Neural Computing and Applications

, Volume 23, Issue 7–8, pp 2387–2403 | Cite as

Decision tree classifiers for automated medical diagnosis

  • Ahmad Taher Azar
  • Shereen M. El-Metwally
Original Article


Decision support systems help physicians and also play an important role in medical decision-making. They are based on different models, and the best of them are providing an explanation together with an accurate, reliable and quick response. This paper presents a decision support tool for the detection of breast cancer based on three types of decision tree classifiers. They are single decision tree (SDT), boosted decision tree (BDT) and decision tree forest (DTF). Decision tree classification provides a rapid and effective method of categorizing data sets. Decision-making is performed in two stages: training the classifiers with features from Wisconsin breast cancer data set, and then testing. The performance of the proposed structure is evaluated in terms of accuracy, sensitivity, specificity, confusion matrix and receiver operating characteristic (ROC) curves. The results showed that the overall accuracies of SDT and BDT in the training phase achieved 97.07 % with 429 correct classifications and 98.83 % with 437 correct classifications, respectively. BDT performed better than SDT for all performance indices than SDT. Value of ROC and Matthews correlation coefficient (MCC) for BDT in the training phase achieved 0.99971 and 0.9746, respectively, which was superior to SDT classifier. During validation phase, DTF achieved 97.51 %, which was superior to SDT (95.75 %) and BDT (97.07 %) classifiers. Value of ROC and MCC for DTF achieved 0.99382 and 0.9462, respectively. BDT showed the best performance in terms of sensitivity, and SDT was the best only considering speed.


Computer-aided diagnosis (CAD) Decision support systems (DSS) Decision tree classification Single decision tree Boosted decision tree Decision tree forest k-fold cross-validation 



I would like to highly appreciate and gratefully acknowledge Phillip H. Sherrod, software developer and consultant on predictive modeling, for his support and consultation during modeling process.


