[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content

Advertisement

Springer Nature Link
Log in

Development and Evaluation of a Machine Learning Prediction Model for Flap Failure in Microvascular Breast Reconstruction

  • Reconstructive Oncology
  • Published:
Annals of Surgical Oncology Aims and scope Submit manuscript

A Correction to this article was published on 01 November 2021

This article has been updated

Abstract

Background

Despite high success rates, flap failure remains an inherent risk in microvascular breast reconstruction. Identifying patients who are at high risk for flap failure would enable us to recommend alternative reconstructive techniques. However, as flap failure is a rare event, identification of risk factors is statistically challenging. Machine learning is a form of artificial intelligence that automates analytical model building. It has been proposed that machine learning can build superior prediction models when the outcome of interest is rare.

Methods

In this study we evaluate machine learning resampling and decision-tree classification models for the prediction of flap failure in a large retrospective cohort of microvascular breast reconstructions.

Results

A total of 1012 patients were included in the study. Twelve patients (1.1%) experienced flap failure. The ROSE informed oversampling technique and decision-tree classification resulted in a strong prediction model (AUC 0.95) with high sensitivity and specificity. In the testing cohort, the model maintained acceptable specificity and predictive power (AUC 0.67), but sensitivity was reduced. The model identified four high-risk patient groups. Obesity, comorbidities and smoking were found to contribute to flap loss. The flap failure rate in high-risk patients was 7.8% compared with 0.44% in the low-risk cohort (p = 0.001).

Conclusions

This machine-learning risk prediction model suggests that flap failure may not be a random event. The algorithm indicates that flap failure is multifactorial and identifies a number of potential contributing factors that warrant further investigation.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Change history

References

  1. Maajani K, Jalali A, Alipour S, Khodadost M, Tohidinik HR, Yazdani K. The global and regional survival rate of women with breast cancer: a systematic review and meta-analysis. Clin Breast Cancer. 2019;19:165–77.

    Article  PubMed  Google Scholar 

  2. Zhong T, Hu J, Bagher S, et al. A comparison of psychological response, body image, sexuality, and quality of life between immediate and delayed autologous tissue breast reconstruction: a prospective long-term outcome study. Plast Reconstr Surg. 2016;138:772–80.

    Article  CAS  PubMed  Google Scholar 

  3. Zhong T, McCarthy C, Min S, et al. Patient satisfaction and health-related quality of life after autologous tissue breast reconstruction: a prospective analysis of early postoperative outcomes. Cancer. 2012;118:1701–9.

    Article  PubMed  Google Scholar 

  4. Zhong T, McCarthy CM, Price AN, Pusic AL. Evidence-based medicine: breast reconstruction. Plast Reconstr Surg. 2013;132:1658–69.

    Article  CAS  PubMed  Google Scholar 

  5. Bennett KG, Qi J, Kim HM, Hamill JB, Pusic AL, Wilkins EG. Comparison of 2-year complication rates among common techniques for postmastectomy breast reconstruction. JAMA Surg. 2018;153:901–8.

    Article  PubMed  PubMed Central  Google Scholar 

  6. Santosa KB, Qi J, Kim HM, Hamill JB, Wilkins EG, Pusic AL. Long-term patient-reported outcomes in postmastectomy breast reconstruction. JAMA Surg. 2018;153:891–9.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Wilkins EG, Hamill JB, Kim HM, et al. Complications in postmastectomy breast reconstruction: one-year outcomes of the Mastectomy Reconstruction Outcomes Consortium (MROC) Study. Ann Surg. 2018;267:164–70.

    Article  PubMed  Google Scholar 

  8. Higgins KS, Gillis J, Williams JG, LeBlanc M, Bezuhly M, Chorney JM. Women’s experiences with flap failure after autologous breast reconstruction: a qualitative analysis. Ann Plast Surg. 2017;78:521–5.

    Article  CAS  PubMed  Google Scholar 

  9. Mehrara BJ, Santoro TD, Arcilla E, Watson JP, Shaw WW, Da Lio AL. Complications after microvascular breast reconstruction: experience with 1195 flaps. Plast Reconstr Surg. 2006;118:1100–9 (discussion 1110–1).

  10. Unukovych D, Gallego CH, Aineskog H, Rodriguez-Lorenzo A, Mani M. Predictors of reoperations in deep inferior epigastric perforator flap breast reconstruction. Plast Reconstr Surg Glob Open. 2016;4:e1016.

    Article  PubMed  PubMed Central  Google Scholar 

  11. Wade RG, Razzano S, Sassoon EM, Haywood RM, Ali RS, Figus A. Complications in DIEP flap breast reconstruction after mastectomy for breast cancer: a prospective cohort study comparing unilateral versus bilateral reconstructions. Ann Surg Oncol. 2017;24:1465–74.

    Article  PubMed  Google Scholar 

  12. O’Neill AC, Haykal S, Bagher S, Zhong T, Hofer S. Predictors and consequences of intraoperative microvascular problems in autologous breast reconstruction. J Plast Reconstr Aesthet Surg JPRAS. 2016;69:1349–55.

