Sexual dimorphism in aortic architecture and its segmental abdominal influence using neural networks
Keywords:
aorta; sex characteristics; anatomy; cross-sectional studies; neural networks; machine learningAbstract
Introduction: Sex-related anatomical differences in the aorta, modeled using neural networks, can reveal distinct morphological and functional patterns
Objective: To analyze, by sex, the influence of thoracic aortic segments on abdominal aortic diameter using a multilayer perceptron neural network.
Methods: This observational, cross-sectional, and analytical study used secondary data from 801 patients who underwent non-contrast thoracic computed tomography. Aortic diameters were measured at eight thoracic segments and the abdominal aorta, segmented using deep-learning-based artificial intelligence algorithms. Separate multilayer perceptron neural network models were developed for men and women. Model performance was assessed using mean squared error (MSE) and relative importance analysis of each aortic segment, with k-fold cross-validation.
Results: The neural network models included a single hidden layer with 5 neurons for men (n=559) and 8 neurons for women (n=242). Model performance was superior in women, with lower MSE in training (26.17 vs. 66.88) and testing (13.13 vs. 29.76), as well as lower relative error during training (0.301 vs. 0.348). In both sexes, the aortic segment at the diaphragm showed the highest normalized importance (100%). In men, the next most influential segments were the mid-descending aorta (59.1%) and the ascending aorta (28.2%). In women, the proximal aortic arch (27.6%) and the sinotubular junction (11.1%) exhibited the greatest secondary relevance.
Conclusions: The segmental contribution to predicting abdominal aortic diameter differs by sex, reinforcing the presence of sex-specific functional and structural vascular dimorphism, as revealed by artificial neural networks.
Downloads
References
1. Zaid M, Sala L, Despins L, et al. Cardiovascular sex-differences: insights via physiology-based modeling and potential for noninvasive sensing via ballistocardiography. Front Cardiovasc Med. 2023;10:1215958. DOI: 10.3389/fcvm.2023.1215958.
2. Marques-Antunes M, van Oort MJH, Oliveri F, et al. Angiographic characterization and sex-related anatomical differences of atrial coronary arteries anatomy-A proposal of systematic classification. Catheter Cardiovasc Interv. 2025;105(4):951-8. DOI: 10.1002/ccd.31414.
3. Gao Z, Xiong J, Chen Z, et al. Gender differences of morphological and hemodynamic characteristics of abdominal aortic aneurysm. Biol Sex Differ. 2020;11(1):41. DOI: 10.1186/s13293-020-00318-3.
4. Zuo X, Liu L, Liu K, et al. Proximal aorta dilatation in hypertension. J Hypertens. 2023;41(10):1511-20. DOI: 10.1097/HJH.0000000000003518.
5. Rylski B, Desjardins B, Moser W, et al. Gender-related changes in aortic geometry throughout life. Eur J Cardiothorac Surg. 2014;45(5):805-11. DOI: 10.1093/ejcts/ezt597.
6. Bhatt N, Chung JC-Y. Gender differences in acute aortic syndromes. Curr Opin Cardiol. 2023;38(2):75-81. DOI: 10.1097/HCO.0000000000001012.
7. Voigt KR, Gökalp AL, Papageorgiou G, et al. Male-female differences in ascending aortic aneurysm surgery: 25-year single center results. Semin Thorac Cardiovasc Surg. 2023;35(2):300-8. DOI: 10.1053/j.semtcvs.2022.01.002.
8. García-Ortiz L, Recio-Rodríguez JI, Mora-Simón S, et al. Vascular structure and function and their relationship with health-related quality of life in the MARK study. BMC Cardiovasc Disord. 2016;16(1):95. DOI: 10.1186/s12872-016-0272-9.
9. Shirazi DH, Toosi H. Deep multilayer perceptron neural network for the prediction of Iranian dam project delay risks. J Constr Eng Manag. 2023;149(4). DOI: 10.1061/jcemd4.coeng-12367.
10. Wang Y, Yang J, Lu Y, et al. Thoracic aorta diameter calculation by artificial intelligence can predict the degree of arterial stiffness. Front Cardiovasc Med. 2021;8:737161. DOI: 10.3389/fcvm.2021.737161.
11. Aghaabbasi M, Chalermpong S. Machine learning techniques for evaluating the nonlinear link between built-environment characteristics and travel behaviors: A systematic review. Travel Behav Soc. 2023;33:100640. DOI: 10.1016/j.tbs.2023.100640.
12. Vatner SF, Zhang J, Vyzas C, et al. Vascular stiffness in aging and disease. Front Physiol. 2021;12:762437. DOI: 10.3389/fphys.2021.762437.
13. Wanhainen A, Themudo R, Ahlström H, et al. Thoracic and abdominal aortic dimension in 70-year-old men and women--a population-based whole-body magnetic resonance imaging (MRI) study. J Vasc Surg. 2008;47(3):504-12. DOI: 10.1016/j.jvs.2007.10.043.
14. Lau ES, Panah LG, Zern EK, et al. Arterial stiffness and vascular load in HFpEF: Differences among women and men. J Card Fail. 2022;28(2):202-11. DOI: 10.1016/j.cardfail.2021.10.019.
15. Carlestål E, Thorell A, Bergstrand L, et al. High prevalence of thoracic aortic dilatation in men with previous inguinal hernia repair. Aorta (Stamford). 2022;10(3):122-30. DOI: 10.1055/s-0042-1749172.
16. Obel LM, Diederichsen AC, Steffensen FH, et al. Population-based risk factors for ascending, arch, descending, and abdominal aortic dilations for 60-74-year-old individuals. J Am Coll Cardiol. 2021;78(3):201-11. DOI: 10.1016/j.jacc.2021.04.094.
17. Neutel CHG, Corradin G, Puylaert P, et al. High Pulsatile Load Decreases Arterial Stiffness: An ex vivo Study. Front Physiol. 2021;12:741346. DOI: 10.3389/fphys.2021.741346.
18. Bellemare F, Jeanneret A, Couture J. Sex differences in thoracic dimensions and configuration. Am J Respir Crit Care Med. 2003;168(3):305-12. DOI: 10.1164/rccm.200208-876OC.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Alberto Guevara-Tirado
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All content published in this journal is Open Access, distributed under the terms of the CC BY-NC 4.0 License.
It allows:
- Copy and redistribute published material in any medium or format.
- Adapt the content.
This will be done under the following terms:
- Attribute the authors' credits and indicate whether changes were made, in which case it must be in a reasonable way.
- Non-commercial use.
- Recognize the journal where it is published.
The copyrights of each article are maintained, without restrictions.
