Predictive Modeling of Endovenous Laser Ablation Treatment Outcome in Varicose Veins

Abstract

Varicose veins afflict a significant portion of adults, with approximately 30% experiencing this condition, which often necessitates medical treatment like endovenous laser ablation (EVLA). EVLA has emerged as a highly effective and minimally invasive treatment. However, despite its efficacy, there is a lack of literature on predictive modeling of EVLA treatment outcomes considering both surgical settings and patient characteristics. In this study, we present a comprehensive analysis employing logistic regression under both maximum likelihood (ML) and Bayesian frameworks, as well as support vector machine (SVM) regression. Our results indicate that Bayesian logistic regression with uniform prior demonstrates superior performance. Furthermore, through repeated random sub-sampling validation, we confirm the robustness of our models in predicting successful EVLA outcomes. These findings provide the potential of machine learning techniques in augmenting predictive capabilities in medical decision-making. Our study contributes to the burgeoning literature on predictive modeling in medical contexts, offering insights into the optimization of EVLA treatment outcomes.

Keywords

• Bayesian logistic regression
• Logistic regression
• Support vector machine
• Endovenous laser ablation
• Varicose veins

References

1. D. Chadwick, B. Arch, A. Wilder-Smith, and N. Paton, "Distinguishing dengue fever from other infections on the basis of simple clinical and laboratory features: Application of logistic regression analysis," Journal of Clinical Virology, vol. 35, no. 2, pp. 147–153, 2006.
2. J. Cheng, A. Randall, and P. Baldi, "Prediction of protein stability changes for single-site mutations using support vector machines," Proteins: Structure, Function, and Bioinformatics, vol. 62, no. 4, pp. 1125–1132, 2006.
3. C. A. Cowpland, A. L. Cleese, and M. S. Whiteley, "Factors affecting optimal linear endovenous energy density for endovenous laser ablation in incompetent lower limb truncal veins–A review of the clinical evidence," Phlebology, vol. 32, no. 5, pp. 299-306, 2017.
4. A. Gelman and D. B. Rubin, "Avoiding model selection in Bayesian social research," Sociological Methodology, vol. 25, pp. 165-173, 1995.
5. T. Lin, L. I. Cervino, X. Tang, N. Vasconcelos, and S. B. Jiang, "Fluoroscopic tumor tracking for image-guided lung cancer radiotherapy," Physics in Medicine and Biology, vol. 54, no. 4, pp. 981–992, 2009.
6. L. Mundy, T. L. Merlin, R. A. Fitridge, and J. E. Hiller, "Systematic review of endovenous laser treatment for varicose veins," British Journal of Surgery, vol. 92, no. 10, pp. 1189–1194, 2005.
7. S. Mordon, B. Wassmer, and J. Zemmouri, "Mathematical modeling of 980-nm and 1320-nm endovenous laser treatment," Lasers in Surgery and Medicine, vol. 39, no. 3, pp. 256–265, 2007.
8. N. Riaz, P. Shanker, R. Wiersma, O. Gudmudsson, W. Mao, B. Widrow, and L. Xing, "Predicting respiratory tumor motion with multi-dimensional adaptive filters and support vector regression," Physics in Medicine and Biology, vol. 54, no. 19, pp. 5735–5748, 2009.

9. S. S. Srivatsa, S. Chung, and V. Sidhu, "The relative roles of power, linear endovenous energy density, and pullback velocity in determining short-term success after endovenous laser ablation of the truncal saphenous veins," Journal of Vascular Surgery: Venous and Lymphatic Disorders, vol. 7, no. 1, pp. 90-97, 2019.
10. T. Verplancke, S. Van Looy, D. Benoit, S. Vansteelandt, P. Depuydt, F. De Turck, and J. Decruyenaere, "Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignancies," BMC Medical Informatics and Decision Making, vol. 8, no. 56, pp. 1–8, 2008.
11. H. Yussuff, N. Mohamad, U. K. Ngah, and A. S. Yahaya, "Breast cancer analysis using logistic regression," IJRRAS, vol. 10, January 2012.
12. X. Zhou, K. Y. Liu, and S. T. Wong, "Cancer classification and prediction using logistic regression with Bayesian gene selection," Journal of Biomedical Informatics, vol. 37, no. 4, pp. 249–259, 2004.