  1. 1.
    Alsabti K, Ranka S, Singh V (1998) CLOUDS: a decision tree classifier for large datasets. In: Proceedings of the fourth international conference on knowledge discovery and data mining (KDD-98), August 27–31. AAAI Press, New York City, NY, USA, pp 2–8Google Scholar
  2. 2.
    Amit Y, Geman D (1997) Shape quantization and recognition with randomized trees. Neural Comput 9(7):1545–1588CrossRefGoogle Scholar
  3. 3.
    Ankerst M, Elsen C, Ester M, Kriegel HP (1999) Visual classification: an interactive approach to decision tree construction. In: Proceedings of international conference on knowledge discovery and data mining (KDD ‘99), San Diego, CA, USAGoogle Scholar
  4. 4.
    Arditi D, Pulket T (2005) Predicting the outcome of construction litigation using boosted decision trees. J Comput Civil Eng 19(4):387–393CrossRefGoogle Scholar
  5. 5.
    Balakumaran T, Vennila ILA, Shankar GC (2010) Microcalcification detection in digital mammograms using novel filter bank. Procedia Comput Sci 2:272–282CrossRefGoogle Scholar
  6. 6.
    Bick U, Diekmann F (2007) Digital mammography: what do we and what don’t we know? Eur Radiol 17(8):1931–1942CrossRefGoogle Scholar
  7. 7.
    Boyle P, Levin B (2008) World cancer report 2008. International Agency for Research on Cancer, LyonGoogle Scholar
  8. 8.
    Bradford JP, Kunz C, Kohavi R et al (1998) Pruning decision trees with misclassification costs. In: Proceedings of the 10th European conference on machine learning, Chemnitz, Germany, pp 131–136, April 21–23, 1998Google Scholar
  9. 9.
    Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth & Brooks, CAzbMATHGoogle Scholar
  10. 10.
    Breiman L (1994) Bagging predictors. Technical report 421. Department of Statistics, University of California, BerkeleyGoogle Scholar
  11. 11.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRefzbMATHGoogle Scholar
  12. 12.
    Brown DE (2008) Introduction to data mining for medical informatics. Clin Lab Med 28(1):9–35CrossRefGoogle Scholar
  13. 13.
    Burrell HC, Sibbering DM, Wilson AR et al (1996) Screening Interval breast cancers: mammographic features and prognostic factors. Radiology 199(3):811–817Google Scholar
  14. 14.
    Burrell HC, Pinder SE, Wilson AR et al (1996) The positive predictive value of mammographic signs: a review of 425 non-palpable breast lesions. Clin Radiol 51(4):277–281CrossRefGoogle Scholar
  15. 15.
    Clark LA, Pregibon D (1992) Tree-based models. In: Chambers JM, Hastie TJ (eds) Statistical models (chap 9). S. Chapman & Hall, New York, pp 377–420Google Scholar
  16. 16.
    Christoyianni I, Koutras A, Dermatas E, Kokkinakis G (2002) Computer aided diagnosis of breast cancer in digitized mammograms. Comput Med Imaging Graph 26(5):309–319CrossRefGoogle Scholar
  17. 17.
    Cummings MP, Segal MR (2004) Few amino acid positions in rpoB are associated with most of the rifampin resistance in Mycobacterium tuberculosis. BMC Bioinform 5:137–143CrossRefGoogle Scholar
  18. 18.
    De’ath G (2007) Boosted trees for ecological modeling and prediction. Ecology 88(1):243–251MathSciNetCrossRefGoogle Scholar
  19. 19.
    De’ath G, Fabricius KE (2000) Classification and regression trees: a powerful yet simple technique for ecological data analysis. Ecology 81(11):3178–3192CrossRefGoogle Scholar
  20. 20.
    Delen D, Walker G, Kadam A (2005) Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med 34(2):113–127CrossRefGoogle Scholar
  21. 21.
    Dershaw DD (2006) Status of mammography after the digital mammography imaging screening trial: digital versus film. Breast J 12(2):99–102CrossRefGoogle Scholar
  22. 22.
    DeSantis C, Siegel R, Bandi P, Jemal A (2011) Breast cancer statistics. CA Cancer J Clin 61(6):409–418CrossRefGoogle Scholar
  23. 23.
    Diamantidis NA, Karlis D, Giakoumakis EA (2000) Unsupervised stratification of cross-validation for accuracy estimation. Artif Intell 116(1–2):1–16MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Dietterich TG (1990) Machine learning. Annu Rev Comput Sci 4(1):255–306CrossRefGoogle Scholar