    Article  Google Scholar 

  13. O’Neill AC, Murphy AM, Sebastiampillai S, Zhong T, Hofer SOP. Predicting complications in immediate microvascular breast reconstruction: validity of the breast reconstruction assessment (BRA) surgical risk calculator. J Plast Reconstr Aesthet Surg JPRAS. 2019;72:1285–91.

    Article  Google Scholar 

  14. Lie KH, Barker AS, Ashton MW. A classification system for partial and complete DIEP flap necrosis based on a review of 17,096 DIEP flaps in 693 articles including analysis of 152 total flap failures. Plast Reconstr Surg. 2013;132:1401–8.

    Article  CAS  PubMed  Google Scholar 

  15. Davison SP, Kessler CM, Al-Attar A. Microvascular free flap failure caused by unrecognized hypercoagulability. Plast Reconstr Surg. 2009;124:490–5.

    Article  CAS  PubMed  Google Scholar 

  16. Kolbenschlag J, Daigeler A, Lauer S, et al. Can rotational thromboelastometry predict thrombotic complications in reconstructive microsurgery? Microsurgery. 2014;34:253–60.

    Article  PubMed  Google Scholar 

  17. Pavlou M, Ambler G, Seaman SR, et al. How to develop a more accurate risk prediction model when there are few events. BMJ. 2015;351:h3868.

    Article  PubMed  PubMed Central  Google Scholar 

  18. Kruppa J, Ziegler A, Konig IR. Risk estimation and risk prediction using machine-learning methods. Hum Genet. 2012;131:1639–54.

    Article  Google Scholar 

  19. Wong GL, Ma AJ, Deng H, et al. Machine learning model to predict recurrent ulcer bleeding in patients with history of idiopathic gastroduodenal ulcer bleeding. Aliment Pharmacol Ther. 2019;49:912–8.

    Article  CAS  PubMed  Google Scholar 

  20. Sheikhtaheri A, Orooji A, Pazouki A, Beitollahi M. A clinical decision support system for predicting the early complications of one-anastomosis gastric bypass surgery. Obes Surg. 2019;29:2276–86.

    Article  PubMed  Google Scholar 

  21. Miller R, Tumin D, Cooper J, Hayes D Jr, Tobias JD. Prediction of mortality following pediatric heart transplant using machine learning algorithms. Pediatr Transplant. 2019:e13360.

  22. Liu Y, Zhang Y, Liu D, et al. Prediction of ESRD in IgA nephropathy patients from an Asian cohort: a random forest model. Kidney Blood Press Res. 2018;43:1852–64.

    Article  CAS  PubMed  Google Scholar 

  23. Kazemi A, Kazemi K, Sami A, Sharifian R. Identifying factors that affect patient survival after orthotopic liver transplant using machine-learning techniques. Exp Clin Transplant. 2019;17:775–83.

    Article  PubMed  Google Scholar 

  24. Harris AHS, Kuo AC, Weng Y, Trickey AW, Bowe T, Giori NJ. Can machine learning methods produce accurate and easy-to-use prediction models of 30-day complications and mortality after knee or hip arthroplasty? Clin Orthop Relat Res. 2019;477:452–60.

    Article  PubMed  PubMed Central  Google Scholar 

  25. Fei Y, Gao K, Li WQ. Artificial neural network algorithm model as powerful tool to predict acute lung injury following to severe acute pancreatitis. Pancreatology. 2018;18:892–9.

    Article  PubMed  Google Scholar 

  26. Fei Y, Gao K, Li WQ. Prediction and evaluation of the severity of acute respiratory distress syndrome following severe acute pancreatitis using an artificial neural network algorithm model. HPB. 2018;21:891–897.

    Article  PubMed  Google Scholar 

  27. Cao Y, Fang X, Ottosson J, Naslund E, Stenberg E. A comparative study of machine learning algorithms in predicting severe complications after bariatric surgery. J Clin Med. 2019. https://doi.org/10.3390/jcm8050668.

    Article  PubMed  PubMed Central  Google Scholar 

  28. Christodoulou E, Ma J, Collins GS, Steyerberg EW, Verbakel JY, Van Calster B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019;110:12–22.

    Article  PubMed  Google Scholar 

  29. Tang Y, Zhang YQ, Chawla NV and Krasser S. SVMs modeling for highly imbalanced classification. IEEE Trans Syst Man Cybern B. 2009;39:281–8.

    Article  Google Scholar 

  30. Chawla N BK, Hall L, Kegelmeyer W. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;6:321–57.

    Article  Google Scholar 

  31. Lunardon N MG, Torelli N. ROSE: a package for binary imbalanced learning. R J. 2012;6:79–89.

    Article  Google Scholar 

  32. Banfield RE, Hall LO, Bowyer KW, Kegelmeyer WP. A comparison of decision tree ensemble creation techniques. IEEE Trans Pattern Anal Mach Intell. 2007;29:173–80.

