Skip to main content
SpringerLink
Log in

Random forest modeling using socioeconomic distress predicts hernia repair approach

  • 2020 SAGES Oral
  • Published:
Surgical Endoscopy Aims and scope Submit manuscript

Abstract

Background

Surgical techniques for abdominal wall hernia repair have advanced, yet it is unclear if all patient populations experience these innovations equally. We hypothesized that in patients undergoing abdominal wall herniorrhaphy, there would be socioeconomic variation between robotic, laparoscopic, and open approaches.

Methods

We performed a retrospective review of patients undergoing abdominal wall herniorrhaphy at a tertiary care center from 2013 through 2019. Patients were stratified by approach: laparoscopic (LH), open (OH), or robotic (RH). Insurance type was categorized as private, Medicare, or Medicaid/uninsured. Using zip code data, we obtained a Distressed Communities Index (DCI), which is comprised of 7 unique socioeconomic variables. We employed random forest (RF) modeling to predict surgical approach and determined each factor’s variable importance (VI) for our model.

Results

There were 559 patients; 39.7% (n = 222) LH, 33.3% (n = 186) OH, and 27% (n = 151) RH. The DCI (p < 0.01) and rates of poverty (p = 0.01), adults without diplomas (p < 0.01), and unemployment (p < 0.01) were highest in the OH group while job growth (p = 0.02) and median income ratio (p < .01) were highest in the RH group. The LH group had a greater proportion of privately insured patients than Medicaid/ uninsured patients (43.4% vs 15.9%, p < 0.01). The most important variables identified by our RF model were job growth (for RH), insurance type (for LH), and no high school diploma (for OH).

Conclusion

Insurance type, job growth, and educational attainment may influence operative approach and can contribute to the existing disparities in hernia surgery. Surgeons should address these inequalities and commit to parity in the delivery of surgical care.

Graphic abstract

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. Nunez MF, Ortega G, Souza Mota LG, Olufajo OA, Altema DW, Fullum TM, Tran D (2019) Socioeconomic disparities in the complexity of hernias evaluated at Emergency Departments across the United States. Am J Surg 218:551–559

    Article  Google Scholar 

  2. Madenci AL, Wolf LL, Jiang W, Koehlmoos TP, Learn PA, Haider AH, Smink DS (2018) Contemporary factors associated with the use of laparoscopy for inguinal hernia repair among department of defense beneficiaries. Mil Med 183:e420–e426

    Article  Google Scholar 

  3. Vu JV, Gunaseelan V, Krapohl GL, Englesbe MJ, Campbell DA, Dimick JB, Telem DA (2019) Surgeon utilization of minimally invasive techniques for inguinal hernia repair: a population-based study. Surg Endosc 33:486–493

    Article  Google Scholar 

  4. Huntington CR, Cox TC, Blair LJ, Prasad T, Lincourt AE, Heniford BT, Augenstein VA (2016) Nationwide variation in outcomes and cost of laparoscopic procedures. Surg Endosc 30:934–946

    Article  Google Scholar 

  5. Armijo PR, Pokala B, Flores L, Hosein S, Oleynikov D (2020) Current state of robotic use in inguinal hernia repair: a survey of minimally invasive hernia surgeons. Updates Surg 72:179–184

    Article  Google Scholar 

  6. Sheetz KH, Dimick JB (2019) Is it time for safeguards in the adoption of robotic surgery? JAMA 321:1971

    Article  Google Scholar 

  7. Prabhu AS, Carbonell A, Hope W et al (2020) Robotic inguinal vs transabdominal laparoscopic inguinal hernia repair. JAMA Surg. https://doi.org/10.1001/jamasurg.2020.0034

    Article  PubMed  PubMed Central  Google Scholar 

  8. Wilson CB (2006) Adoption of new surgical technology. BMJ 332:112–114

    Article  Google Scholar 

  9. Tracy B (2017) Principles of coding and reimbursement for surgeons. Princ Coding Reimburse Surg. https://doi.org/10.1007/978-3-319-43595-4

    Article  Google Scholar 

  10. Wood KL, Haider SF, Bui A, Leitman IM (2020) Access to common laparoscopic general surgical procedures: do racial disparities exist? Surg Endosc 34:1376–1386

    Article  Google Scholar 

  11. Economic Innovation Group (2017) Distressed Communities Index (DCI): Methodology. https://eig.org/dci/methodology. Accessed 1 Aug 2019

  12. Braveman PA, Cubbin C, Egerter S, Chideya S, Marchi KS, Metzler M, Posner S (2005) Socioeconomic status in health research. JAMA 294:2879

    Article  CAS  Google Scholar 

  13. Kleinberg EM (2000) On the algorithmic implementation of stochastic discrimination. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/34.857004

    Article  Google Scholar 

  14. Breiman L (2001) Random forests. Mach Learn 45:5–32

    Article  Google Scholar 

  15. Breiman L (1996) Bagging predictors. Mach Learn 24:123–140

    Google Scholar 

  16. Saltelli A (2002) Making best use of model evaluations to compute sensitivity indices. Comput Phys Commun 145:280–297

    Article  CAS  Google Scholar 

  17. Earl DJ, Deem MW (2008) Monte carlo simulations. Methods Mol Biol 443:25–36

    Article  CAS  Google Scholar 

  18. Pearce J, Ferrier S (2000) Evaluating the predictive performance of habitat models developed using logistic regression. Ecol Modell 133:225–245

