Surgical Endoscopy

, Volume 30, Issue 2, pp 480–488 | Cite as

Prediction of excess weight loss after laparoscopic Roux-en-Y gastric bypass: data from an artificial neural network

  • Eric S. WiseEmail author
  • Kyle M. Hocking
  • Stephen M. Kavic



Laparoscopic Roux-en-Y gastric bypass (LRYGB) has become the gold standard for surgical weight loss. The success of LRYGB may be measured by excess body mass index loss (%EBMIL) over 25 kg/m2, which is partially determined by multiple patient factors. In this study, artificial neural network (ANN) modeling was used to derive a reasonable estimate of expected postoperative weight loss using only known preoperative patient variables. Additionally, ANN modeling allowed for the discriminant prediction of achievement of benchmark 50 % EBMIL at 1 year postoperatively.


Six hundred and forty-seven LRYGB included patients were retrospectively reviewed for preoperative factors independently associated with EBMIL at 180 and 365 days postoperatively (EBMIL180 and EBMIL365, respectively). Previously validated factors were selectively analyzed, including age; race; gender; preoperative BMI (BMI0); hemoglobin; and diagnoses of hypertension (HTN), diabetes mellitus (DM), and depression or anxiety disorder. Variables significant upon multivariate analysis (P < .05) were modeled by “traditional” multiple linear regression and an ANN, to predict %EBMIL180 and %EBMIL365.


The mean EBMIL180 and EBMIL365 were 56.4 ± 16.5 % and 73.5 ± 21.5 %, corresponding to total body weight losses of 25.7 ± 5.9 % and 33.6 ± 8.0 %, respectively. Upon multivariate analysis, independent factors associated with EBMIL180 included black race (B = −6.3 %, P < .001), BMI0 (B = −1.1 %/unit BMI, P < .001), and DM (B = −3.2 %, P < .004). For EBMIL365, independently associated factors were female gender (B = 6.4 %, P < .001), black race (B = −6.7 %, P < .001), BMI0 (B = −1.2 %/unit BMI, P < .001), HTN (B = −3.7 %, P = .03), and DM (B = −6.0 %, P < .001). Pearson r 2 values for the multiple linear regression and ANN models were 0.38 (EBMIL180) and 0.35 (EBMIL365), and 0.42 (EBMIL180) and 0.38 (EBMIL365), respectively. ANN prediction of benchmark 50 % EBMIL at 365 days generated an area under the curve of 0.78 ± 0.03 in the training set (n = 518) and 0.83 ± 0.04 (n = 129) in the validation set.


Available at, this or other ANN models may be used to provide an optimized estimate of postoperative EBMIL following LRYGB.


Bariatric Obesity Gastric bypass Outcomes 



Dr. Colleen Brophy, M.D., Professor of Surgery, Vanderbilt University, Vanderbilt University Department of Biostatistics, Vanderbilt RedCAP: CTSA Award UL1 TR000445 from NCATS/NIH.


Eric Wise, Kyle Hocking and Stephen Kavic have no conflict of interest to disclose.


