Predictive models for bariatric surgery risks with imbalanced medical datasets

  • Talayeh RazzaghiEmail author
  • Ilya Safro
  • Joseph Ewing
  • Ehsan Sadrfaridpour
  • John D. Scott
Original Research


Bariatric surgery (BAR) has become a popular treatment for type 2 diabetes mellitus which is among the most critical obesity-related comorbidities. Patients who have bariatric surgery, are exposed to complications after surgery. Furthermore, the mid- to long-term complications after bariatric surgery can be deadly and increase the complexity of managing safety of these operations and healthcare costs. Current studies on BAR complications have mainly used risk scoring for identifying patients who are more likely to have complications after surgery. Though, these studies do not take into consideration the imbalanced nature of the data where the size of the class of interest (patients who have complications after surgery) is relatively small. We propose the use of imbalanced classification techniques to tackle the imbalanced bariatric surgery data: synthetic minority oversampling technique (SMOTE), random undersampling, and ensemble learning classification methods including Random Forest, Bagging, and AdaBoost. Moreover, we improve classification performance through using Chi-squared, Information Gain, and Correlation-based feature selection techniques. We study the Premier Healthcare Database with focus on the most-frequent complications including Diabetes, Angina, Heart Failure, and Stroke. Our results show that the ensemble learning-based classification techniques using any feature selection method mentioned above are the best approach for handling the imbalanced nature of the bariatric surgical outcome data. In our evaluation, we find a slight preference toward using SMOTE method compared to the random undersampling method. These results demonstrate the potential of machine-learning tools as clinical decision support in identifying risks/outcomes associated with bariatric surgery and their effectiveness in reducing the surgery complications as well as improving patient care.


Imbalanced data Risk prediction Clinical decision support Bariatric surgery 



This work was funded in part by Clemson University—Greenville Healthcare System postdoctoral program.

Supplementary material

10479_2019_3156_MOESM1_ESM.pdf (63 kb)
Supplementary material 1 (pdf 62 KB)


