Skip to main content

Advertisement

SpringerLink
Log in

What We Are Missing: Using Machine Learning Models to Predict Vitamin C Deficiency in Patients with Metabolic and Bariatric Surgery

  • Original Contributions
  • Published:
Obesity Surgery Aims and scope Submit manuscript

Abstract

Purpose

Vitamin C (VC) is implicated in many physiological pathways. Vitamin C deficiency (VCD) can compromise the health of patients with metabolic and bariatric surgery (patients). As symptoms of VCD are elusive and data on VCD in patients is scarce, we aim to characterize patients with measured VC levels, investigate the association of VCD with other lab abnormalities, and create predictive models of VCD using machine learning (ML).

Methods

A retrospective chart review of patients seen from 2017 to 2021 at a tertiary care center in Northeastern USA was conducted. A 1:4 case mix of patients with VC measured to a random sample of patients without VC measured was created for comparative purposes. ML models (BayesNet and random forest) were used to create predictive models and estimate the prevalence of VCD patients.

Results

Of 5946 patients reviewed, 187 (3.1%) had VC measures, and 73 (39%) of these patients had VC<23 μmol/L(VCD. When comparing patients with VCD to patients without VCD, the ML algorithms identified a higher risk of VCD in patients deficient in vitamin B1, D, calcium, potassium, iron, and blood indices. ML models reached 70% accuracy. Applied to the testing sample, a “true” VCD prevalence of ~20% was predicted, among whom ~33% had scurvy levels (VC<11 μmol/L).

Conclusion

Our models suggest a much higher level of patients have VCD than is reflected in the literature. This indicates a high proportion of patients remain potentially undiagnosed for VCD and are thus at risk for postoperative morbidity and mortality.

Graphical 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
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Johnson LE. Vitamin C Deficiency. Merck & Co., Inc.  2022; [cited 2022 Oct 9]. Available from: https://www.merckmanuals.com/professional/nutritional-disorders/vitamin-deficiency,-dependency,-and-toxicity/vitamin-c-deficiency.

  2. Nosewicz J, Spaccarelli N, Roberts KM, et al. The epidemiology, impact, and diagnosis of micronutrient nutritional dermatoses part 1: Zinc, selenium, copper, vitamin A, and vitamin C. J Am Acad Dermatol. 2022;86(2):267–78.

    Article  CAS  PubMed  Google Scholar 

  3. Hansen EP, Metzsche C, Henningsen E, Toft P. Severe scurvy after gastric bypass surgery and a poor postoperative diet. J Clin Med Res. 2012;4(2):135.

    PubMed  PubMed Central  Google Scholar 

  4. Riess KP, Farnen JP, Lambert PJ, Mathiason MA, Kothari SN. Ascorbic acid deficiency in bariatric surgical population. Surg Obes Relat Dis. 2009;5(1):81–6.

    Article  PubMed  Google Scholar 

  5. Padayatty SJ, Levine M. Vitamin C: the known and the unknown and Goldilocks. Oral Dis. 2016;22(6):463–93.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Spoelstra-de Man A, Oudemans-van Straaten H, Elbers P. Vitamin C and thiamine in critical illness. BJA Education. 2019;19(9):290.

    Article  CAS  PubMed Central  Google Scholar 

  7. Rowe S, Carr AC. Global vitamin C status and prevalence of deficiency: a cause for concern? Nutrients. 2020;12(7).

  8. Khalife R, Grieco A, Khamisa K, Tinmouh A, McCudden C, Saidenberg E. Scurvy, an old story in a new time: the hematologist’s experience. Blood Cells Mol Dis. 2019;76:40–4.

    Article  PubMed  Google Scholar 

  9. Hemila H, Chalker E. Vitamin C can shorten the length of stay in the ICU: a meta-analysis. Nutrients. 2019;11(4):708.

    Article  CAS  PubMed Central  Google Scholar 

  10. Carr AC, Rowe S. The emerging role of vitamin C in the prevention and treatment of COVID-19. Nutrients. 2020;12(11).

  11. Carr Ac MC. The role of vitamin C in the treatment of pain: new insights. J Transl Med. 2017;15(1):77.

    Article  PubMed  PubMed Central  Google Scholar 

  12. Carr AC, Cook J. Intravenous vitamin C for cancer therapy - identifying the current gaps in our knowledge. Front Physiol. 2018;9:1182.

    Article  PubMed  PubMed Central  Google Scholar 

  13. D'Aniello C, Cermola F, Patriarca EJ, Minchiotti G. Vitamin C in stem cell biology: impact on extracellular matrix homeostasis and epigenetics. Stem Cells Int. 2017;2017:8936156.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Dosedel M, Jirkovsky E, Macakova K, et al. Vitamin C-sources, physiological role, kinetics, deficiency, use, toxicity, and determination. Nutrients. 2021;13(2):615.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Maxfield L, Crane JS. Vitamin C deficiency. In: StatPearls [Internet]. Treasure Island (FL): StatPearls; 2022. Available from: https://www.ncbi.nlm.nih.gov/books/NBK493187/.