    Article  Google Scholar 

  19. Stronks K, van de Mheen H, van den Bos J, Mackenbach J (1997) The interrelationship between income, health and employment status. Int J Epidemiol 26:592–600

    Article  CAS  Google Scholar 

  20. Tatebe LC, Gray R, Tatebe K, Garcia F, Putty B (2018) Socioeconomic factors and parity of access to robotic surgery in a county health system. J Robot Surg 12:35–41

    Article  Google Scholar 

  21. Smink DS, Paquette IM, Finlayson SRG (2009) Utilization of laparoscopic and open inguinal hernia repair: a population-based analysis. J Laparoendosc Adv Surg Tech 19:745–748

    Article  Google Scholar 

  22. Ecker BL, Kuo LEY, Simmons KD, Fischer JP, Morris JB, Kelz RR (2016) Laparoscopic versus open ventral hernia repair: longitudinal outcomes and cost analysis using statewide claims data. Surg Endosc 30:906–915

    Article  Google Scholar 

  23. Calfee RP, Shah CM, Canham CD, Wong AHW, Gelberman RH, Goldfarb CA (2012) The influence of insurance status on access to and utilization of a tertiary hand surgery referral center. J Bone Joint Surg Am 94:2177–2184

    Article  Google Scholar 

  24. Bowman K (2010) Impact of race and socioeconomic status on presentation and management of ventral hernias. Arch Surg 145:776

    Article  Google Scholar 

  25. Stewart CL, Dumitra S, Nota C, Ituarte PHG, Melstrom LG, Woo Y, Singh G, Fong Y, Nathan H, Warner SG (2019) Hospital factors strongly influence robotic use in general surgery. Surgery 166:867–872

    Article  Google Scholar 

  26. LaPar DJ, Bhamidipati CM, Mery CM, Stukenborg GJ, Jones DR, Schirmer BD, Kron IL, Ailawadi G (2010) Primary payer status affects mortality for major surgical operations. Trans Meet Am Surg Assoc 128:148–156

    Google Scholar 

  27. Henny CP, Hofland J (2005) Laparoscopic surgery: pitfalls due to anesthesia, positioning, and pneumoperitoneum. Surg Endosc 19:1163–1171

    Article  CAS  Google Scholar 

  28. Haynes SR, Lawler PG (1995) An assessment of the consistency of ASA physical status classification allocation. Anaesthesia 50:195–199

    Article  CAS  Google Scholar 

  29. Scott JW, Havens JM, Wolf LL, Zogg CK, Rose JA, Salim A, Haider AH (2017) Insurance status is associated with complex presentation among emergency general surgery patients. Surgery 161:320–328

    Article  Google Scholar 

  30. Hsiang W, McGeoch C, Lee S, Cheung W, Becher R, Davis KA, Schuster KM (2018) The effect of insurance type on access to inguinal hernia repair under the Affordable Care Act. Surgery 164:201–205

    Article  Google Scholar 

  31. Yim CK, Shumate L, Barnett SH, Leitman IM (2018) Health literacy assessment and patient satisfaction in surgical practice. Ann Med Surg 35:25–28

    Article  Google Scholar 

  32. Wright JP, Edwards GC, Goggins K, Tiwari V, Maiga A, Moses K, Kripalani S, Idrees K (2018) Association of health literacy with postoperative outcomes in patients undergoing major abdominal surgery. JAMA Surg 153:137

    Article  Google Scholar 

  33. De Oliveira GS, McCarthy RJ, Wolf MS, Holl J (2015) The impact of health literacy in the care of surgical patients: a qualitative systematic review. BMC Surg 15:86

    Article  Google Scholar 

  34. Chew LD, Bradley KA, Flum DR, Cornia PB, Koepsell TD (2004) The impact of low health literacy on surgical practice. Am J Surg 188:250–253

    Article  Google Scholar 

  35. Mahoney ST, Tawfik-Sexton D, Strassle PD, Farrell TM, Duke MC (2018) Effects of education and health literacy on postoperative hospital visits in bariatric surgery. J Laparoendosc Adv Surg Tech 28:1100–1104

    Article  Google Scholar 

  36. Roumm AR, Pizzi L, Goldfarb NI, Cohn H (2005) Minimally invasive: minimally reimbursed? an examination of six laparoscopic surgical procedures. Surg Innov 12:261–287

    Article  Google Scholar 

Download references

Funding

This research did not receive any specific funding from the public, commercial, or not-for-profit sectors.

Author information

Authors and Affiliations

  1. Department of Surgery, Emory University School of Medicine, Glenn Memorial Building, 69 Jesse Hill Jr. Drive SE, Atlanta, GA, 30303, USA

    Brett M. Tracy & Randi N. Smith

  2. Department of Surgery, Memorial University Medical Center, Savannah, GA, 31404, USA

    Timothy M. Finnegan & Christopher K. Senkowski

Authors
  1. Brett M. Tracy
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Timothy M. Finnegan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Randi N. Smith
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Christopher K. Senkowski
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Brett M. Tracy.

Ethics declarations

Disclosures

Drs. Tracy, Finnegan, Smith, and Senkowski 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

Tracy, B.M., Finnegan, T.M., Smith, R.N. et al. Random forest modeling using socioeconomic distress predicts hernia repair approach. Surg Endosc 35, 3890–3895 (2021). https://doi.org/10.1007/s00464-020-07860-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00464-020-07860-6

Keywords

Search

Navigation