  1. 1.
    Wood GC, Benotti P, Gerhard GS, Miller EK, Zhang Y, Zaccone RJ, Argyropoulos GA, Petrick AT, Still CD (2014) A patient-centered electronic tool for weight loss outcomes after Roux-en-Y gastric bypass. J Obes 2014:364941PubMedCentralCrossRefPubMedGoogle Scholar
  2. 2.
    Colquitt JL, Pickett K, Loveman E, Frampton GK (2014) Surgery for weight loss in adults. Cochrane Database Syst Rev 8:CD003641PubMedGoogle Scholar
  3. 3.
    Carter J, Elliott S, Kaplan J, Lin M, Posselt A, Rogers S (2015) Predictors of hospital stay following laparoscopic gastric bypass: analysis of 9593 patients from the National Surgical Quality Improvement Program. Surg Obes Relat Dis 11:288–294Google Scholar
  4. 4.
    Tadross JA, le Roux CW (2009) The mechanisms of weight loss after bariatric surgery. Int J Obes 33(Suppl 1):S28–s32CrossRefGoogle Scholar
  5. 5.
    Levine MS, Carucci LR (2014) Imaging of bariatric surgery: normal anatomy and postoperative complications. Radiology 270:327–341CrossRefPubMedGoogle Scholar
  6. 6.
    Kissler HJ, Settmacher U (2013) Bariatric surgery to treat obesity. Semin Nephrol 33:75–89CrossRefPubMedGoogle Scholar
  7. 7.
    Lutz TA, Bueter M (2014) The physiology underlying Roux-en-Y gastric bypass: a status report. Am J Physiol Regul Integr Comp Physiol 307:R1275–R1291PubMedCentralCrossRefPubMedGoogle Scholar
  8. 8.
    van de Laar A (2012) Bariatric Outcomes Longitudinal Database (BOLD) suggests excess weight loss and excess BMI loss to be inappropriate outcome measures, demonstrating better alternatives. Obes Surg 22:1843–1847CrossRefPubMedGoogle Scholar
  9. 9.
    Still CD, Wood GC, Chu X, Manney C, Strodel W, Petrick A, Gabrielsen J, Mirshahi T, Argyropoulos G, Seiler J, Yung M, Benotti P, Gerhard GS (2014) Clinical factors associated with weight loss outcomes after Roux-en-Y gastric bypass surgery. Obesity 22:888–894PubMedCentralCrossRefPubMedGoogle Scholar
  10. 10.
    Dallal RM, Quebbemann BB, Hunt LH, Braitman LE (2009) Analysis of weight loss after bariatric surgery using mixed-effects linear modeling. Obes Surg 19:732–737CrossRefPubMedGoogle Scholar
  11. 11.
    Coleman KJ, Huang YC, Hendee F, Watson HL, Casillas RA, Brookey J (2014) Three-year weight outcomes from a bariatric surgery registry in a large integrated healthcare system. Surg Obes Relat Dis 10:396–403CrossRefPubMedGoogle Scholar
  12. 12.
    Alger-Mayer S, Polimeni JM, Malone M (2008) Preoperative weight loss as a predictor of long-term success following Roux-en-Y gastric bypass. Obes Surg 18:772–775CrossRefPubMedGoogle Scholar
  13. 13.
    Alger-Mayer S, Rosati C, Polimeni JM, Malone M (2009) Preoperative binge eating status and gastric bypass surgery: a long-term outcome study. Obes Surg 19:139–145CrossRefPubMedGoogle Scholar
  14. 14.
    Livhits M, Mercado C, Yermilov I, Parikh JA, Dutson E, Mehran A, Ko CY, Gibbons MM (2012) Preoperative predictors of weight loss following bariatric surgery: systematic review. Obes Surg 22:70–89CrossRefPubMedGoogle Scholar
  15. 15.
    Mitchell JE, King WC, Courcoulas A, Dakin G, Elder K, Engel S, Flum D, Kalarchian M, Khandelwal S, Pender J, Pories W, Wolfe B (2015) Eating behavior and eating disorders in adults before bariatric surgery. Int J Eat Disord 48:215–222Google Scholar
  16. 16.
    Edwards-Hampton SA, Madan A, Wedin S, Borckardt JJ, Crowley N, Byrne KT (2014) A closer look at the nature of anxiety in weight loss surgery candidates. Int J Psychiatry Med 47:105–113CrossRefPubMedGoogle Scholar
  17. 17.
    Stein J, Stier C, Raab H, Weiner R (2014) Review article: the nutritional and pharmacological consequences of obesity surgery. Aliment Pharmacol Ther 40:582–609CrossRefPubMedGoogle Scholar
  18. 18.
    Munoz M, Botella-Romero F, Gomez-Ramirez S, Campos A, Garcia-Erce JA (2009) Iron deficiency and anaemia in bariatric surgical patients: causes, diagnosis and proper management. Nutr Hosp 24:640–654PubMedGoogle Scholar
  19. 19.