  16. Crandon JH, Landau B, Mikal S, Balmanno J, Jefferson M, Mahoney N. Ascorbic acid economy in surgical patients as indicated by blood ascorbic acid levels. N Engl J Med. 1958;258(3):105–13.

    Article  CAS  PubMed  Google Scholar 

  17. Lewis CA, de Jersey S, Hopkins G, Hickman I, Osland E. Does bariatric surgery cause vitamin A, B1, C or E deficiency? A systematic review. Obes Surg. 2018;28:3640–57.

    Article  PubMed  Google Scholar 

  18. Hujoel PP, Hujoel MLA. Vitamin C and scar strength: analysis of a historical trial and implications for collagen-related pathologies. Am J Clin Nutr. 2022;115(1):8–17.

    Article  PubMed  Google Scholar 

  19. Travica N, Ried K, Hudson I, Scholey A, Pipingas A, Sali A. The effects of surgery on plasma/serum vitamin C concentrations: a systematic review and meta-analysis. Br J Nutr. 2020;4:1–39.

    Google Scholar 

  20. Boulesteix AL, Schmid M. Machine learning versus statistical modeling. Biom J. 2014;56(4):588–93.

    Article  Google Scholar 

  21. Lalehzarian SP, Gowd AK, Liu JN. Machine learning in orthopaedic surgery. World J Orthop. 2021;12(9):685.

    Article  PubMed  PubMed Central  Google Scholar 

  22. Balch JA, Delitto D, Tighe PJ, et al. Machine learning applications in solid organ transplantation and related complications. Front Immunol. 2021;3707:739728.

    Article  Google Scholar 

  23. Hashimoto DA, Rosman G, Rus D, Meireles OR. Artificial intelligence in surgery: promises and perils. Annals of Surgery. 2018;268(1):70–6.

    Article  PubMed  Google Scholar 

  24. Peloso A, Moeckli B, Delaune V, Oldani G, Andres A, Compagnon P. Artificial intelligence: present and future potential for solid organ transplantation. Transpl Int. 2022;35:10640.

    Article  PubMed  PubMed Central  Google Scholar 

  25. Olier I, Ortega-Martorell S, Pieroni M, Lip GY. How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management. Cardiovasc Res. 2021;117(7):1700–17.

    Article  CAS  PubMed Central  Google Scholar 

  26. Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement. BMC Med. 2015;6(13):1.

    Article  Google Scholar 

  27. Parrott J, Frank L, Rabena R, Craggs-Dino L, Isom KA, Greiman L. American Society for Metabolic and Bariatric Surgery Integrated Health Nutritional Guidelines for the Surgical Weight Loss Patient 2016 Update: micronutrients. Surg Obes Relat Dis. 2017;13(5):727–41.

    Article  PubMed  Google Scholar 

  28. Camaschella C, Girelli D. The changing landscape of iron deficiency. Mol Aspects Med. 2020;75:100861.

    Article  CAS  Google Scholar 

  29. Cappellini MD, Comin-Colet J, de Francisco A, Dignass A, Doehner W, Lam CS, et al. Iron deficiency across chronic inflammatory conditions: international expert opinion on definition, diagnosis, and management. Am J Hematol. 2017;92(10):1068–78.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Cappellini MD, Musallam KM, Taher AT. Iron deficiency anaemia revisited. J Intern Med. 2020;287(2):153–70.

    Article  CAS  PubMed  Google Scholar 

  31. Benotti PN, Wood GC, Dove JT, et al. Iron deficiency is highly prevalent among candidates for metabolic surgery and may affect perioperative outcomes. Surg Obes Relat Dis. 2021;17:1692–9.

    Article  PubMed  Google Scholar 

  32. Fertrin KY. Diagnosis and management of iron deficiency in chronic inflammatory conditions (CIC): is too little iron making your patient sick? Hematology Am Soc Hematol Educ Program. 2020;2020(1):478–86.

    Article  PubMed  PubMed Central  Google Scholar 

  33. Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F. 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). 2011;42(4):463–84.

    Article  Google Scholar 

  34. Cooper GF, Herskovits E. A Bayesian method for the induction of probabilistic networks from data. Mach Learn. 1992;9(4):309–47.

    Article  Google Scholar 

  35. Breiman L. Random forests. Mach Learn. 2001;45(1):5–32.

    Article  Google Scholar 

  36. Rodriguez JD, Perez A, Lozano JA. Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Trans Pattern Anal Mach Intell. 2009;32(3):569–75.

