Predicting outcomes following endovascular aortoiliac revascularization using machine learning

Ben Li^#^{1

2

3

4}, Badr Aljabri^#⁵, Derek Beaton⁶, Leen Al-Omran⁷, Mohamad A Hussain⁸, Douglas S Lee^{9

10

11}, Duminda N Wijeysundera^{10

11

12

13}, Ori D Rotstein^{1

3

13

14}, Charles de Mestral^{1

2

10

11

13}, Muhammad Mamdani^{3

4

6

10

11

13

15}, Mohammed Al-Omran^{16

17

18

19

20

21}

Affiliations

¹ Department of Surgery, University of Toronto, Toronto, ON, Canada.
² Division of Vascular Surgery, St. Michael's Hospital, Unity Health Toronto, University of Toronto, Toronto, ON, Canada.
³ Institute of Medical Science, University of Toronto, Toronto, ON, Canada.
⁴ Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, ON, Canada.
⁵ Department of Surgery, King Saud University, Riyadh, Saudi Arabia.
⁶ Data Science & Advanced Analytics, Unity Health Toronto, University of Toronto, Toronto, ON, Canada.
⁷ College of Medicine, Alfaisal University, Riyadh, Saudi Arabia.
⁸ Division of Vascular and Endovascular Surgery and the Center for Surgery and Public Health, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
⁹ Division of Cardiology, Peter Munk Cardiac Centre, University Health Network, Toronto, ON, Canada.
¹⁰ Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, ON, Canada.
¹¹ ICES, University of Toronto, Toronto, ON, Canada.
¹² Department of Anesthesia, St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada.
¹³ Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada.
¹⁴ Division of General Surgery, St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada.
¹⁵ Leslie Dan Faculty of Pharmacy, University of Toronto, Toronto, ON, Canada.
¹⁶ Department of Surgery, University of Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
¹⁷ Division of Vascular Surgery, St. Michael's Hospital, Unity Health Toronto, University of Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
¹⁸ Institute of Medical Science, University of Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
¹⁹ Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
²⁰ Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
²¹ Department of Surgery, King Faisal Specialist Hospital and Research Center, Riyadh, Saudi Arabia. mohammed.al-omran@unityhealth.to.

^# Contributed equally.

PMID: 40707760
PMCID: PMC12289885
DOI: 10.1038/s41746-025-01865-y

Predicting outcomes following endovascular aortoiliac revascularization using machine learning

Ben Li et al. NPJ Digit Med. 2025.

. 2025 Jul 24;8(1):475.

doi: 10.1038/s41746-025-01865-y.

Authors

Affiliations

¹ Department of Surgery, University of Toronto, Toronto, ON, Canada.
² Division of Vascular Surgery, St. Michael's Hospital, Unity Health Toronto, University of Toronto, Toronto, ON, Canada.
³ Institute of Medical Science, University of Toronto, Toronto, ON, Canada.
⁴ Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, ON, Canada.
⁵ Department of Surgery, King Saud University, Riyadh, Saudi Arabia.
⁶ Data Science & Advanced Analytics, Unity Health Toronto, University of Toronto, Toronto, ON, Canada.
⁷ College of Medicine, Alfaisal University, Riyadh, Saudi Arabia.
⁸ Division of Vascular and Endovascular Surgery and the Center for Surgery and Public Health, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
⁹ Division of Cardiology, Peter Munk Cardiac Centre, University Health Network, Toronto, ON, Canada.
¹⁰ Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, ON, Canada.
¹¹ ICES, University of Toronto, Toronto, ON, Canada.
¹² Department of Anesthesia, St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada.
¹³ Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada.
¹⁴ Division of General Surgery, St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada.
¹⁵ Leslie Dan Faculty of Pharmacy, University of Toronto, Toronto, ON, Canada.
¹⁶ Department of Surgery, University of Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
¹⁷ Division of Vascular Surgery, St. Michael's Hospital, Unity Health Toronto, University of Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
¹⁸ Institute of Medical Science, University of Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
¹⁹ Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
²⁰ Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada. mohammed.al-omran@unityhealth.to.
²¹ Department of Surgery, King Faisal Specialist Hospital and Research Center, Riyadh, Saudi Arabia. mohammed.al-omran@unityhealth.to.