  25. 25.
    Doi K, MacMahon H, Katsuragawa S et al (1999) Computer-aided diagnosis in radiology: potential and pitfalls. Eur J Radiol 31(2):97–109CrossRefGoogle Scholar
  26. 26.
    Doi K (2007) Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 31(4–5):198–211CrossRefGoogle Scholar
  27. 27.
    Elatar I (2002) Cancer registration, NCI Egypt 2001. National Cancer Institute, Cairo., accessed 26 May 2012
  28. 28.
    Endo A, Shibata T, Tanaka H (2008) Comparison of seven algorithms to predict breast cancer survival. Biomed Soft Comput Hum Sci 13(2):11–16Google Scholar
  29. 29.
    Fan CY, Changb PC, Linb JJ, Hsieh JC (2011) A hybrid model combining case-based reasoning and fuzzy decision tree for medical data classification. Appl Soft Comput 11(1):632–644CrossRefGoogle Scholar
  30. 30.
    Ferri U, Flach PA, Hernandez-Orallo J (2003) Improving the AUC of probabilistic estimation trees. In: Lecture notes in artificial intelligence, vol 2837, pp 121–132Google Scholar
  31. 31.
    Francois D, Rossi F, Wertz V, Verleysen M (2007) Resampling methods for parameter-free and robust feature selection with mutual information. Neurocomputing 70(7–9):1276–1288CrossRefGoogle Scholar
  32. 32.
    Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: Proceedings of the 13th international conference on artificial intelligence: machine learning. International Machine Learning Society, pp 148–156Google Scholar
  33. 33.
    Freund Y, Schapire RE (1999) A short introduction to boosting. J Jpn Soc Artif Intell 14(5):148–156Google Scholar
  34. 34.
    Friedman JH, Kohavi R, Yun Y (1996). Lazy decision trees. In: Proceedings of the 13th national conference on artificial intelligence and eighth innovative applications of artificial intelligence conference, vol 1. AAAI Press/The MIT Press, AAAI 96, IAAI 96, August 4–8, 1996, pp 717–724Google Scholar
  35. 35.
    Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Statist 29(5):1189–1232MathSciNetCrossRefzbMATHGoogle Scholar
  36. 36.
    Fulton T, Kasif S, Salzberg S, Waltz D (1996) Local induction of decision trees: towards interactive data mining. In: Proceedings of the second international conference on knowledge discovery and data mining, Portland, OR, USA, pp 14–19Google Scholar
  37. 37.
    Garofalakis M, Hyun D, Rastogi R, Shim K (2000). Efficient algorithms for constructing decision trees with constraints. In: Proceedings of the 6th ACM SIGKDD international conference on knowledge discovery and data mining, Boston, MA, USA, pp 335–339Google Scholar
  38. 38.
    Hambly NM, McNicholas MM, Phelan N, Hargaden GC, O’Doherty A, Flanagan FL (2009) Comparison of digital mammography and screen-film mammography in breast cancer screening: a review in the Irish breast screening program. Am J Roentgenol 193(4):1010–1018CrossRefGoogle Scholar
  39. 39.
    Ho T (1995) Random decision forest. In: 3rd international conference on document analysis and recognition, Montreal, Canada, August 14–18, 1995, pp 278–282Google Scholar
  40. 40.
    Ho T (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20(8):832–844CrossRefGoogle Scholar
  41. 41.
    Houssami N, Given-Wilson R, Ciatto S (2009) Early detection of breast cancer: overview of the evidence on computer-aided detection in mammography screening. J Med Imaging Radiat Oncol 53(2):171–176CrossRefGoogle Scholar
  42. 42.
    Ibrahim NA, Kudus A, Daud I, Abu Bakar MR (2008) Decision tree for competing risks survival probability in breast cancer study. Proc World Acad Sci Eng Technol 38:15–19Google Scholar
  43. 43.
    Islam SR, Aziz SM (2012) Mammography is the most effective method of breast cancer screening. Mymensingh Med J 21(2):366–371Google Scholar
  44. 44.
    Kallergi M (1998) Digital mammography: from theory to practice. Cancer Control 5(1):72–79Google Scholar
  45. 45.
    Kerekes J (2008) Receiver operating characteristic curve confidence intervals and regions. IEEE Geosci Remote Sens Lett 5(2):251–255CrossRefGoogle Scholar