    Article  Google Scholar 

  37. Ian H. Witten EF, Mark A Hall. Christopher J. Pal Weka 3: machine learning software in Java. 2017. In: Data mining: practical machine learning tools and techniques [Internet]. Cambridge, MA 02139: Morgan Kaufmann. fourth. [654]. Available from: https://www.cs.waikato.ac.nz/ml/weka/.

  38. Baynes JW. Aging of complex systems. Medical Biochemistry E-Book. 2018:416.

  39. Zughaier SM, Alvarez JA, Sloan JH, Konrad RJ, Tangpricha V. The role of vitamin D in regulating the iron-hepcidin-ferroportin axis in monocytes. J Clin Transl Endocrinol. 2014;1(1):e19–25.

    CAS  PubMed Central  Google Scholar 

  40. Zofkova I, Davis M, Blahos J. Trace elements have beneficial, as well as detrimental effects on bone homeostasis. Physiol Res. 2017;66(3):391.

    Article  CAS  PubMed  Google Scholar 

  41. Toxqui L, Vaquero MP. Chronic iron deficiency as an emerging risk factor for osteoporosis: a hypothesis. Nutrients. 2015;7(4):2324–44.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  42. Gaffney-Stomberg E. The impact of trace minerals on bone metabolism. Biol Trace Elem Res. 2019;188(1):26–34.

    Article  CAS  Google Scholar 

  43. Balogh E, Paragh G, Jeney V. Influence of iron on bone homeostasis. Pharmaceuticals. 2018;11(4):107.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  44. Tian T, Shao J, Shen Z, et al. Association of serum vitamin C with all-cause and cause-specific death: data from National Health and Nutrition Examination Survey (NHANES 2003-2006). Nutrition. 2022;101:111696.

    Article  PubMed  Google Scholar 

  45. Carr AC, Pullar JM, Bozonet SM, Vissers MC. Marginal ascorbate status (Hypovitaminosis C) results in an attenuated response to vitamin C supplementation. Nutrients. 2016;8(6):341.

    Article  PubMed  PubMed Central  Google Scholar 

  46. Berger MM, Shenkin A, Schweinlin A, et al. ESPEN micronutrient guideline. Clin Nutr. 2022;41(6):1357–424.

    Article  CAS  PubMed  Google Scholar 

  47. Vitamin C, Committee SotAFF. Medical Research Council. Vitamin C requirement of human adults. Lmcet; 1948.

Download references

Acknowledgements

We thank Evan M. Parrott for his graphic arts expertise, which greatly assisted the presentation at IFSO 2022 and this publication.

Author information

Authors and Affiliations

  1. Temple University Health System, 7600 Centrail Avenue, Philadelphia, PA, 19111, USA

    Julie M. Parrott

  2. Departmet of Clinical and Preventive Nutrition Sciences, Rutgers University, 65 Bergen Street, Suite 120, Newark, NJ, 07107-1709, USA

    Julie M. Parrott

  3. Faculty of Health Sciences and Wellbeing, The University of Sunderland, Edinburg Building, City Campus, Chester Road, Sunderland, SR1 3SD, UK

    Julie M. Parrott

  4. The Child Center of NY, 118-35 Queens Boulevard, 6th Floor, Forest Hills, New York, NY, 11375, USA

    Austen J. Parrott

  5. Department of Surgery, Hospital of the University of Pennsylvania, 3400 Spruce Street, Philadelphia, PA, 19104, USA

    Armaun D. Rouhi

  6. School of Health Professions, Rutgers Biomedical and Health Sciences, Reserach Tower, 836B, 675 Hoes Lane West, Piscataway, NJ, 08854, USA

    J. Scott Parrott

  7. Penn Metabolic and Bariatic Surgery and Gastrointestinal Surgery, Hospital of the University of Pennsylvania, 3400 Spruce Street, Philadelphia, PA, 19104, USA

    Kristoffel R. Dumon

Authors
  1. Julie M. Parrott
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Austen J. Parrott
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Armaun D. Rouhi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. J. Scott Parrott
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kristoffel R. Dumon
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Julie M. Parrott.

Ethics declarations

Ethics Approval

IRB # 834987.

Consent to Participate

For this type of study, formal consent is not required.

Conflict of Interest

The authors declare no competing interests.

Additional information

Publisher’s Note

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

Key Points

• VCD is harmful to numerous physiological pathways and disrupts human health.

• Vitamin B1, D, calcium, potassium, and iron deficiencies are associated with VCD.

• ML models predict a higher prevalence of VCD than previously considered in patients with MBS.

• Deficient lab indices may distinguish patients with MBS at risk for VCD.

Supplementary Information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Parrott, J.M., Parrott, A.J., Rouhi, A.D. et al. What We Are Missing: Using Machine Learning Models to Predict Vitamin C Deficiency in Patients with Metabolic and Bariatric Surgery. OBES SURG 33, 1710–1719 (2023). https://doi.org/10.1007/s11695-023-06571-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11695-023-06571-w

Keywords

Search

Navigation