Skip to main content

Advertisement

SpringerLink
Log in

Prediction of thirty-day morbidity and mortality after laparoscopic sleeve gastrectomy: data from an artificial neural network

  • 2019 SAGES Oral
  • Published:
Surgical Endoscopy Aims and scope Submit manuscript

Abstract

Background

Multiple patient factors may convey increased risk of 30-day morbidity and mortality after laparoscopic vertical sleeve gastrectomy (LVSG). Assessing the likelihood of short-term morbidity is useful for both the bariatric surgeon and patient. Artificial neural networks (ANN) are computational algorithms that use pattern recognition to predict outcomes, providing a potentially more accurate and dynamic model relative to traditional multiple regression. Using a comprehensive national database, this study aims to use an ANN to optimize the prediction of the composite endpoint of 30-day readmission, reoperation, reintervention, or mortality, after LVSG.

Methods

A cohort of 101,721 LVSG patients was considered for analysis from the 2016 Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program national dataset. Select patient factors were chosen a priori as simple, pertinent and easily obtainable, and their association with the 30-day endpoint was assessed. Those factors with a significant association on both bivariate and multivariate nominal logistic regression analysis were incorporated into a back-propagation ANN with three nodes each assigned a training value of 0.333, with k-fold internal validation. Logistic regression and ANN models were compared using area under receiver-operating characteristic curves (AUROC).

Results

Upon bivariate analysis, factors associated with 30-day complications were older age (P = 0.03), non-white race, higher initial body mass index, severe hypertension, diabetes mellitus, non-independent functional status, and previous foregut/bariatric surgery (all P < 0.001). These factors remained significant upon nominal logistic regression analysis (n = 100,791, P < 0.001, r2= 0.008, AUROC = 0.572). Upon ANN analysis, the training set (80% of patients) was more accurate than logistic regression (n = 80,633, r2= 0.011, AUROC = 0.581), and it was confirmed by the validation set (n = 20,158, r2= 0.012, AUROC = 0.585).

Conclusions

This study identifies a panel of simple and easily obtainable preoperative patient factors that may portend increased morbidity after LSG. Using an ANN model, prediction of these events can be optimized relative to standard logistic regression modeling.

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
Fig. 2

Similar content being viewed by others

References

  1. MBSAQIP (2016) MBSAQIP Participant Use Data File

  2. Penny W, Frost D (1996) Neural networks in clinical medicine. Med Deci Mak 16:386–398

    Article  CAS  Google Scholar 

  3. Yoldas O, Tez M, Karaca T (2012) Artificial neural networks in the diagnosis of acute appendicitis. Am J Emerg Med 30:1245–1247

    Article  Google Scholar 

  4. Wise ES, Stonko DP, Glaser ZA, Garcia KL, Huang JJ, Kim JS, Kallos JA, Starnes JR, Fleming JW, Hocking KM, Brophy CM, Eagle SS (2017) Prediction of prolonged ventilation after coronary artery bypass grafting: data from an artificial neural network. Heart Surg Forum 20:E007–E014

    Article  Google Scholar 

  5. Cruz-Ramirez M, Hervas-Martinez C, Fernandez JC, Briceno J, de la Mata M (2013) Predicting patient survival after liver transplantation using evolutionary multi-objective artificial neural networks. Artif Intell Med 58:37–49

    Article  Google Scholar 

  6. Wise ES, Hocking KM, Brophy CM (2015) Prediction of in-hospital mortality after ruptured abdominal aortic aneurysm repair using an artificial neural network. J Vasc Surg 62(1):8–15

    Article  Google Scholar 

  7. Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143:29–36

    Article  CAS  Google Scholar 

  8. Benaiges D, Mas-Lorenzo A, Goday A, Ramon JM, Chillaron JJ, Pedro-Botet J, Flores-Le Roux JA (2015) Laparoscopic sleeve gastrectomy: more than a restrictive bariatric surgery procedure? World J Gastroenterol 21:11804–11814

    Article  CAS  Google Scholar 

  9. Salminen P, Helmio M, Ovaska J, Juuti A, Leivonen M, Peromaa-Haavisto P, Hurme S, Soinio M, Nuutila P, Victorzon M (2018) Effect of laparoscopic sleeve gastrectomy versus laparoscopic Roux-en-Y gastric bypass on weight loss at 5 years among patients with morbid obesity: the sleevepass randomized clinical trial. JAMA 319:241–254