  46. 46.
    Kuo WJ, Chang RF, Chen DR, Lee CC (2001) Data mining with decision trees for diagnosis of breast tumor in medical ultrasonic images. Breast Cancer Res Treat 66(1):51–57CrossRefGoogle Scholar
  47. 47.
    Jemal A, Murray T, Samuels A, Ghafoor A, Ward E, Thun MJ (2003) Cancer statistics. CA Cancer J Clin 53:5–26CrossRefGoogle Scholar
  48. 48.
    Jerez-Aragonés JM, Gómez-Ruiz JA, Ramos-Jiménez G, Muñoz-Pérez J, Alba-Conejo E (2003) A combined neural network and decision trees model for prognosis of breast cancer relapse. Artif Intell Med 27(1):45–63CrossRefGoogle Scholar
  49. 49.
    Lavrac N (1999) Selected techniques for data mining in medicine. Artif Intell Med 16(1):3–23CrossRefGoogle Scholar
  50. 50.
    Laya MB, Larson EB, Taplin SH, White E (1996) Effect of estrogen replacement therapy on the specificity and sensitivity of screening mammography. J Natl Cancer Inst 88(10):643–649CrossRefGoogle Scholar
  51. 51.
    Lee MY, Yang CS (2010) Entropy-based feature extraction and decision tree induction for breast cancer diagnosis with standardized thermograph images. Comput Methods Program Biomed 100(1):269–282CrossRefGoogle Scholar
  52. 52.
    Lewin JM, D’Orsi CJ, Hendrick RE, Moss LJ, Isaacs PK, Karellas A, Cutter GR (2002) Clinical comparison of full-field digital mammography and screen-film mammography for detection of breast cancer. Am J Roentgenol 179(3):671–677CrossRefGoogle Scholar
  53. 53.
    Li H, Giger ML, Yuan Y, Chen W, Horsch K, Lan L, Jamieson AR, Sennett CA, Jansen SA (2008) Evaluation of computer-aided diagnosis on a large clinical full-field digital mammographic dataset. Acad Radiol 15(11):1437–1445CrossRefGoogle Scholar
  54. 54.
    Lim TS, Loh WY, Shih YS (1998) An empirical comparison of decision trees and other classification methods. Technical report 979. Department of Statistics, University of WisconsinGoogle Scholar
  55. 55.
    Llora X, Garrell JM (2001) Evolution of decision trees. In: Proceedings of the 4th Catalan conference on artificial intelligence (CCIA ‘2001). ACIA PressGoogle Scholar
  56. 56.
    Locasale JW, Cantley LC (2010) Altered metabolism in cancer. BMC Biol 88:88CrossRefGoogle Scholar
  57. 57.
    Mangasarian OL, Wolberg WH (1990) Cancer diagnosis via linear programming. SIAM News 23(5):1–18Google Scholar
  58. 58.
    Mangasarian OL, Setiono R, Wolberg WH (1990) Pattern recognition via linear programming: theory and application to medical diagnosis. In: Coleman TF, Li Y (eds) Large-scale numerical optimization. SIAM, Philadelphia, pp 22–30Google Scholar
  59. 59.
    Meinshausen N (2006) Quantile regression forests. J Mach Learn Res 7:983–999MathSciNetzbMATHGoogle Scholar
  60. 60.
    Mehta M, Agrawal R, Rissanen J (1996) SLIQ: a fast scalable classifier for data mining. In: Proceedings of the 5th international conference on extending database technology, Avignon, France, March 25–29, pp 18–32Google Scholar
  61. 61.
    McAree B, O’Donnell ME, Spence A et al (2010) Breast cancer in women under 40 years of age: a series of 57 cases from Northern Ireland. Breast 19(2):97–104CrossRefGoogle Scholar
  62. 62.
    Mingers J (1989) An empirical comparison of selection measures for decision tree induction. Mach Learn 3(4):319–342Google Scholar
  63. 63.
    Muller S (1997) Full-field digital mammography designed as a complete system. Eur J Radiol 31(1):25–34CrossRefGoogle Scholar
  64. 64.
    NHS breast screening programmes: annual review 2011. ISBN: 978-1-84463-079-0.
  65. 65.
    Noble M, Bruening W, Uhl S, Schoelles K (2009) Computer-aided detection mammography for breast cancer screening: systematic review and meta-analysis. Arch Gynecol Obstet 279(6):881–890CrossRefGoogle Scholar
  66. 66.
    Omar S, Khaled H, Gaafar R et al (2003) Breast cancer in Egypt: a review of disease presentation and detection strategies. East Mediterr Health J 9(3):448–463Google Scholar
  67. 67.
