Skip to main content

Advertisement

SpringerLink
Log in

Artificial neural networks for assessing the risk of urinary calcium stone among men

  • Original Paper
  • Published:
Urological Research Aims and scope Submit manuscript

Abstract

The pathophysiology of idiopathic calcium oxalate nephrolithiasis involves metabolic abnormalities. Previous studies gave conflicting results about the metabolic factors in stone formers. Artificial neural networks (ANN) are new methods based on computer programming that have outperformed conventional methods in prediction of outcomes in different medical applications. The aim of our study was to compare with ANN the clinical and biochemical parameters implicated in urinary calcium stone between stone formers (SF) and controls (C). We compared 11 clinical and biochemical variables among 119 male idiopathic calcium oxalate SF and 96 C by univariate and multivariate statistical analyses. Univariate analyses included discriminant analysis, logistic regression analysis, and ANN. For multivariate analyses, stepwise discriminant analysis and ANN were performed. Variables included age, body mass index (BMI), family history of nephrolithiasis, supersaturation with respect to calcium oxalate, calcemia, and 24-h urinary calcium, oxalate, uric acid, urea, sodium, and citrate. With univariate and multivariate analyses, ANN were as efficient as classical statistical analyses in discriminating the different parameters. The sensitivity, the specificity, and the percentage of correctly classified patients were similar in all analyses. With ANN, supersaturation (receiver operating characteristic, ROC curves index 0.73) and urea (ROC 0.72) were the most discriminant followed by family history and urinary calcium (ROC 0.67). ROC index was 0.63 for citrate, 0.61 for oxalate and urate, 0.60 for sodium and calcemia, 0.58 for age, and 0.56 for BMI, but these parameters were not statistically different between SF and C. ANN gave additional information since they made it possible to determine the cut-off values of the parameters and their predictive power. Cut-off values for being a stone former were 8.9 for supersaturation and 363 mmol/day for urinary urea with a predictive power of 0.69 and 0.70, respectively. Univariate and multivariate analysis evidenced supersaturation and 24-h urinary urea excretion as the most discriminant parameters between the two populations. In addition to high supersaturation, the negative impact of protein intake was confirmed.

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

Similar content being viewed by others

References

  1. Johnson CM, Wilson DM, O’Fallon WM et al (1979) Renal stone epidemiology: a 25-year study in Rochester, Minnesota. Kidney Int 16:624–631

    Article  PubMed  CAS  Google Scholar 

  2. Norlin A, Lindell B, Granberg PO, Lindvall N (1976) Urolithiasis: a study of its frequency. Scand J Urol Nephrol 10:150–153

    Article  PubMed  CAS  Google Scholar 

  3. Ljunghall S, Danielson BG (1984) A prospective study of renal stones recurrences. Br J Urol 56:122–124

    Article  PubMed  CAS  Google Scholar 

  4. Goodman HO, Holmes RP, Assimos DG (1995) Genetic factors in calcium oxalate disease. J Urol 153:301–307

    Article  PubMed  CAS  Google Scholar 

  5. Ginalski JM, Portmann L, Jaeger Ph (1990) Does medullary sponge kidney cause nephrolithiasis? Am J Roentgenol 155:299–302

    CAS  Google Scholar 

  6. Coe FL, Parks J, Asplin J (1992) The pathogenesis and treatment of kidney stones. N Engl J Med 327:1141–1152

    Article  PubMed  CAS  Google Scholar 

  7. Curhan G, Willett WC, Speizer FE, Stampfer MJ (2001) Twenty-four-hour urine chemistries and the risk of kidney stones among women and men. Kidney Int 59:2290–2298

    PubMed  CAS  Google Scholar 

  8. Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford

    Google Scholar 

  9. Masters T (1993) Practical neural networks recipes in C++. Academic, New York

    Google Scholar 

  10. Forsstrom JJ, Dalton KJ (1995) Artificial neural networks for decision support in clinical medicine. Ann Med 27:509–517

    Article  PubMed  CAS  Google Scholar 

  11. Bagli DJ, Agarwal SK, Venkasteswara S et al (1998) Artificial neural networks in pediatric urology: prediction of sonographic outcome following pyeloplasty. J Urol 160:980–983

    Article  PubMed  CAS  Google Scholar 

  12. Baxt WG (1995) Application of neural networks to clinical medicine. Lancet 346:1135–1138

    Article  PubMed  CAS  Google Scholar 

  13. Nafe R, Choritz H (1992) Introduction of a neuronal network as a tool for diagnostic analysis and classification based on experimental pathologic data. Exp Toxicol Pathol 44:17–24

    PubMed  CAS  Google Scholar 

  14. Bottaci L, Drew PJ, Hartley JE et al (1997) Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions. Lancet 350:469–472

    Article  PubMed  CAS  Google Scholar 

  15. Ebell MH (1993) Artificial neural networks for predicting failure to survive following in-hospital cardiopulmonary resuscitation. J Fam Pract 36:297–303

    PubMed  CAS  Google Scholar 

  16. Pofahl WE, Walczak SM, Rhone E, Izenberg SD (1998) Use of an artificial neural network to predict length of stay in acute pancreatitis. Am Surg 64:868–872

    PubMed  CAS  Google Scholar 

  17. Le Goff JM, Lavayssiere L, Rouëssé J, Spyrato F (2000) Nonlinear discriminant analysis and prognostic factor classification in node-negative primary breast cancer using probabilistic neural networks. Anticancer Res 20:2213–2218

    PubMed  CAS  Google Scholar 

  18. Brown CM, Ackerman DK, Purich DL (1994) EQUIL93: a tool for experimental and clinical urolithiasis. Urol Res 22:119–126