    Article  Google Scholar 

  10. Melissas J, Braghetto I, Molina JC, Silecchia G, Iossa A, Iannelli A, Foletto M (2015) Gastroesophageal reflux disease and sleeve gastrectomy. Obes Surg 25:2430–2435

    Article  Google Scholar 

  11. Telem DA, Yang J, Altieri M, Patterson W, Peoples B, Chen H, Talamini M, Pryor AD (2016) Rates and risk factors for unplanned emergency department utilization and hospital readmission following bariatric surgery. Ann Surg 263:956–960

    Article  Google Scholar 

  12. Major P, Wysocki M, Torbicz G, Gajewska N, Dudek A, Malczak P, Pedziwiatr M, Pisarska M, Radkowiak D, Budzynski A (2018) Risk factors for prolonged length of hospital stay and readmissions after laparoscopic sleeve gastrectomy and laparoscopic Roux-en-Y gastric bypass. Obes Surg 28:323–332

    Article  Google Scholar 

  13. Sippey M, Kasten KR, Chapman WH, Pories WJ, Spaniolas K (2016) 30-day readmissions after sleeve gastrectomy versus Roux-en-Y gastric bypass. Surg Obes Relat Dis 12:991–996

    Article  Google Scholar 

  14. Garg T, Rosas U, Rivas H, Azagury D, Morton JM (2016) National prevalence, causes, and risk factors for bariatric surgery readmissions. Am J Surg 212:76–80

    Article  Google Scholar 

  15. Lak KL, Helm MC, Kindel TL, Gould JC (2019) Metabolic syndrome is a significant predictor of postoperative morbidity and mortality following bariatric surgery. J Gastrointest Surg 23:739–744

    Article  Google Scholar 

  16. Lee YC, Lee WJ, Lee TS, Lin YC, Wang W, Liew PL, Huang MT, Chien CW (2007) Prediction of successful weight reduction after bariatric surgery by data mining technologies. Obes Surg 17:1235–1241

    Article  Google Scholar 

  17. Piaggi P, Lippi C, Fierabracci P, Maffei M, Calderone A, Mauri M, Anselmino M, Cassano GB, Vitti P, Pinchera A, Landi A, Santini F (2010) Artificial neural networks in the outcome prediction of adjustable gastric banding in obese women. PLoS ONE 5:e13624

    Article  Google Scholar 

  18. Lee YC, Liew PL, Lee WJ, Lin YC, Lee CK, Huangs MT, Wang W, Lin SC (2009) Prediction of successful weight reduction after laparoscopic adjustable gastric banding. Hepatogastroenterology 56:1222–1226

    CAS  PubMed  Google Scholar 

  19. Wise ES, Hocking KM, Kavic SM (2016) Prediction of excess weight loss after laparoscopic Roux-en-Y gastric bypass: data from an artificial neural network. Surg Endosc 30:480–488

    Article  Google Scholar 

  20. Minhem MA, Safadi BY, Habib RH, Raad EPB, Alami RS (2018) Increased adverse outcomes after laparoscopic sleeve gastrectomy in older super-obese patients: analysis of American College of Surgeons National Surgical Quality Improvement Program Database. Surg Obes Relat Dis 14:1463–1470

    Article  Google Scholar 

Download references

Acknowledgements

None.

Funding

There was no funding used for this manuscript.

Author information

Authors and Affiliations

  1. Department of Surgery, Division of Gastrointestinal/Bariatric Surgery, University Of Minnesota, 420 Delaware St SE, MMC 195, Minneapolis, MN, 55455, USA

    Eric S. Wise, Sayeed Ikramuddin & Daniel B. Leslie

  2. Division of Gastroenterology, Hepatology and Nutrition, Section of Interventional and Advanced Endoscopy, Department of Medicine, University of Minnesota, Minneapolis, USA

    Stuart K. Amateau

Authors
  1. Eric S. Wise
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stuart K. Amateau
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sayeed Ikramuddin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Daniel B. Leslie
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Eric S. Wise.

Ethics declarations

Disclosures

Eric Wise, Stuart Amateau, Sayeed Ikramuddin, and Daniel Leslie have no conflicts of interest or financial ties to disclose.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wise, E.S., Amateau, S.K., Ikramuddin, S. et al. Prediction of thirty-day morbidity and mortality after laparoscopic sleeve gastrectomy: data from an artificial neural network. Surg Endosc 34, 3590–3596 (2020). https://doi.org/10.1007/s00464-019-07130-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00464-019-07130-0

Keywords

Search

Navigation