    Dumont TM, Rughani AI, Tranmer BI (2011) Prediction of symptomatic cerebral vasospasm after aneurysmal subarachnoid hemorrhage with an artificial neural network: feasibility and comparison with logistic regression models. World Neurosurg 75:57–63 discussion 25-58 CrossRefPubMedGoogle Scholar
  20. 20.
    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 17:1235–1241CrossRefPubMedGoogle Scholar
  21. 21.
    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:e13624PubMedCentralCrossRefPubMedGoogle Scholar
  22. 22.
    Yoldas O, Tez M, Karaca T (2012) Artificial neural networks in the diagnosis of acute appendicitis. Am J Emerg Med 30:1245–1247CrossRefPubMedGoogle Scholar
  23. 23.
    Presnell SR, Cohen FE (1993) Artificial neural networks for pattern recognition in biochemical sequences. Annu Rev Biophys Biomol Struct 22:283–298CrossRefPubMedGoogle Scholar
  24. 24.
    Harris PA, Taylor R, Thielke R, Payne J, Gonzalez N, Conde JG (2009) Research electronic data capture (REDCap)—a metadata-driven methodology and workflow process for providing translational research informatics support. J Biomed Inform 42:377–381PubMedCentralCrossRefPubMedGoogle Scholar
  25. 25.
    Cook NR (2007) Use and misuse of the receiver operating characteristic curve in risk prediction—response. Circulation 116:E134–E134CrossRefGoogle Scholar
  26. 26.
    Debnath J, Chatterjee S, Sharma V (2013) Artificial neural networks in the diagnosis of acute appendicitis: should imaging be a part of it? Am J Emerg Med 31:258–259CrossRefPubMedGoogle Scholar
  27. 27.
    Hsieh CH, Lu RH, Lee NH, Chiu WT, Hsu MH, Li YC (2011) Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks. Surgery 149:87–93CrossRefPubMedGoogle Scholar
  28. 28.
    Sakai S, Kobayashi K, Toyabe S, Mandai N, Kanda T, Akazawa K (2007) Comparison of the levels of accuracy of an artificial neural network model and a logistic regression model for the diagnosis of acute appendicitis. J Med Syst 31:357–364CrossRefPubMedGoogle Scholar
  29. 29.
    Gholipour C, Fakhree MB, Shalchi RA, Abbasi M (2009) Prediction of conversion of laparoscopic cholecystectomy to open surgery with artificial neural networks. BMC surgery 9:13PubMedCentralCrossRefPubMedGoogle Scholar
  30. 30.
    Gohari MR, Biglarian A, Bakhshi E, Pourhoseingholi MA (2011) Use of an artificial neural network to determine prognostic factors in colorectal cancer patients. Asian Pac J Cancer Prev APJCP 12:1469–1472PubMedGoogle Scholar
  31. 31.
    Biglarian A, Bakhshi E, Gohari MR, Khodabakhshi R (2012) Artificial neural network for prediction of distant metastasis in colorectal cancer. Asian Pac J Cancer Prev APJCP 13:927–930CrossRefPubMedGoogle Scholar
  32. 32.
    Dolgobrodov SG, Moore P, Marshall R, Bittern R, Steele RJ, Cuschieri A (2007) Artificial neural network: predicted vs observed survival in patients with colonic cancer. Dis Colon Rectum 50:184–191CrossRefPubMedGoogle Scholar
  33. 33.
    Ahmed FE (2005) Artificial neural networks for diagnosis and survival prediction in colon cancer. Mol Cancer 4:29PubMedCentralCrossRefPubMedGoogle Scholar
  34. 34.
    Feng F, Wu Y, Wu Y, Nie G, Ni R (2012) The effect of artificial neural network model combined with six tumor markers in auxiliary diagnosis of lung cancer. J Med Syst 36:2973–2980CrossRefPubMedGoogle Scholar
  35. 35.
    Faradmal J, Soltanian AR, Roshanaei G, Khodabakhshi R, Kasaeian A (2014) Comparison of the performance of log-logistic regression and artificial neural networks for predicting breast cancer relapse. Asian Pac J Cancer Prev APJCP 15:5883–5888CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Eric S. Wise
    • 1
    • 2
    Email author
  • Kyle M. Hocking
    • 1
    • 3
  • Stephen M. Kavic
    • 2
  1. 1.Department of SurgeryVanderbilt University Medical CenterNashvilleUSA
  2. 2.Department of General SurgeryUniversity of Maryland Medical CenterBaltimoreUSA
  3. 3.Department of Biomedical EngineeringVanderbilt UniversityNashvilleUSA

Personalised recommendations