  1. Alexe, S., Blackstone, E., Hammer, P. L., Ishwaran, H., Lauer, M. S., & Snader, C. E. P. (2003). Coronary risk prediction by logical analysis of data. Annals of Operations Research, 119(1–4), 15–42.Google Scholar
  2. Almdal, T., Scharling, H., Jensen, J. S., & Vestergaard, H. (2004). The independent effect of type 2 diabetes mellitus on ischemic heart disease, stroke, and death: A population-based study of 13,000 men and women with 20 years of follow-up. Archives of Internal Medicine, 164(13), 1422–1426.Google Scholar
  3. American Diabetes Association. (2006). Diagnosis and classification of diabetes mellitus. Diabetes Care, 29(Supplement 1), S43–S48.Google Scholar
  4. American Diabetes Association. (2015). Classification and diagnosis of diabetes. Diabetes Care, 38(Supplement 1), S8–S16.Google Scholar
  5. Batista, G. E., Prati, R. C., & Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD Explorations Newsletter, 6(1), 20–29.Google Scholar
  6. Blanco, R., Larrañaga, P., Inza, I., & Sierra, B. (2004). Gene selection for cancer classification using wrapper approaches. International Journal of Pattern Recognition and Artificial Intelligence, 18(08), 1373–1390.Google Scholar
  7. Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140.Google Scholar
  8. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.Google Scholar
  9. Brolin, R. (1996). Gastrointestinal surgery for severe obesity. Nutrition, 12(6), 403–404.Google Scholar
  10. Buchwald, H. (2005). Bariatric surgery for morbid obesity: Health implications for patients, health professionals, and third-party payers. Journal of the American College of Surgeons, 200(4), 593–604.Google Scholar
  11. Buchwald, H., Avidor, Y., Braunwald, E., Jensen, M. D., Pories, W., Fahrbach, K., et al. (2004). Bariatric surgery: A systematic review and meta-analysis. JAMA, 292(14), 1724–1737.Google Scholar
  12. Buchwald, H., Estok, R., Fahrbach, K., Banel, D., Jensen, M. D., Pories, W. J., et al. (2009). Weight and type 2 diabetes after bariatric surgery: Systematic review and meta-analysis. The American Journal of Medicine, 122(3), 248–256.Google Scholar
  13. Cawley, J., & Meyerhoefer, C. (2012). The medical care costs of obesity: An instrumental variables approach. Journal of Health Economics, 31(1), 219–230.Google Scholar
  14. Centers for Disease Control and Prevention. (2011). National diabetes fact sheet: National estimates and general information on diabetes and prediabetes in the United States, 2011. Atlanta, GA: US department of health and human services, centers for disease control and prevention, 201(1).Google Scholar
  15. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357.Google Scholar
  16. Daousi, C., Casson, I., Gill, G., MacFarlane, I., Wilding, J., & Pinkney, J. (2006). Prevalence of obesity in type 2 diabetes in secondary care: Association with cardiovascular risk factors. Postgraduate Medical Journal, 82(966), 280–284.Google Scholar
  17. Deeba, F., Mohammed, S. K., Bui, F. M., & Wahid, K. A. (2016). An empirical study on the effect of imbalanced data on bleeding detection in endoscopic video. In 2016 IEEE 38th annual international conference of the engineering in medicine and biology society (EMBC) (pp. 2598–2601). IEEE.Google Scholar
  18. DeMaria, E. J., Portenier, D., & Wolfe, L. (2007). Obesity surgery mortality risk score: Proposal for a clinically useful score to predict mortality risk in patients undergoing gastric bypass. Surgery for Obesity and Related Diseases, 3(2), 134–140.Google Scholar
  19. Fan, Y. J., & Chaovalitwongse, W. A. (2010). Optimizing feature selection to improve medical diagnosis. Annals of Operations Research, 174(1), 169–183.Google Scholar
  20. Freund, Y., & Schapire, R. E. (1995). A desicion-theoretic generalization of on-line learning and an application to boosting. In European conference on computational learning theory (pp. 23–37). Springer.Google Scholar
  21. Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning. Springer series in statistics (Vol. 1). Berlin: Springer.Google Scholar
  22. Galar, M., Fernandez, A., Barrenechea, E., Bustince, H., & Herrera, F. (2012). A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42(4), 463–484.Google Scholar
  23. Galar, M., Fernández, A., Barrenechea, E., & Herrera, F. (2013). EUSBoost: Enhancing ensembles for highly imbalanced data-sets by evolutionary undersampling. Pattern Recognition, 46(12), 3460–3471.Google Scholar
  24. Grundy, S., Barondess, J., Bellegie, N., Fromm, H., Greenway, F., Halsted, C., et al. (1991). Gastrointestinal surgery for severe obesity. Annals of Internal Medicine, 115(12), 956–961.Google Scholar
  25. Gu, Q., Zhu, L., & Cai, Z. (2009). Evaluation measures of the classification performance of imbalanced data sets. In International symposium on intelligence computation and applications (pp. 461–471). Springer.Google Scholar
  26. Hall, M. A. (1999). Correlation-based feature selection for machine learning. Ph.D. thesis, The University of Waikato.Google Scholar
  27. Hall, M. A. (2000). Correlation-based feature selection of discrete and numeric class machine learning. University of Waikato, Department of Computer Science.Google Scholar
  28. Inza, I., Larrañaga, P., Blanco, R., & Cerrolaza, A. J. (2004). Filter versus wrapper gene selection approaches in DNA microarray domains. Artificial Intelligence in Medicine, 31(2), 91–103.Google Scholar
  29. Inza, I., Larrañaga, P., Etxeberria, R., & Sierra, B. (2000). Feature subset selection by bayesian network-based optimization. Artificial Intelligence, 123(1–2), 157–184.Google Scholar
  30. Jirapech-Umpai, T., & Aitken, S. (2005). Feature selection and classification for microarray data analysis: Evolutionary methods for identifying predictive genes. BMC Bioinformatics, 6(1), 148.Google Scholar
  31. Johnson, B. L., Blackhurst, D. W., Latham, B. B., Cull, D. L., Bour, E. S., Oliver, T. L., et al. (2013). Bariatric surgery is associated with a reduction in major macrovascular and microvascular complications in moderately to severely obese patients with type 2 diabetes mellitus. Journal of the American College of Surgeons, 216(4), 545–556.Google Scholar