    Article  Google Scholar 

  33. Fischer JP, Nelson JA, Kovach SJ, Serletti JM, Wu LC, Kanchwala S. Impact of obesity on outcomes in breast reconstruction: analysis of 15,937 patients from the ACS-NSQIP datasets. J Am Coll Surg. 2013;217:656–64.

    Article  PubMed  Google Scholar 

  34. Chang DW, Wang B, Robb GL, et al. Effect of obesity on flap and donor-site complications in free transverse rectus abdominis myocutaneous flap breast reconstruction. Plast Reconstr Surg. 2000;105:1640–8.

    Article  CAS  PubMed  Google Scholar 

  35. Lee KT, Mun GH. Effects of obesity on postoperative complications after breast reconstruction using free muscle-sparing transverse rectus abdominis myocutaneous, deep inferior epigastric perforator, and superficial inferior epigastric artery flap: a systematic review and meta-analysis. Ann Plast Surg. 2016;76:576–84.

    Article  CAS  PubMed  Google Scholar 

  36. O’Neill AC, Sebastiampillai S, Zhong T, Hofer SOP. Increasing body mass index increases complications but not failure rates in microvascular breast reconstruction: a retrospective cohort study. J Plast Reconstr Aesthet Surg JPRAS. 2019;72:1518–24.

    Article  PubMed  Google Scholar 

  37. Chang EI, Liu J. Prospective evaluation of obese patients undergoing autologous abdominal free flap breast reconstruction. Plast Reconstr Surg. 2018;142:120e–5e.

    Article  CAS  PubMed  Google Scholar 

  38. Garvey PB, Villa MT, Rozanski AT, Liu J, Robb GL, Beahm EK. The advantages of free abdominal-based flaps over implants for breast reconstruction in obese patients. Plast Reconstr Surg. 2012;130:991–1000.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  39. Ochoa O, Chrysopoulo M, Nastala C, Ledoux P, Pisano S. Abdominal wall stability and flap complications after deep inferior epigastric perforator flap breast reconstruction: does body mass index make a difference? Analysis of 418 patients and 639 flaps. Plast Reconstr Surg. 2012;130:21e–33e.

    Article  CAS  PubMed  Google Scholar 

  40. Roy M, Sebastiampillai S, Zhong T, Hofer SOP, O’Neill AC. Synergistic interaction increases complication rates following microvascular breast reconstruction. Plast Reconstr Surg. 2019;144:1e–8e.

    Article  CAS  PubMed  Google Scholar 

  41. Panesar SS, D’Souza RN, Yeh FC, Fernandez-Miranda JC. Machine learning versus logistic regression methods for 2-year mortality prognostication in a small, heterogeneous glioma database. World Neurosurg X. 2019;2:100012.

    Article  PubMed  PubMed Central  Google Scholar 

  42. Fosnot J, Fischer JP, Smartt JM Jr, et al. Does previous chest wall irradiation increase vascular complications in free autologous breast reconstruction? Plast Reconstr Surg. 2011;127:496–504.

    Article  CAS  PubMed  Google Scholar 

  43. McInerney NM, O’Neill AC, Zhong T, Hofer SOP. Response to “Complications in DIEP flap breast reconstruction after mastectomy for breast cancer: a prospective cohort study comparing unilateral and bilateral reconstructions.” Ann Surg Oncol. 2017;24:561–2.

    Article  PubMed  Google Scholar 

Download references

Disclosures

Anne C. O’Neill, Dongyang Yang, Melissa Roy, Stephanie Sebastiampillai, Stefan O.P. Hofer and Wei Xu declare no conflicts of interest.

Author information

Authors and Affiliations

  1. Division of Plastic Surgery, Department of Surgery and Surgical Oncology, University Health Network, University of Toronto, Toronto, Canada

    Anne C. O’Neill MBBCh, PhD, Melissa Roy MD, MSc, Stephanie Sebastiampillai BSc & Stefan O.P. Hofer MD, PhD

  2. Department of Biostatistics, Princess Margaret Cancer Centre, University Health Network, Toronto, Canada

    Dongyang Yang PhD & Wei Xu PhD

Authors
  1. Anne C. O’Neill MBBCh, PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dongyang Yang PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Melissa Roy MD, MSc
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Stephanie Sebastiampillai BSc
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Stefan O.P. Hofer MD, PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Wei Xu PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anne C. O’Neill MBBCh, PhD.

Additional information

Publisher's Note

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

The original online version of this article was revised: Dongyang Yang’s given name was corrected.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

O’Neill, A.C., Yang, D., Roy, M. et al. Development and Evaluation of a Machine Learning Prediction Model for Flap Failure in Microvascular Breast Reconstruction. Ann Surg Oncol 27, 3466–3475 (2020). https://doi.org/10.1245/s10434-020-08307-x

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1245/s10434-020-08307-x