Skip to main content

Advertisement

SpringerLink
Log in

A predictive algorithm for perioperative complications and readmission after ankle arthrodesis

  • Original Article
  • Published:
European Journal of Orthopaedic Surgery & Traumatology Aims and scope Submit manuscript

Abstract

Purpose

Ankle arthrodesis is a mainstay of surgical management for ankle arthritis. Accurately risk-stratifying patients who undergo ankle arthrodesis would be of great utility. There is a paucity of accurate prediction models that can be used to pre-operatively risk-stratify patients for ankle arthrodesis. We aim to develop a predictive model for major perioperative complication or readmission after ankle arthrodesis.

Methods

This is a retrospective cohort study of adult patients who underwent ankle arthrodesis at any non-federal California hospital between 2015 and 2017. The primary outcome is readmission within 30 days or major perioperative complication. We build logistic regression and ML models spanning different classes of modeling approaches, assessing discrimination and calibration. We also rank the contribution of the included variables to model performance for prediction of adverse outcomes.

Results

A total of 1084 patients met inclusion criteria for this study. There were 131 patients with major complication or readmission (12.1%). The XGBoost algorithm demonstrates the highest discrimination with an area under the receiver operating characteristic curve of 0.707 and is well-calibrated. The features most important for prediction of adverse outcomes for the XGBoost model include: diabetes, peripheral vascular disease, teaching hospital status, morbid obesity, history of musculoskeletal infection, history of hip fracture, renal failure, implant complication, history of major fracture.

Conclusion

We report a well-calibrated algorithm for prediction of major perioperative complications and 30-day readmission after ankle arthrodesis. This tool may help accurately risk-stratify patients and decrease likelihood of major complications.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

References

  1. Tucker W, Barnds B, Morris B et al (2022) Nationwide analysis of total ankle replacement and ankle arthrodesis in Medicare patients: trends, complications, and cost. Foot Ankle Spec 15(3):201–208

    Article  PubMed  Google Scholar 

  2. Stavrakis A, SooHoo N (2016) Trends in complication rates following ankle arthrodesis and total ankle replacement. J Bone Joint Surg Am 98:1453–1458

    Article  PubMed  Google Scholar 

  3. Odum S, van Doren B, Anderson R, Davis W (2017) In-hospital complications following ankle arthrodesis versus ankle arthroplasty. J Bone Joint Surg Am 99(17):1469–1475

    Article  PubMed  Google Scholar 

  4. Haddad S, Coetzee J, Estok R, Fahrbach K, Banel D, Nalysynk L (2007) Intermediate and long-term outcomes of total ankle arthroplasty and ankle arthrodesis. A systematic review of the literature. J Bone Joint Surg Am 89(9):1899–1905

    Article  CAS  PubMed  Google Scholar 

  5. Daniels T, Younger A, Penner M et al (2014) Intermediate-term results of total ankle replacement and ankle arthrodesis: a COFAS multicenter study. J Bone Joint Surg Am 96(2):135–142

    Article  PubMed  Google Scholar 

  6. Jiang J, Schipper O, Whyte N, Koh J, Toolan B (2015) Comparison of perioperative complications and hospitalization outcomes after ankle arthrodesis versus total ankle arthroplasty from 2002 to 2011. Foot Ankle Int 36(4):360–368

    Article  PubMed  Google Scholar 

  7. Ross B, Savage-Elliott I, Wu W, Rodriguez R (2023) Complications following total ankle arthroplasty versus ankle arthrodesis for primary ankle osteoarthritis. Foot Ankle Spec 16(1):20–27

    Article  PubMed  Google Scholar 

  8. Courville X, Hecht P, Tosteson A (2011) Is total ankle arthroplasty a cost-effective alternative to ankle fusion? Clin Ortohp Relat Res 469(6):1721–1727

    Article  Google Scholar 

  9. Raikin S, Rasouli M, Espandar R, Maltenfort M (2014) Trends in treatment of advanced ankle arthropathy by total ankle replacement or ankle fusion. Foot Ankle Int 35(3):216–224