    Park SH, Goo JM, Jo CH (2004) Receiver operating characteristic (ROC) curve: practical review for radiologists. Korean J Radiol 5(1):11–18CrossRefGoogle Scholar
  68. 68.
    Pryke M (2012) Effect of population-based screening on breast cancer mortality. Lancet 379(9823):1297–1298CrossRefGoogle Scholar
  69. 69.
    Quinlan JR (1993) C4. 5: programs for machine learning. Morgan Kaufmann, San MateoGoogle Scholar
  70. 70.
    Quinlan JR (2003) Data mining tools See5 and C5.0. RuleQuest Research, Austria.
  71. 71.
    Richards G, Rayward-Smith VJ, Sönksen PH, Carey S, Weng C (2001) Data mining for indicators of early mortality in a database of clinical records. Artif Intell Med 22(3):215–231CrossRefGoogle Scholar
  72. 72.
    Russell S, Norvig P (2002) Artificial intelligence: a modern approach. Prentice-Hall, NJGoogle Scholar
  73. 73.
    Salzberg SL (1997) On comparing classifiers: pitfalls to avoid and a recommended approach. Data Min Knowl Discov 1(3):317–327Google Scholar
  74. 74.
    Shah AJ, Wang J, Yamada T, Fajardo LL (2003) Digital mammography: a review of technical development and clinical applications. Clin Breast Cancer 4(1):63–70CrossRefGoogle Scholar
  75. 75.
    Shapiro S, Strax P, Venet L (1966) Evaluation of periodic breast cancer screening with mammography. Methodology and early observations. JAMA 195(9):731–738CrossRefGoogle Scholar
  76. 76.
    Shanthi S, Bhaskaran VM (2011) Intuitionistic fuzzy C-means and decision tree approach for breast cancer detection and classification. Eur J Sci Res 66(3):345–351Google Scholar
  77. 77.
    Sherrod PH (2012) DTREG predictive modeling software., accessed 16 Sep 2012
  78. 78.
    Shiraishi A (2008) Current state of digital mammography. Breast Cancer 15(3):194–199CrossRefGoogle Scholar
  79. 79.
    Sinclair N, Littenberg B, Geller B, Muss H (2011) Accuracy of screening mammography in older women. Am J Roentgenol 197(5):1268–1273CrossRefGoogle Scholar
  80. 80.
    Skaane P (2009) Studies comparing screen-film mammography and full-field digital mammography in breast cancer screening: updated review. Acta Radiol 50(1):3–14CrossRefGoogle Scholar
  81. 81.
    Štajduhar I, Dalbelo-Bašic′ B (2012) Uncensoring censored data for machine learning: a likelihood-based approach. Expert Syst Appl 39(1):7226–7234CrossRefGoogle Scholar
  82. 82.
    Theodoridis S, Koutroumbas K (2006) Pattern recognition, 3rd edn. Academic Press, San DiegozbMATHGoogle Scholar
  83. 83.
    Ture M, Tokatli F, Kurt I (2009) Using Kaplan–Meier analysis together with decision tree methods (C&RT, CHAID, QUEST, C4.5 and ID3) in determining recurrence-free survival of breast cancer patients. Expert Syst Appl 36(1):2017–2026CrossRefGoogle Scholar
  84. 84.
    Tyler RM, Brady DC, Targett TE (2009) Temporal and spatial dynamics of diel—cycling hypoxia in estuarine tributaries. Estuaries Coasts 32:123–145CrossRefGoogle Scholar
  85. 85.
    UCI (2012) Machine learning repository., accessed 16 Sep 2012
  86. 86.
    Van Ongeval Ch (2007) Digital mammography for screening and diagnosis of breast cancer: an overview. JBR BTR 90(3):163–166Google Scholar
  87. 87.
    Vinnicombe S, Pinto Pereira SM, McCormack VA et al (2009) Full-field digital versus screen-film mammography: comparison within the UK breast screening program and systematic review of published data. Radiology 251(2):347–358CrossRefGoogle Scholar
  88. 88.
    Wilkinson JE (2011) Effect of mammography on breast cancer mortality. Am Fam Physician 84(11):1225–1227Google Scholar
  89. 89.
    Yuan Q, Cai C, Xiao H et al (2007) Diagnosis of breast tumours and evaluation of prognostic risk by using machine learning approaches. Commun Comput Inf Sci 2:1250–1260. doi: 10.1007/978-3-540-74282 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2012

Authors and Affiliations

  1. 1.Faculty of EngineeringMisr University for Science and Technology (MUST)6th of October CityEgypt
  2. 2.Systems and Biomedical Engineering DepartmentCairo UniversityGizaEgypt

Personalised recommendations