    Article  PubMed  CAS  Google Scholar 

  19. Specht D (1990) Probabilistic neural networks. Neural Networks 3:109–118

    Article  Google Scholar 

  20. Goldfarb S (1988) Dietary factors in the pathogenesis and prophylaxis of calcium nephrolithiasis. Kidney Int 34:544–555

    Article  PubMed  CAS  Google Scholar 

  21. Lemann J, Pleuss JA, Worcester EM et al (1996) Urinary oxalate excretion increases with body size and decreases with increasing dietary calcium intake among healthy adults. Kidney Int 49:200–208

    Article  PubMed  CAS  Google Scholar 

  22. Parks JH, Coe FL (1986) A urinary calcium-citrate index for the evaluation of nephrolithiasis. Kidney Int 30:85–90

    Article  PubMed  CAS  Google Scholar 

  23. Hodgkinson A, Pyrah LN (1958) The urinary excretion of calcium and inorganic phosphate in 344 patients with calcium stone of renal origin. Br J Surg 46:10–18

    Article  PubMed  CAS  Google Scholar 

  24. Pak CY, Britton F, Peterson R et al (1980) Ambulatory evaluation of nephrolithiasis: classification, clinical presentation and diagnostic criteria. Am J Med 69:19–30

    Article  PubMed  CAS  Google Scholar 

  25. Larsson L, Tiselius HG (1987) Hyperoxaluria. Miner Electrolyte Metab 13:242–250

    PubMed  CAS  Google Scholar 

  26. Parks JH, Coward M, Coe FL (1997) Correspondence between stone composition and urine supersaturation in nephrolithiasis. Kidney Int 51:894–900

    Article  PubMed  CAS  Google Scholar 

  27. Leonetti F, Dussol B, Berthezene P et al (1998) Dietary and urinary risk factors for stones in idiopathic calcium stone formers compared with healthy subjects. Nephrol Dial Transplant 13:617–622

    Article  PubMed  CAS  Google Scholar 

  28. Rotily M, Leonetti F, Iovanna C et al (2000) Effects of low animal protein or high-fiber diets on urine composition in calcium nephrolithiasis. Kidney Int 57:115–1123

    Article  Google Scholar 

  29. Curhan GC, Willett WC, Rimm EB, Stampfer MJ (1993) Twenty-four-hour urine chemistries and the risk of kidney stones among women and men. N Engl J Med 328:833–838

    Article  PubMed  CAS  Google Scholar 

  30. Nguyen QV, Kälin A, Drouve U et al (2001) Sensitivity to meat protein intake and hyperoxaluria in idiopathic calcium stone formers. Kidney Int 59:2273–2281

    PubMed  CAS  Google Scholar 

  31. Giannini S, Nobile M, Sartori L et al (1999) Acute effects of moderate dietary protein restriction in patients with idiopathic hypercalciuria and calcium nephrolithiasis. Am J Clin Nutr 69:267–271

    PubMed  CAS  Google Scholar 

  32. Borghi L, Schianchi T, Meschi T et al (2002) Comparison of two diets for the prevention of recurrent stones in idiopathic hypercalciuria. N Engl J Med 346:77–84

    Article  PubMed  CAS  Google Scholar 

  33. Osther PJ (1999) Hyperoxaluria in idiopathic calcium nephrolithiasis. What are the limits? Scand J Urol Nephrol 33:368–371

    Article  PubMed  CAS  Google Scholar 

  34. Strauss AL, Coe FL, Parks JH (1982) Formation of a single calcium stone of renal origin. Clinical and laboratory characteristics of patients. Arch Intern Med 142:504–507

    Article  PubMed  CAS  Google Scholar 

  35. Erickson SB, Cooper K, Broadus AE et al (1984) Oxalate absorption and postprandial urine supersaturation in an experimental human model of absorptive hypercalciuria. Clin Sci 67:131–138

    PubMed  CAS  Google Scholar 

  36. Grover PK, Ryall RL (1994) Urate and calcium oxalate stones: from repute to rhetoric to reality. Miner Electrolyte Metab 20:361–370

    PubMed  CAS  Google Scholar 

  37. Sarmina I, Spirnak JP, Resnick MI (1987) Urinary lithiasis in the black population: an epidemiological study and review of the literature. J Urol 138:14–17

    PubMed  CAS  Google Scholar 

  38. Carson CC (1990) Renal calculus disease. Clin Ger Med 6:115–129

    CAS  Google Scholar 

Download references

Acknowledgements

This work was supported by research grants (Programme Hospitalier de Recherche Clinique N° 99/0050) from the Ministère de la Santé. We thank F. Leonetti, MD, S. Morange, MD, J. Casanova, C. Portelli, O. Pola, and G. Burkhart for their contributions to the study.

Author information

Authors and Affiliations

  1. Service de Néphrologie, Hôpital de la Conception, 147 Bd Baille, 13385, Marseille Cedex 05, France

    Bertrand Dussol & Yvon Berland

  2. Centre d’Investigation Clinique, INSERM-APHM, Marseille, France

    Bertrand Dussol, Patrice Berthezene & Yvon Berland

  3. Ecole Pratique des Hautes Etudes, Université Montpellier II, Marseille, France

    Jean-Michel Verdier

  4. AVENTI Co., Marseille, France

    Jean-Marc Le Goff

Authors
  1. Bertrand Dussol
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jean-Michel Verdier
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jean-Marc Le Goff
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Patrice Berthezene
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yvon Berland
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bertrand Dussol.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Dussol, B., Verdier, JM., Le Goff, JM. et al. Artificial neural networks for assessing the risk of urinary calcium stone among men. Urol Res 34, 17–25 (2006). https://doi.org/10.1007/s00240-005-0006-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00240-005-0006-4

Keywords

Search

Navigation