Skip to main content

Applying Data Mining Techniques in the Development of a Diagnostics Questionnaire for GERD

Digestive Diseases and Sciences volume 52, pages 1871–1878 (2007)Cite this article

Abstract

Gastroesophageal reflux disease (GERD) is a common condition, managed mostly in primary care practice. Heartburn and acid regurgitation are considered primary symptoms, and are usually highly specific. However, the symptom spectrum is much wider and in many cases it is difficult to determine whether the patient has GERD or dyspepsia from another origin. The aim of this study is to develop a symptom score and rule for the diagnosis of GERD, using data mining techniques, to provide a clinical diagnostic tool for primary care practitioners in the evaluation and management of upper gastrointestinal symptoms. A diagnostic symptom questionnaire consisting of 15 items and based on the current literature was designed to measure the presence and severity of reflux and dyspepsia symptoms using a 5-point Likert-type scale. A total of 132 subjects with uninvestigated upper abdominal symptoms were prospectively recruited for symptom evaluation. All patients were interviewed and examined, underwent upper gastrointestinal endoscopy, and completed the questionnaire. Based on endoscopic findings as well as the medical interview, the subjects were classified as having reflux disease (GERD) or non-reflux disease (non-GERD). Data mining models and algorithms (neural networks, decision trees, and logistic regression) were used to build a short and simple new discriminative questionnaire. The most relevant variables discriminating GERD from non-GERD patients were heartburn, regurgitation, clinical response to antacids, sour taste, and aggravation of symptoms after a heavy meal. The sensitivity and specificity of the new symptom score were 70%–75% and 63%–78%, respectively. The area under the ROC curve for logistic regression and neural networks were 0.783 and 0.787, respectively. We present a new validated discriminative GERD questionnaire using data mining techniques. The questionnaire is useful, friendly, and short, and therefore can be easily applied in clinical practice for choosing the appropriate diagnostic workup for patients with upper gastrointestinal complaints.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. Ofman JJ (2003) The economic and quality-of-life impact of symptomatic gastroesophageal reflux disease. Am J Gastroenterol 98:S8–S14

    PubMed  Article  Google Scholar 

  2. Hastie T, Tibshirnai R, Friedman J (2001) The elements of statistical learning, data mining, inference and prediction. Springer, New York

    Google Scholar 

  3. Hand DJ, Mannila H, Smyth P (2001) Principles of data mining (adaptive computation and machine learning). MIT Press, Cambridge, MA

    Google Scholar 

  4. Klosgen W, Zytkow JM (eds) (2002) Handbook of data mining and knowledge discovery. Oxford University Press, New York

  5. Moayyedi P, Duffett S, Braunholtz D, Mason S, Richards ID, Dowell AC, Axon AT (1998) The Leeds Dyspepsia Questionnaire: a valid tool for measuring the presence and severity of dyspepsia. Aliment Pharmacol Ther 12:1257–1262

    PubMed  Article  CAS  Google Scholar 

  6. Kline-Leidy N, Farup C, Rentz AM, Ganoczy D, Koch KL (2000) Patient-based assessment in dyspepsia. Development and validation of Dyspepsia Symptom Severity Index (DSSI). Dig Dis Sci 45:1172–1179

    Article  Google Scholar 

  7. Talley NJ, Phillips SFP, Melton LJ 3rd, Wiltgen C, Zinsmeister AR (1989) A patient questionnaire to identify a bowel disease. Ann Intern Med 111:671–674

    PubMed  CAS  Google Scholar 

  8. Shaw MJ, Talley NJ, Beebe TJ, Rockwood T, Carlsson R, Adlis S, Fendrick AM, Jones R, Dent J, Bytzer P (2001) Initial validation of a diagnostic questionnaire for gastroesophageal reflux disease. Am J Gastroenterol 96:52–57

    PubMed  Article  CAS  Google Scholar 

  9. El-Omar EM, Banerjee S, Wirz A, McColl KE (1996) The Glasgow Dyspepsia Severity Score—a tool for the global measurement of dyspepsia. Eur J Gastroenterol Hepatol 8:967–971

    PubMed  CAS  Google Scholar 

  10. Carlesson R, Dent J, Bolling-Sternevald E, Johnsson F, Junghard O, Lauritsen K, Riley S, Lundell L (1998) The usefulness of a structured questionnaire in the assessment of symptomatic gastroesophageal reflux disease. Scand J Gastroenterol 33:1023–1029

    Article  Google Scholar 

  11. Talley NJ, Boyce PM, Owen BK, Newman P, Paterson KJ (1995) Initial validation of a bowel symptom questionnaire and measurement of chronic gastrointestinal symptom in Australians. Aus N Z J Med 25:302–308

