Skip to main content

Predictive Analytics for Determining Patients’ Vitamin D Status

  • Conference paper
  • First Online:
  • 1236 Accesses

Part of the book series: Studies in Big Data ((SBD,volume 53))

Abstract

Vitamin D level has an important role in bone and mineral metabolic. A deficiency of this vitamin is largely described in safe persons, but less studied in hospitalized patients. Recently, we can observe an increase in vitamin D tests above the worldwide due to a possible influence of vitamin D deficiency in several diseases, with the important costs to healthcare systems.

The main purpose of this study is the prediction of vitamin D levels and understand how this vitamin correlates with some biochemical parameters. The participants of this study are patients from the nephrology department of the CHU Mohamed VI in the northeast of Morocco (October 2015 and June 2017), these patients have a valid value for vitamin D and other biochemical parameters such as High-Density Lipoprotein Cholesterol (HDL-C), Albumin among others. Furthermore, the population contains 141 men and 157 women aged in the average (standard deviation) of 53 (17) and 55(18) years respectively. A Spearman coefficient correlation was calculated to evaluate the correlation between all these parameters. Besides, an ordinal logistic regression was performed to determine the association between vitamin D and biochemical parameters. And a nonlinear effect of continuous variables was performed with a restricted cubic spline.

The vitamin D levels vary according to gender. About 96% of patients had a hypovitaminosis D. A little less than the half of them had a vitamin D deficiency. In unadjusted ordinal regression, Sex, albumin, ASAT, total bilirubin, calcium, total protein, alkaline reserve, sodium, and free T4 hormone have a positive association with the odds of being in an upper vitamin D category. Otherwise, PTH bio intact had a nonlinear relationship with vitamin D status. The area under the curve predicting the vitamin D status was 0.85 with the ordinal spline regression model versus 0.81 with the ordinal regression model.

This model had could predict the vitamin D status in hospitalized population, but it needs complement information about patients which are essential for the prediction of vitamin D status like clinical variables.

To sum up, vitamin D deficiency was highly prevalent in hospitalized patients of the nephrology department despite the sunny weather in Morocco.

This is a preview of subscription content, log in via an institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD   219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Christodoulou, S., Goula, T., Ververidis, A., Drosos, G.: Vitamin D and bone disease. Biomed. Res. Int. 396541 (2013). https://doi.org/10.1155/2013/396541

  2. Visser, M., Deeg, D.J.H., Lips, P., Longitudinal Aging Study Amsterdam: Low vitamin D and high parathyroid hormone levels as determinants of loss of muscle strength and muscle mass (Sarcopenia): the longitudinal aging study Amsterdam. J. Clin. Endocrinol Metab. 88, 5766–5772 (2003). https://doi.org/10.1210/jc.2003-030604

  3. Pilz, S., Verheyen, N., Grübler, M.R., et al.: Vitamin D and cardiovascular disease prevention. Nat. Rev. Cardiol. 13, 404–417 (2016). https://doi.org/10.1038/nrcardio.2016.73

    Article  Google Scholar 

  4. Wang, T.J., Pencina, M.J., Booth, S.L., et al.: Vitamin D deficiency and risk of cardiovascular disease. Circulation 117, 503–511 (2008). https://doi.org/10.1161/CIRCULATIONAHA.107.706127

    Article  Google Scholar 

  5. Melamed, M.L., Michos, E.D., Post, W., Astor, B.: 25-Hydroxyvitamin D levels and the risk of mortality in the general population. Arch. Intern. Med. 168, 1629–1637 (2008). https://doi.org/10.1001/archinte.168.15.1629

    Article  Google Scholar 

  6. Pearce, S.H.S., Cheetham, T.D.: Diagnosis and management of vitamin D deficiency. BMJ 340, b5664 (2010)

    Article  Google Scholar 

  7. Al-Badr, W., Martin, K.J.: Vitamin D and kidney disease. Clin. J. Am. Soc. Nephrol. 3, 1555–1560 (2008). https://doi.org/10.2215/CJN.01150308

    Article  Google Scholar 

  8. von Domarus, C., Brown, J., Barvencik, F., et al.: How much vitamin D do we need for skeletal health? Clin. Orthop. Relat. Res. 469, 3127–3133 (2011). https://doi.org/10.1007/s11999-011-1880-4

    Article  Google Scholar 

  9. Allali, F., El Aichaoui, S., Khazani, H., et al.: High prevalence of hypovitaminosis D in Morocco: relationship to lifestyle, physical performance, bone markers, and bone mineral density. Semin. Arthritis Rheum. 38, 444–451 (2009). https://doi.org/10.1016/j.semarthrit.2008.01.009

    Article  Google Scholar 

  10. Gallagher, J.C.: Vitamin D and aging. Endocrinol. Metab. Clin. North Am. 42, 319–332 (2013). https://doi.org/10.1016/j.ecl.2013.02.004

    Article  Google Scholar 

  11. Metzger, M., Houillier, P., Gauci, C., et al.: Relation between circulating levels of 25(OH) vitamin D and parathyroid hormone in chronic kidney disease: quest for a threshold. J. Clin. Endocrinol. Metab. 98, 2922–2928 (2013). https://doi.org/10.1210/jc.2013-1294

    Article  Google Scholar 

  12. Mackawy, A.M.H., Al-Ayed, B.M., Al-Rashidi, B.M.: Vitamin D deficiency and its association with thyroid disease. Int. J. Health Sci. (Qassim) 7, 267–275 (2013)

    Article  Google Scholar 

  13. Ahmed, M.M.: Association of renal failure with thyroid dysfunction: a retrospective cohort study. Saudi J. Kidney Dis. Transpl. 25, 1017–1025 (2014). https://doi.org/10.4103/1319-2442.139902

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Souad Bechrouri .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Bechrouri, S., Monir, A., Mraoui, H., Sebbar, EH., Saalaoui, E., Choukri, M. (2019). Predictive Analytics for Determining Patients’ Vitamin D Status. In: Farhaoui, Y., Moussaid, L. (eds) Big Data and Smart Digital Environment. ICBDSDE 2018. Studies in Big Data, vol 53. Springer, Cham. https://doi.org/10.1007/978-3-030-12048-1_32

Download citation

Publish with us

Policies and ethics