    Article  PubMed  Google Scholar 

  10. Vakhshori V, Sabour A, Alluri R, Hatch G, Tan E (2019) Patient and practice trends in total ankle replacement and tibiotalar arthrodesis in the United States from 2007 to 2013. J Am Acad Orthop Surg 27(2):e77–e84

    Article  PubMed  Google Scholar 

  11. Merrill R, Ferrandino R, Hoffman R, Ndu A, Shaffer G (2019) Comparing 30-day all-cause readmission rates between tibiotalar fusion and total ankle replacement. Foot Ankle Surg 25:327–331

    Article  PubMed  Google Scholar 

  12. Cabitza F, Locoro A, Banfi G (2018) Machine learning in orthopedics: a literature review. Front Bioeng Biotechnol 6:1–20

    Article  Google Scholar 

  13. Esteva A, Kuprel B, Novoa R et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7660):115–118

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  14. Gulshan V, Peng L, Coram M et al (2016) Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316(22):2402–2410

    Article  PubMed  Google Scholar 

  15. Karhade AV, Thio Q, Ogink P et al (2019) Development of machine learning algorithms for prediction of 30-day mortality after surgery for spinal metastasis. Neurosurgery 85(1):e83–e91

    Article  PubMed  Google Scholar 

  16. Yale New Haven Health Services Corporation/Center for Outcomes Research & Evaluation. 2017 Procedure-specific measure updates and specifications report hospital-level risk-standardized complication measure: elective primary total hip arthroplasty (THA) and/or total knee arthroplasty (TKA) – version 6.0, 2017.

  17. Breiman L (2001) Random forests. Mach Learn 45:5–32

    Article  Google Scholar 

  18. Ratsch G, Onoda T, Muller K (2001) Soft margins for AdaBoost. Mach Learn 42:287–320

    Article  Google Scholar 

  19. Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232

    Article  Google Scholar 

  20. Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: KDD ’16 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 785–94

  21. Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12(85):2825–2830

    Google Scholar 

  22. Fischer J, Bachmann L, Jaeschke R (2003) A reader’s guide to the interpretation of diagnostic test properties: clinical example of sepsis. Intensive Care Med 29:1043–1051

    Article  PubMed  Google Scholar 

  23. Steyerberg E, Vergouwe Y (2014) Towards better clinical prediction models: seven steps for development and an ABCD for validation. Eur Heart J 35(29):1925–1931

    Article  PubMed  PubMed Central  Google Scholar 

  24. Manning DW, Edelstein AI, Alvi HM (2016) Risk prediction tools for hip and knee arthroplasty. J Am Acad Orthop Surg 24(1):19–27

    Article  PubMed  Google Scholar 

  25. Myers T, Lowery N, Frykberg R, Wukich D (2012) Ankle and hindfoot fusions: comparison of outcomes in patients with and without diabetes. Foot Ankle Int 33(1):20–28

    Article  PubMed  Google Scholar 

  26. Chalayon O, Wang B, Blankenhorn B et al (2015) Factors affecting the outcomes of uncomplicated primary open ankle arthrodesis. Foot Ankle Int 36(10):1170–1179

    Article  PubMed  Google Scholar 

  27. Jain S, Tiernan D, Kearns S (2016) Analysis of risk factors for failure of arthroscopic ankle fusion in a series of 52 ankles. Foot Ankle Surg 22(2):91–96

    Article  PubMed  Google Scholar 

  28. Schipper O, Jiang J, Chen L, Koh J, Toolan B (2015) Effect of diabetes mellitus on perioperative complications and hospital outcomes after ankle arthrodesis and total ankle arthroplasty. Foot Ankle Int 36(3):258–267

    Article  PubMed  Google Scholar 

  29. Wukich D, Crim B, Frykberg R, Rossario B (2014) Neuropathy and poorly controlled diabetes increase the rate of surgical site infection after foot and ankle surgery. J Bone Joint Surg Am 96:832–839

    Article  PubMed  PubMed Central  Google Scholar 

  30. Shibuya N, Humphers J, Fluhman B, Jupiter D (2013) Factors associated with nonunion, delayed union, and malunion in foot and ankle surgery in diabetic patients. J Foot Ankle Surg 52:207–211

