Deep Learning-Enabled Diagnosis of Abdominal Aortic Aneurysm Using Pulse Volume Recording Waveforms: An In Silico Study
Sensors · 2025
DOI: 10.3390/s25216678 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Sina Masoumi Shahrbabak und 6 weiteren Autor:innen. Beteiligte Einrichtung: Mechanical Engineering, University of Maryland, College Park, MD 20742, USA. Hauptthemen laut MEDLINE: Aortic Aneurysm, Abdominal, Deep Learning. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, National Institutes of Health, University of Maryland Graduate School Faculty-Student Research Award.
Abstract (Originalsprache)
This paper investigates the feasibility of diagnosing abdominal aortic aneurysm (AAA) via deep learning (DL)-enabled analysis of non-invasive arterial pulse waveform signals. We generated arterial blood pressure (BP) and pulse volume recording (PVR) waveform signals across a diverse synthetic patient cohort using a systemic arterial circulation model coupled with a viscoelastic model relating arterial BP to PVR while simulating a range of AAA severity levels. We confirmed the plausibility of the synthetic data by comparing the alterations in the simulated waveform signals due to AAA against previously reported in vivo findings. Then, we developed a convolutional neural network (CNN) with continuous property-adversarial regularization that can estimate AAA severity from brachial and tibial PVR signals. We evaluated the algorithm’s performance in comparison with an identical CNN trained on invasive arterial BP waveform signals. The DL-enabled PVR-based algorithm achieved robust AAA detection across different severity thresholds with area under the ROC curve values >0.89, and showed reasonable accuracy in severity estimation, though slightly lower than its invasive BP counterpart (MAE: 12.6% vs. 10.3%). These findings suggest that DL-enabled analysis of PVR waveform signals offers a non-invasive and cost-effective approach for AAA diagnosis, potentially enabling accessible screening through operator-agnostic and point-of-care technologies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Mechanical Engineering, University of Maryland, College Park, MD 20742, USA.
- ONEPREDICT Inc., Seoul 06160, Republic of Korea.
- Mechanical Engineering, Seoul National University, Seoul 08826, Republic of Korea.
- Department of Internal Medicine, National Yang-Ming University, Taipei 112304, Taiwan.
- Institute of Emergency and Critical Care Medicine, National Yang-Ming University, Taipei 112304, Taiwan.
- Bioengineering and Anesthesiology and Perioperative Medicine, University of Pittsburgh, Pittsburgh, PA 15261, USA.
ORCID-Profile: Sina Masoumi Shahrbabak, Byeng Dong Youn, Hao-Min Cheng, Ramakrishna Mukkamala, Jin-Oh Hahn
Förderung
- NIH HHS
- National Institutes of Health
- University of Maryland Graduate School Faculty-Student Research Award
Zitieren
APA
Masoumi Shahrbabak, S., Youn, B. D., Cheng, H. M., Chen, C. H., Sung, S. H., Mukkamala, R., & Hahn, J. O. (2025). Deep Learning-Enabled Diagnosis of Abdominal Aortic Aneurysm Using Pulse Volume Recording Waveforms: An In Silico Study. Sensors. https://doi.org/10.3390/s25216678
Vancouver
Masoumi Shahrbabak S, Youn BD, Cheng HM, Chen CH, Sung SH, Mukkamala R, et al. Deep Learning-Enabled Diagnosis of Abdominal Aortic Aneurysm Using Pulse Volume Recording Waveforms: An In Silico Study. Sensors. 2025. doi:10.3390/s25216678
BibTeX
@article{MasoumiShahrbabak2025,
author = {Masoumi Shahrbabak, Sina and Youn, Byeng Dong and Cheng, Hao-Min and Chen, Chen-Huan and Sung, Shih-Hsien and Mukkamala, Ramakrishna and Hahn, Jin-Oh},
title = {Deep Learning-Enabled Diagnosis of Abdominal Aortic Aneurysm Using Pulse Volume Recording Waveforms: An In Silico Study},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25216678}
}
EUVIMED