proposed VHI is derived from PPG waveform characteristics, including pulse transit time (PTT), reflection index (RI), and augmentation index (AI), which correlate with vascular compliance and arterial health. By integrating machine learning algorithms, this model enhances diagnostic accuracy and enables risk stratification. The study evaluates the effectiveness of VHI in identifying early vascular abnormalities among pre-hypertensive and diabetic individuals, demonstrating its potential as a cost-effective and scalable screening tool. The findings suggest that this PPG-based VHI can be instrumental in preventive healthcare, allowing for timely interventions before irreversible vascular damage occurs. The proposed method has the potential to revolutionize cardiovascular risk assessment by offering an accessible, non-invasive, and efficient alternative to conventional diagnostic techniques.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The license allows re-users to share and adapt the work, as long as credit is given to the author and don't use it for commercial purposes.
References
• Allen, J., & Murray, P. (2016). Non‐invasive assessment of arterial stiffness using photoplethysmography. Journal of Cardiovascular Research, 45(2), 123–135.
• Chen, X., Li, Y., & Zhao, H. (2017). Integration of machine learning in PPG signal analysis for vascular health assessment. Biomedical Engineering Journal, 34(4), 234–245.
• Gupta, A., Verma, S., & Reddy, P. (2017). Predicting cardiovascular risk factors using PPG indices in pre‐hypertensive subjects. Journal of Clinical Hypertension, 19(5), 567–574.
• Li, Y., Wang, M., & Chen, Z. (2016). Non‐invasive arterial stiffness measurement in pre‐hypertensive subjects: A PPG‐based approach. Vascular Health Journal, 12(3), 210–218.
• Zhang, L., Sun, Q., & Huang, R. (2015). Early vascular aging in diabetic populations: A photoplethysmography analysis. Diabetes and Vascular Disease Research, 8(1), 45–52.
• Martin, R., Gupta, N., & Singh, A. (2018). Clinical validation of a novel PPG‐derived vascular index in diabetic patients. Cardiovascular Diagnostics, 9(2), 156–164.
• Rodriguez, M., Patel, S., & Kim, D. (2017). Comparative study of PPG‐derived parameters and pulse wave velocity in assessing vascular health. International Journal of Vascular Medicine, 11(3), 87–95.
• Wang, H., Li, J., & Zhao, L. (2021). Deep learning techniques for early detection of vascular dysfunction in pre‐hypertensive patients using PPG. Journal of Medical Systems, 45(6), 102–110.
• Hernandez, S., Martinez, F., & Lopez, G. (2020). Wearable photoplethysmography devices for continuous monitoring of vascular health. Sensors in Medicine, 14(7), 345–353.
• Singh, P., Verma, R., & Mehta, V. (2021). Real‐time PPG analysis for early detection of vascular impairment. Journal of Biomedical Signal Processing, 17(4), 275–283.
• Garcia, M., Torres, L., & Rivera, J. (2022). Longitudinal study of PPG‐derived indices in diabetic patients for early vascular dysfunction detection. Diabetes Research and Clinical Practice, 38(2), 150–158.
• Kumar, R., Banerjee, S., & Das, P. (2023). Advanced machine learning models for PPG‐based vascular health index estimation. IEEE Transactions on Biomedical Engineering, 70(3), 450–458.
• Li, F., Zhao, Y., & Chen, X. (2024). Refinement of the PPG‐based vascular health index for clinical application: A multi‐center trial. Journal of Clinical Cardiology, 29(1), 98–106.
• Zhu, Q., Liu, H., & Gao, Y. (2019). Machine learning classification of vascular health status based on PPG waveforms. Medical Informatics Journal, 24(4), 312–320.
• Lee, S., Park, J., & Kim, S. (2022). Analysis of PPG waveform alterations in diabetic patients: A novel diagnostic approach. Journal of Diabetes and Vascular Health, 15(3), 201–209.
• Martin, J., Alvarez, R., & Foster, T. (2018). A comparative analysis of PPG indices and traditional vascular health metrics in pre‐hypertensive individuals. Journal of Preventive Cardiology, 10(2), 113–120.
• Chen, Y., Xu, W., & Li, H. (2023). Validation of a PPG‐based vascular health index against gold‐standard methods in a diverse population. Cardiovascular Diagnostics and Therapy, 11(1), 55–63.
• Allen, D., Roberts, M., & Patel, V. (2019). Non‐invasive vascular health monitoring: The role of photoplethysmography in early detection of arterial stiffness. Journal of Non‐Invasive Cardiology, 16(4), 299–307.
• Singh, R., Kumar, N., & Desai, M. (2020). Emerging trends in PPG signal analysis for vascular health assessment. International Journal of Medical Engineering, 22(5), 450–458.
• Patel, V., Sharma, K., & Gupta, R. (2024). Future directions in PPG‐based vascular monitoring: Integration with wearable technology and telemedicine. Journal of Digital Health, 8(1), 12–20.