    Article  PubMed  Google Scholar 

  31. DeVries J, Berlet G, Hyer C (2013) Predictive risk assessment for major amputation after tibiotalocalcaneal arthrodesis. Foot Ankle Int 34(6):846–850

    Article  PubMed  Google Scholar 

  32. Pitts C, Alexander B, Washington J et al (2020) Factors affecting the outcomes of tibiotalcaneal fusion. Bone Joint J 102-B(3):345–351

    Article  PubMed  Google Scholar 

  33. Collier B, Dossett L, May A, Diaz J (2008) Glucose control and the inflammatory response. Nutr Clin Pr 23(1):3–15

    Article  Google Scholar 

  34. Abdel M, Ast M, Lee Y, Lyman S, Gonzalez Della Valle A (2014) All-cause in-hospital complications and urinary tract infections increased in obese patients undergoing total knee arthroplasty. J Arthroplasty 29(7):1430–1434

    Article  PubMed  Google Scholar 

  35. Huddleston J, Wang Y, Uquillas C, Herndon J, Maloney W (2012) Age and obesity are risk factors for adverse events after total hip arthroplasty. Clin Orthop Relat Res 470(2):490–496

    Article  PubMed  Google Scholar 

  36. Gupta A, Chalmers P, Rahman Z et al (2014) Reverse total shoulder arthroplasty in patients of varying body mass index. J Shoulder Elbow Surg 23(1):35–42

    Article  PubMed  Google Scholar 

  37. Werner B, Burrus M, Looney A, Park J, Perumal V, Cooper M (2015) Obesity is associated with increased complications after operative management of end-stage ankle arthritis. Foot Ankle Int 36(8):863–870

    Article  PubMed  Google Scholar 

  38. Gross C, Chang D, Adams S, Parekh S, Bohnen J (2017) Surgical resident involvement in foot and ankle surgery. Foot Ankle Surg 23(4):261–267

    Article  PubMed  Google Scholar 

  39. Bozic K, Bashyal R, Anthony S, Chiu V, Shulman B, Rubash H (2013) Is administratively coded comorbidity and complication data in total joint arthroplasty valid? Clin Orthop Relat Res 471:201–205

    Article  PubMed  Google Scholar 

  40. Hashimoto D, Rosman G, Rus D, Meireles O (2018) Artificial intelligence in surgery: promises and perils. Ann Surg 268(1):70–76

    Article  PubMed  Google Scholar 

Download references

Funding

The authors received no funding for this study.

Author information

Authors and Affiliations

  1. Department of Orthopaedic Surgery, David Geffen School of Medicine at UCLA, 10833 Le Conte Avenue, 76-116 CHS, Los Angeles, CA, 90095, USA

    Akash A. Shah, Sai K. Devana & Nelson F. SooHoo

  2. Department of Artificial Intelligence, Chung-Ang University School of Software and Computer Engineering, Seoul, South Korea

    Changhee Lee

Authors
  1. Akash A. Shah
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sai K. Devana
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Changhee Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nelson F. SooHoo
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to research design, acquisition of data, and interpretation of data. AAS contributed to analysis of data and drafting the manuscript. SKD and CL contributed to analysis of data, interpretation of data, and critical revision of the manuscript. NFS contributed to critical revision of the manuscript. All authors have read and approve the final manuscript.

Corresponding author

Correspondence to Akash A. Shah.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Ethical approval

This study is exempt from Institutional Review Board approval. This study complies with the current laws of the country in which it was performed.

Informed consent

Informed consent was not required for this retrospective study that is exempt from Institutional Review Board approval.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 14 kb)

Supplementary file2 (DOCX 13 kb)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shah, A.A., Devana, S.K., Lee, C. et al. A predictive algorithm for perioperative complications and readmission after ankle arthrodesis. Eur J Orthop Surg Traumatol 34, 1373–1379 (2024). https://doi.org/10.1007/s00590-023-03805-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00590-023-03805-6

Keywords

Search

Navigation