Download PDF
J Reconstr Microsurg 2024; 40(01): 070-077
DOI: 10.1055/a-2071-3368
Original Article

A Machine Learning Approach to Predicting Donor Site Complications Following DIEP Flap Harvest

Hao Huang   *
1   NewYork-Presbyterian Hospital—Cornell and Columbia, New York, New York
,
Marcos Lu Wang   *
2   Division of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, New York
,
Yunchan Chen 
2   Division of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, New York
,
Tara M. Chadab
1   NewYork-Presbyterian Hospital—Cornell and Columbia, New York, New York
,
Nicholas A. Vernice
2   Division of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, New York
,
David M. Otterburn
2   Division of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, New York
› Author Affiliations Funding None.
› Further Information
    Permissions and Reprints

Abstract

Background The additional donor site incisions in autologous breast reconstruction can predispose to abdominal complications. The purpose of this study is to delineate predictors of donor site morbidity following deep inferior epigastric perforator (DIEP) flap harvest and use those predictors to develop a machine learning model that can identify high-risk patients.

Methods This is a retrospective study of women who underwent DIEP flap reconstruction from 2011 to 2020. Donor site complications included abdominal wound dehiscence, necrosis, infection, seroma, hematoma, and hernia within 90 days postoperatively. Multivariate regression analysis was used to identify predictors for donor site complications. Variables found significant were used to construct machine learning models to predict donor site complications.

Results Of 258 patients, 39 patients (15%) developed abdominal donor site complications, which included 19 cases of dehiscence, 12 cases of partial necrosis, 27 cases of infection, and 6 cases of seroma. On univariate regression analysis, age (p = 0.026), body mass index (p = 0.003), mean flap weight (p = 0.006), and surgery time (p = 0.035) were predictors of donor site complications. On multivariate regression analysis, age (p = 0.025), body mass index (p = 0.010), and surgery duration (p = 0.048) remained significant. Radiographic features of obesity, such as abdominal wall thickness and total fascial diastasis, were not significant predictors of complications (p > 0.05). In our machine learning algorithm, the logistic regression model was the most accurate at predicting donor site complications with the accuracy of 82%, specificity of 0.93, and negative predictive value of 0.87.

Conclusion This study demonstrates that body mass index is superior to radiographic features of obesity in predicting donor site complications following DIEP flap harvest. Other predictors include older age and longer surgery duration. Our logistic regression machine learning model has the potential to quantify the risk of donor site complications.

Keywords

breast reconstruction - donor site - machine learning

* Hao Huang and Marcos Lu Wang contributed equally and are joint first authors


Supplementary Material



Publication History

Received: 10 September 2022

Accepted: 19 March 2023

Accepted Manuscript online:
11 April 2023

Article published online:
05 June 2023

© 2023. Thieme. All rights reserved.

Thieme Medical Publishers, Inc.
333 Seventh Avenue, 18th Floor, New York, NY 10001, USA

 