^# Contributed equally.

PMID: 40707760
PMCID: PMC12289885
DOI: 10.1038/s41746-025-01865-y

Abstract

Endovascular aortoiliac revascularization is a common treatment option for peripheral artery disease that carries non-negligible risks. Outcome prediction tools may support clinical decision-making but remain limited. We developed machine learning algorithms that predict 30-day post-procedural outcomes. The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent endovascular aortoiliac revascularization between 2011-2021. Input features included 37 pre-operative demographic/clinical variables. The primary outcome was 30-day post-procedural major adverse limb event (MALE) or death. Data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 machine learning models were trained using pre-operative features. Overall, 6601 patients were included, and 30-day MALE/death occurred in 470 (7.1%) individuals. The best-performing model was XGBoost, achieving an AUROC (95% CI) of 0.94 (0.93-0.95). In comparison, logistic regression had an AUROC (95% CI) of 0.74 (0.73-0.76). The XGBoost model accurately predicted 30-day post-procedural outcomes, performing better than logistic regression.

PubMed Disclaimer

Conflict of interest statement

Competing interests: The authors declare no competing interests.

Figures

**Fig. 1. Flowchart for patient selection and outcomes.**
Patients undergoing open revascularization were not included in this study. NSQIP National Surgical Quality Improvement Program.

Fig. 2. Receiver operating characteristic curve for predicting 30-day major adverse limb event or death following endovascular aortoiliac revascularization using Extreme Gradient Boosting (XGBoost) model.
AUROC area under the receiver operating characteristic curve, CI confidence interval.

**Fig. 3. Calibration plot with Brier score.**
Extreme Gradient Boosting (XGBoost) model calibration for predicting 30-day major adverse limb event or death following endovascular aortoiliac revascularization.

Fig. 4. Variable importance scores (gain) for the top 10 predictors of 30-day major adverse limb event or death following endovascular aortoiliac revascularization in the Extreme Gradient Boosting (XGBoost) model.
CLTI chronic limb threatening ischemia.

See this image and copyright information in PMC

References

1. Fowkes, F. G. R. et al. Comparison of global estimates of prevalence and risk factors for peripheral artery disease in 2000 and 2010: a systematic review and analysis. Lancet Lond. Engl.382, 1329–1340 (2013). - PubMed
1. Agnelli, G., Belch, J. J. F., Baumgartner, I., Giovas, P. & Hoffmann, U. Morbidity and mortality associated with atherosclerotic peripheral artery disease: a systematic review. Atherosclerosis293, 94–100 (2020). - PubMed
1. Kim, M., Kim, Y., Ryu, G. W. & Choi, M. Functional status and health-related quality of life in patients with peripheral artery disease: a cross-sectional study. Int. J. Environ. Res. Public. Health18, 10941 (2021). - PMC - PubMed
1. Kohn, C. G., Alberts, M. J., Peacock, W. F., Bunz, T. J. & Coleman, C. I. Cost and inpatient burden of peripheral artery disease: findings from the National Inpatient Sample. Atherosclerosis286, 142–146 (2019). - PubMed
1. Heaton, J. & Khan, Y. S. Aortoiliac Occlusive Disease. in StatPearls (StatPearls Publishing, Treasure Island (FL), 2022). - PubMed

Grants and funding

LinkOut - more resources

Full Text Sources
- Nature Publishing Group
- PubMed Central

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Predicting outcomes following endovascular aortoiliac revascularization using machine learning

Affiliations

Predicting outcomes following endovascular aortoiliac revascularization using machine learning

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

Grants and funding

LinkOut - more resources

Full Text Sources