  32. Johnson, R. J., Johnson, B. L., Blackhurst, D. W., Bour, E. S., Cobb, W. S., Carbonell, A. M., et al. (2012). Bariatric surgery is associated with a reduced risk of mortality in morbidly obese patients with a history of major cardiovascular events. The American Surgeon, 78(6), 685–692.Google Scholar
  33. Kannel, W. B., & McGee, D. L. (1979). Diabetes and cardiovascular disease: The Framingham study. JAMA, 241(19), 2035–2038.Google Scholar
  34. Karegowda, A. G., Manjunath, A., & Jayaram, M. (2010). Comparative study of attribute selection using gain ratio and correlation based feature selection. International Journal of Information Technology and Knowledge Management, 2(2), 271–277.Google Scholar
  35. Khalilia, M., Chakraborty, S., & Popescu, M. (2011). Predicting disease risks from highly imbalanced data using random forest. BMC Medical Informatics and Decision Making, 11(1), 51.Google Scholar
  36. King, G., & Zeng, L. (2001). Logistic regression in rare events data. Political Analysis, 9(2), 137–163.Google Scholar
  37. Liaw, A., & Wiener, M. (2002). Classification and regression by randomforest. R News, 2(3), 18–22.Google Scholar
  38. Li, L., Weinberg, C. R., Darden, T. A., & Pedersen, L. G. (2001). Gene selection for sample classification based on gene expression data: Study of sensitivity to choice of parameters of the GA/KNN method. Bioinformatics, 17(12), 1131–1142.Google Scholar
  39. López, V., Fernández, A., García, S., Palade, V., & Herrera, F. (2013). An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics. Information Sciences, 250, 113–141.Google Scholar
  40. Ogden, C. L., Carroll, M. D., Fryar, C. D., & Flegal, K. M. (2015). Prevalence of obesity among adults and youth: United States, 2011–2014. NCHS Data Brief, 219(219), 1–8.Google Scholar
  41. Ooi, C., & Tan, P. (2003). Genetic algorithms applied to multi-class prediction for the analysis of gene expression data. Bioinformatics, 19(1), 37–44.Google Scholar
  42. Polikar, R. (2006). Ensemble based systems in decision making. IEEE Circuits and Systems Magazine, 6(3), 21–45.Google Scholar
  43. Pories, W. J. (2008). Bariatric surgery: Risks and rewards. The Journal of Clinical Endocrinology and Metabolism, 93(11 Supplement 1), s89–s96.Google Scholar
  44. Quinlan, J. R. (2014). C4.5: Programs for machine learning. Amsterdam: Elsevier.Google Scholar
  45. Razzaghi, T., Safro, I. (2015). Scalable multilevel support vector machines. In ICCS (pp. 2683–2687).Google Scholar
  46. Razzaghi, T., Roderick, O., Safro, I., & Marko, N. (2016). Multilevel weighted support vector machine for classification on healthcare data with missing values. PLoS ONE, 11(5), e0155,119.Google Scholar
  47. Rokach, L. (2010). Ensemble-based classifiers. Artificial Intelligence Review, 33(1), 1–39.Google Scholar
  48. Roumani, Y. F., May, J. H., Strum, D. P., & Vargas, L. G. (2013). Classifying highly imbalanced ICU data. Health Care Management Science, 16(2), 119–128.Google Scholar
  49. Roumani, Y. F., Roumani, Y., Nwankpa, J. K., & Tanniru, M. (2018). Classifying readmissions to a cardiac intensive care unit. Annals of Operations Research, 263(1–2), 429–451.Google Scholar
  50. Saeys, Y., Inza, I., & Larrañaga, P. (2007). A review of feature selection techniques in bioinformatics. Bioinformatics, 23(19), 2507–2517.Google Scholar
  51. Sarker, A., & Gonzalez, G. (2015). Portable automatic text classification for adverse drug reaction detection via multi-corpus training. Journal of Biomedical Informatics, 53, 196–207.Google Scholar
  52. Schapire, R. E. (1990). The strength of weak learnability. Machine Learning, 5(2), 197–227.Google Scholar
  53. Şeref, O., Razzaghi, T., & Xanthopoulos, P. (2017). Weighted relaxed support vector machines. Annals of Operations Research, 249(1–2), 235–271.Google Scholar
  54. Stamler, J., Vaccaro, O., Neaton, J. D., & Wentworth, D. (1993). Diabetes, other risk factors, and 12-yr cardiovascular mortality for men screened in the multiple risk factor intervention trial. Diabetes Care, 16(2), 434–444.Google Scholar
  55. Taft, L., Evans, R. S., Shyu, C., Egger, M., Chawla, N., Mitchell, J., et al. (2009). Countering imbalanced datasets to improve adverse drug event predictive models in labor and delivery. Journal of Biomedical Informatics, 42(2), 356–364.Google Scholar
  56. Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data mining: Practical machine learning tools and techniques. Burlington: Morgan Kaufmann.Google Scholar
  57. World Health Organization. (2016). Global report on diabetes. World Health Organization.Google Scholar
  58. Xiong, M., Fang, X., & Zhao, J. (2001). Biomarker identification by feature wrappers. Genome Research, 11(11), 1878–1887.Google Scholar
  59. Yang, Y., & Pedersen, J. O. (1997). A comparative study on feature selection in text categorization. ICML, 97, 412–420.Google Scholar
  60. Zadrozny, B., Langford, J., & Abe, N. (2003). Cost-sensitive learning by cost-proportionate example weighting. In Third IEEE international conference on data mining, 2003. ICDM 2003 (pp. 435–442). IEEE.Google Scholar
  61. Zheng, B., Zhang, J., Yoon, S. W., Lam, S. S., Khasawneh, M., & Poranki, S. (2015). Predictive modeling of hospital readmissions using metaheuristics and data mining. Expert Systems with Applications, 42(20), 7110–7120.Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Talayeh Razzaghi
    • 1
    Email author
  • Ilya Safro
    • 2
  • Joseph Ewing
    • 3
  • Ehsan Sadrfaridpour
    • 2
  • John D. Scott
    • 4
  1. 1.Department of Industrial Engineering, EC III, Room 288, MSC 4230New Mexico State UniversityLas CrucesUSA
  2. 2.School of ComputingClemson UniversityClemsonUSA
  3. 3.Quality Management DepartmentGreenville Health SystemGreenvilleUSA
  4. 4.Department of SurgeryGreenville Hospital System University Medical CenterGreenvilleUSA

Personalised recommendations