  • References

  • 1 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 (10) 891-899
    CrossrefPubMedGoogle Scholar
  • 2 Macadam SA, Zhong T, Weichman K. et al. Quality of life and patient-reported outcomes in breast cancer survivors: a multicenter comparison of four abdominally based autologous reconstruction methods. Plast Reconstr Surg 2016; 137 (03) 758-771
    CrossrefPubMedGoogle Scholar
  • 3 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 (10) 901-908
    CrossrefPubMedGoogle Scholar
  • 4 Allen RJ, Treece P. Deep inferior epigastric perforator flap for breast reconstruction. Ann Plast Surg 1994; 32 (01) 32-38
    CrossrefPubMedGoogle Scholar
  • 5 Paik JM, Lee KT, Jeon BJ. et al. Donor site morbidity following DIEP flap for breast reconstruction in Asian patients: is it different?. Microsurgery 2015; 35 (08) 596-602
    CrossrefPubMedGoogle Scholar
  • 6 Grünherz L, Keijzer W, Uyulmaz S. et al. Donor site aesthetics and morbidity after DIEP flap breast reconstruction—a retrospective multicenter study. Breast J 2020; 26 (10) 1980-1986
    CrossrefPubMedGoogle Scholar
  • 7 Vyas RM, Dickinson BP, Fastekjian JH, Watson JP, DaLio AL, Crisera CA. Risk factors for abdominal donor-site morbidity in free flap breast reconstruction. Plast Reconstr Surg 2008; 121 (05) 1519-1526
    CrossrefPubMedGoogle Scholar
  • 8 Patterson CW, Palines PA, Bartow MJ. et al. Stratification of surgical risk in DIEP breast reconstruction based on classification of obesity. J Reconstr Microsurg 2022; 38 (01) 1-9
    Article in Thieme ConnectPubMedGoogle Scholar
  • 9 Timmermans FW, Westland PB, Hummelink S. et al. A retrospective investigation of abdominal visceral fat, body mass index (BMI), and active smoking as risk factors for donor site wound healing complications after free DIEP flap breast reconstructions. J Plast Reconstr Aesthet Surg 2018; 71 (06) 827-832
    CrossrefPubMedGoogle Scholar
  • 10 Cummings P. The relative merits of risk ratios and odds ratios. Arch Pediatr Adolesc Med 2009; 163 (05) 438-445
    CrossrefPubMedGoogle Scholar
  • 11 Naoum GE, Ho AY, Shui A. et al. Risk of developing breast reconstruction complications: a machine-learning nomogram for individualized risk estimation with and without postmastectomy radiation therapy. Plast Reconstr Surg 2022; 149 (01) 1e-12e
    CrossrefPubMedGoogle Scholar
  • 12 Chen JH, Asch SM. Machine learning and prediction in medicine—beyond the peak of inflated expectations. N Engl J Med 2017; 376 (26) 2507-2509
    CrossrefPubMedGoogle Scholar
  • 13 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 (05) 576-584
    CrossrefPubMedGoogle Scholar
  • 14 Jandali S, Nelson JA, Sonnad SS. et al. Breast reconstruction with free tissue transfer from the abdomen in the morbidly obese. Plast Reconstr Surg 2011; 127 (06) 2206-2213
    CrossrefPubMedGoogle Scholar
  • 15 Levi B, Rinkinen J, Kidwell KM. et al. Morphomic analysis for preoperative donor site risk assessment in patients undergoing abdominal perforator flap breast reconstruction: a proof of concept study. J Reconstr Microsurg 2014; 30 (09) 635-640
    Article in Thieme ConnectPubMedGoogle Scholar
  • 16 DelMauro MA, Moon VA. Obesity and the abdominal wall vasculature: correlating BMI with perforator anatomy. J Reconstr Microsurg 2020; 36 (06) 438-444
    Article in Thieme ConnectPubMedGoogle Scholar
  • 17 Lin HS, Watts JN, Peel NM, Hubbard RE. Frailty and post-operative outcomes in older surgical patients: a systematic review. BMC Geriatr 2016; 16 (01) 157
    CrossrefPubMedGoogle Scholar
  • 18 Turrentine FE, Wang H, Simpson VB, Jones RS. Surgical risk factors, morbidity, and mortality in elderly patients. J Am Coll Surg 2006; 203 (06) 865-877
    CrossrefPubMedGoogle Scholar
  • 19 Daley BJ, Cecil W, Clarke PC, Cofer JB, Guillamondegui OD. How slow is too slow? Correlation of operative time to complications: an analysis from the Tennessee Surgical Quality Collaborative. J Am Coll Surg 2015; 220 (04) 550-558
    CrossrefPubMedGoogle Scholar
  • 20 Klasson S, Nyman J, Svensson H, Velander P. Smoking increases donor site complications in breast reconstruction with DIEP flap. J Plast Surg Hand Surg 2016; 50 (06) 331-335
    CrossrefPubMedGoogle Scholar
  • 21 Takeishi M, Shaw WW, Ahn CY, Borud LJ. TRAM flaps in patients with abdominal scars. Plast Reconstr Surg 1997; 99 (03) 713-722
    CrossrefPubMedGoogle Scholar
  • 22 Fu RH, Toyoda Y, Li L, Baser O, Rohde CH, Otterburn DM. Smoking and postoperative complications in plastic and general surgical procedures: a propensity score-matched analysis of 294,903 patients from the national surgical quality improvement program database from 2005 to 2014. Plast Reconstr Surg 2018; 142 (06) 1633-1643
    CrossrefPubMedGoogle Scholar
  • 23 Losken A, Carlson GW, Jones GE, Culbertson JH, Schoemann M, Bostwick III J. Importance of right subcostal incisions in patients undergoing TRAM flap breast reconstruction. Ann Plast Surg 2002; 49 (02) 115-119
    CrossrefPubMedGoogle Scholar
  • 24 Agarwal P, Kukrele R, Sharma D. Vacuum assisted closure (VAC)/negative pressure wound therapy (NPWT) for difficult wounds: a review. J Clin Orthop Trauma 2019; 10 (05) 845-848
    CrossrefPubMedGoogle Scholar
  • 25 Löfstrand J, Paganini A, Lidén M, Hansson E. Donor-site satisfaction of DIEP and latissimus dorsi flaps—a comparative cohort study. J Reconstr Microsurg 2022
    PubMedGoogle Scholar
  • 26 Van Vliet A, Girardot A, Bouchez J, Kumar A, Dayicioglu D. Abdominal plication for better cosmetic outcomes during deep inferior epigastric perforator flap breast reconstruction. Ann Plast Surg 2021; 86 (6S, Suppl 5): S575-S577
    CrossrefPubMedGoogle Scholar
  • 27 Kraft CT, Chao AH. Concurrent ventral hernia repair is effective in patients undergoing abdominally based microsurgical breast reconstruction. J Reconstr Microsurg 2020; 36 (08) 572-576
    Article in Thieme ConnectPubMedGoogle Scholar
  • 28 Bond ES, Soteropulos CE, Yang Q, Poore SO. The impact of prior abdominal surgery on complications of abdominally based autologous breast reconstruction: a systematic review and meta-analysis. J Reconstr Microsurg 2021; 37 (07) 566-579
    Article in Thieme ConnectPubMedGoogle Scholar
  • 29 Dinis J, Allam O, Junn A. et al. Predictors for prolonged drain use following autologous breast reconstruction. J Reconstr Microsurg 2022; 38 (02) 160-167
    Article in Thieme ConnectPubMedGoogle Scholar