    CAS  Google Scholar 

  12. Manterola C, Munos S, Grande L, Bustos L (2002) Initial validation of a questionnaire for detecting gastroesophageal reflux disease in epidemiological settings. J Clin Epidemiol 55:1041–1045

    PubMed  Article  Google Scholar 

  13. Wong WM, Lam KF, Lai KC, Hui WM, Hu WH, Lam CL, Wong NY, Xia HH, Huang JQ, Chan AO, Lam SK, Wong BC (2003) A validated symptoms questionnaire (Chinese GERDQ) for the diagnosis of gastro-esophageal reflux disease in Chinese population. Aliment Pharmacol Ther 17:1407–1413

    PubMed  Article  CAS  Google Scholar 

  14. Numans ME, De Wit NJ (2003) Reflux symptoms in general practice: diagnostic evaluation of the Carlsson-Dent gastro-esophageal reflux disease questionnaire. Aliment Pharmacol Ther 17:1049–1055

    PubMed  Article  CAS  Google Scholar 

  15. Allen CJ, Parameswaran K, Belda J, Anvari M (2000) Reproducibility, validity and responsiveness of a disease-specific symptom questionnaire for gastroesophageal reflux disease. Dis Esophagus 13:265–270

    PubMed  Article  CAS  Google Scholar 

  16. Rothman M, Farup C, Stewart W, Helbers L, Zeldis J (2001) Symptoms associated with gastroesophageal reflux disease; development of a questionnaire for use in clinical trials. Dig Dis Sci 46:1540–1548

    PubMed  Article  CAS  Google Scholar 

  17. Ofman JJ, Shaw M, Sadik K, Grogg A, Emery K, Lee J, Reyes E, Fullerton S (2002) Identifying patients with gastroesophageal reflux disease; validation of a practical screening tool. Dig Dis Sci 47:1863–1869

    PubMed  Article  CAS  Google Scholar 

  18. Locke GR, Talley NJ, Weaver AL, Zinsmeister AR (1994) A new questionnaire for gastroesophageal reflux disease. Mayo Clin Proc 69:539–547

    PubMed  CAS  Google Scholar 

  19. Brown WH, Chey WD, Elta GH (2002) Number of responses on a review of systems questionnaire predicts the diagnosis of functional gastrointestinal disorders. J Clin Gastroenterol 36:222–227

    Article  Google Scholar 

  20. Moayyedi P, Axon AT (1999) The usefulness of the likelihood ratio in the diagnosis of dyspepsia and gastroesophageal reflux disease. Am J Gastroenterol 94:3122–3125

    PubMed  Article  CAS  Google Scholar 

  21. Shaw M, Talley NJ, Adlis S, Beebe T, Tomshine P, Healey M (1998) Development of a digestive health status instrument: tests of scaling assumptions, structure and reliability in primary care population. Aliment Pharmacol Ther 12:1067–1078

    PubMed  Article  CAS  Google Scholar 

  22. Small PK, Loudon MA, Waldron B (1995) Importance of reflux symptoms in functional dyspepsia. Gut 36:189–192

    PubMed  CAS  Google Scholar 

  23. Talley NJ, Weaver AL, Tesmer DL, Zinsmeister AR (1993) Lack of discriminant value of dyspepsia subgroups in patients referred for upper endoscopy. Gastroenterology 105:1378–1386

    PubMed  CAS  Google Scholar 

  24. Junghard O, Lauritsen K, Talley NJ, Wiklund IK (1998) Validation of seven graded diary cards for severity of dyspepsia symptoms in patients with non ulcer dyspepsia. Eur J Surg Suppl 583:106–111

    PubMed  Article  Google Scholar 

  25. Wallace MB, Durkalski VL, Vaughan J, Palesch YY, Libby ED, Jowell PS, Nickl NJ, Schutz SM, Leung JW, Cotton PB (2001) Age and alarm symptoms do not predict endoscopic findings among patients with dyspepsia: a multicenter database study. Gut 49:29–34

    PubMed  Article  CAS  Google Scholar 

  26. Kolodny M (1998) Computerized disease management algorithms—the future is now. Eur J Surg Suppl 583:104–105

    PubMed  Article  Google Scholar 

  27. Stanghellini V, Tosetti C, Paternico A, De Giorgio R, Barbara G, Salvioli B, Corinaldesi R (1999) Predominant symptoms identify different subgroups in functional dyspepsia. Am J Gastroenterol 94:2080–2085

    PubMed  Article  CAS  Google Scholar 

  28. Mujica VR, Rao SSC (1999) Recognizing atypical manifestations of GERD. Asthma, chest pain and otolaryngologic disorders may be due to reflux. Postgrad Med 105:53–55

    PubMed  CAS  Google Scholar 

  29. Weusten BL, Roelofs JM, Akkermans LM, Van Berge-Henegouwen GP, Smout AJ (1994) The symptom-association probability: an improved method for symptom analysis of 24-hour esophageal ph data. Gastroenterology 107:1741–1745

    PubMed  CAS  Google Scholar 

  30. Grainger SL, Klass HJ, Rake MO, Williams JG (1994) Prevalence of dyspepsia: the epidemiology of overlapping symptoms. Postgrad Med J 70:154–161

    PubMed  CAS  Article  Google Scholar 

  31. Armstrong D, Bennett JR, Blum AL, Dent J, De Dombal FT, Galmiche JP, Luncell L, Margulies M, Richter JE, Spechler SJ, Tytgat GN, Wallin L (1996) The endoscopic assessment of oesophagitis: a progress report on observer agreement. Gastroenterology 111:85–92

    PubMed  Article  CAS  Google Scholar 

  32. Leshno M, Lin VY, Pinkus A, et al (1993) Multilayer feedforward networks with a non polynomial activation function can approximate any function. Neural Networks 6:861–867

    Article  Google Scholar 

  33. Stanghellini V, Armstrong D, Monnikes H, Bardhan KD (2004) Systematic review: do we need a new gastro-oesophageal reflux disease questionnaire? Aliment Pharmacol Ther 19:463–479

    PubMed  Article  CAS  Google Scholar 

  34. Carlsson R, Holloway RH (2000) Endoscopy-negative reflux disease. Baillier Clin Gastroenterol 14:827–837

    Article  CAS  Google Scholar 

  35. Stanghellini V, Cogliandro R, Cogliandro L, De Giorgio R, Barbara G, Corinaldesi R (2003) Unsolved problems in the management of patients with gastroesophageal reflux disease. Dig Liv Dis 35:843–848

    Article  CAS  Google Scholar 

  36. Fass R, Fennerty MB, Vakil N (2001) Nonerosive reflux disease—current concepts and dilemmas. Am J Gastroenterol 96:303–314

    PubMed  CAS  Google Scholar 

  37. Shaw M (2004) Diagnostic utility of reflux disease symptoms. Gut 53(Suppl 4):25–27

    Google Scholar 

  38. Schenk BE, Kuipers EJ, Klinkenberg-Knol EC, Festen HP, Jansen EH, Tuynman HA, Schrijver M, Dieleman LA, Meuwissen SG (1997) Omeprazole as a diagnostic tool in gastroesophageal reflux disease. Am J Gastroenterol 92:1997–2000

    PubMed  CAS  Google Scholar 

  39. Fass R, Ofman JJ, Gralnek IM, Johnson C, Camargo E, Sampliner RE, Fennerty MB (1999) Clinical and economic assessment of the omeprazole test in patients with symptoms suggestive of gastroesophageal reflux disease. Arch Intern Med 159:2161–2168

    PubMed  Article  CAS  Google Scholar 

  40. Talley NJ, McNeil D, Piper DW (1987) Discriminant value of dyspeptic symptoms: a study of the clinical presentation of 221 patients with dyspepsia of unknown cause, peptic ulceration, or cholelithiasis. Gut 20:40–46

    Google Scholar 

Download references

Acknowledgements

Noya Horowitz and Menachem Moshkowitz equally contributed to this work.

Author information

Affiliations

  1. Department of Gastroenterology and Liver Disease, Tel-Aviv-Sourasky Medical Center, Tel Aviv, Israel

    Noya Horowitz, Menachem Moshkowitz, Zamir Halpern & Moshe Leshno

  2. Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel

    Noya Horowitz, Menachem Moshkowitz, Zamir Halpern & Moshe Leshno

  3. Faculty of Management, Tel Aviv University, Tel Aviv, Israel

    Moshe Leshno

  4. Faculty of Management, Tel-Aviv University, Tel Aviv, 69978, Israel

    Moshe Leshno

Authors
  1. Noya Horowitz
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Menachem Moshkowitz
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zamir Halpern
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Moshe Leshno
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Moshe Leshno.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Horowitz, N., Moshkowitz, M., Halpern, Z. et al. Applying Data Mining Techniques in the Development of a Diagnostics Questionnaire for GERD. Dig Dis Sci 52, 1871–1878 (2007). https://doi.org/10.1007/s10620-006-9202-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10620-006-9202-5

Keywords

  • Logistic Regression
  • Hide Layer
  • Receiver Operating Characteristic Curve
  • Dyspepsia
  • Data Mining Technique