Skip to main content

Using MLP and SVM for predicting survival rate of oral cancer patients

Abstract

In this paper, we have attempted to build multilayer perceptron (MLP) and support vector machine (SVM) models for predicting survivability of the oral cancer patients who visit the ENT OPD. MLP and SVM have been applied in the past by few researchers for prediction of oral cancer using the genetic database. However, the database used for current research has the attributes like clinical symptoms, history of addiction, diagnosis, investigations, treatments and follow-up details which is gathered from presentations and review graphs related to oral malignancy from ENT and head and neck department. The MLP and SVM models are compared on the basis of various estimation criteria to identify the most effective model. Experimental result shows that accuracy of classification of SVM model is 73.56 %, whereas MLP model is 70.05 %; specificity of SVM model is 73.53 %, whereas MLP model is 65.36 %; and sensitivity of MLP model is 77.00 %, whereas SVM model is 73.56 %. SVM displays better results in terms of true negative, false negative, geometric mean of sensitivity and specificity, positive predictive value, geometric mean of positive predictive value and negative predictive value, precision, F-measure, area under receiver operating characteristics curve and lift and gain chart. Hence, it may be concluded that SVM is a most favourable model for predicting survival rate of oral cancer patients.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

References

  • Agrawal M, Pandey S, Jain S, Maitin S (2012) Oral cancer awareness of the general public in Gorakhpur City, India. Asian Pac J Cancer Prev 13:5195–5199

    Article  Google Scholar 

  • Christopher C (2010) Encyclopaedia Britannica: definition of data mining

  • Chuang LY, Wu KC, Chang HW, Yang CH (2011). Support vector machine-based prediction for oral cancer using four snps in DNA repair genes. In: Proceedings of the International MultiConference of Engineers and Computer scientists. March 16–18

  • Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines. Cambridge University Press, Cambridge

    Google Scholar 

  • Data Mining Curriculum (2006) ACM SIGKDD

  • Elango JK, Gangadharan P, Sumithra S, Kuriakose MA (2006) Trends of head and neck cancers in urban and rural India. Asian Pac J Cancer Prev 07(01):108–112

    Google Scholar 

  • Exarchos KP, Rigas G, Goletsis Y, Fotiadis DI (2012) Modelling of oral cancer progression using dynamic bayesian networks, data mining for biomarker discovery, Springer optimization and its applications, pp 199–221

  • Fayyad UM, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery: an overview. Advances in knowledge discovery and data mining (AAAI Press/MIT Press), p 1–36

  • Gadewal NS, Zingde SM (2011) Database and interaction network of genes involved in oral cancer: version II. Bioinformation 06(04):169–170

    Article  Google Scholar 

  • Ha SH, Joo SH (2010) A hybrid data mining method for medical classification of chest pain. World Acad Sci Eng Technol 37:608–613

    Google Scholar 

  • Han J, Kamber M, Pei J (2011) Data mining: concepts and techniques, 3rd edn. Morgan Kaufmann Publishers, San Francisco. ISBN 978-0123814791

    Google Scholar 

  • HariKumar R, Vasanthi NS, Balasubramani M (2012) Performance analysis of artificial neural networks and statistical methods in classification of oral and breast cancer stages. Int J Soft Comput Eng (IJSCE) 2(3):263–269

    Google Scholar 

  • Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction. 2nd edn. Springer, Vienna

    Book  Google Scholar 

  • Jemal A, Thimas A, Murray T, Thun M (2002) Cancer statistics. CA Cancer J Clin 52:181–182

    Article  Google Scholar 

  • Kaladhar DSVGK, Chandana B, Bharath Kumar P (2011) Predicting cancer survivability using Classification algorithms. Int J Res Rev Comput Sci (IJRRCS) 2(2):340–343

    Google Scholar 

  • Kent S (1996) Diagnosis of oral cancer using genetic programming—a technical report. CSTR-96-14

  • Khandekar PS, Bagdey PS, Tiwari RR (2006) Oral cancer and some epidemiological factors: a hospital based study. Indian J Community Med 31(03):157–159

    Google Scholar 

  • LeCun Y (1987) Modeles connexionnistes de l’apprentissage (connectionist learning models). Doctoral dissertation, Université P. et M. Curie (Paris 6)

  • Lippmann RP (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4:4–28

    Article  Google Scholar 

  • Manoharan N, Tyagi BB, Raina V (2010) Cancer incidences in rural Delhi—2004–05. Asian Pac J Cancer Prev 11(01):73–78

    Google Scholar 

  • Milovic B, Milovic M (2012) Prediction and decision making in health care using data mining. Int J Public Health Sci 01(02):69–78

    Google Scholar 

  • Nahar J, Kevin ST, Ali ABMS, Chen YP (2009) Significant cancer prevention factor extraction: an association rule discovery approach. J Med Syst. doi: 10.1007/s10916-009-9372-8

  • Plamondon R, Shirari SN (2000) On-line and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22:63–84

    Article  Google Scholar 

  • Rosenblatt F (1957) The perceptron—a perceiving and recognizing automaton (Technical Report 85-460-1). Cornell Aeronautical Laboratory

  • Rumelhart D, Hinton G, Williams R (1986) Learning internal representations by backpropagating errors. In Rumelhart D and Mc-Clelland J (eds), Parallel distributed processing: explorations in the microstructure of cognition, vol 1. MIT Press, Cambridge, pp 318–362

  • RuthRamya K, Anusha K, Chanti K, Vidya VS, Kumar PP (2012) A class based approach for medical classification of chest pain. Int J Eng Trends Technol 3(2):89–93

    Google Scholar 

  • Sankaranarayanan R, Ramadas K, Thomas K (2005) Effect of screening on oral cancer mortality in Kerala, India: a cluster-randomised controlled trial. Lancet 365(9475):1927–1933

    Article  Google Scholar 

  • Scully C, Bagan JV, Hopper C, Epstein JB (2008) Oral cancer: current and future diagnostics techniques—a review article. Am J Dent 21(04):199–209

    Google Scholar 

  • Shah S, Kusiak A (2007) Cancer gene search with data-mining and genetic algorithms. Comput Biol Med 37:251–261 http://www.intl.elsevierhealth.com/journals/cobm

  • Sharma N, Om H (2012) Framework for early detection and prevention of oral cancer using data mining. Int J Adv Eng Technol 4(2):302–310

    Google Scholar 

  • Swami S, Thakur RS, Chandel RS (2011) Multi-dimensional association rules extraction in smoking habits database. Int J Adv Netw Appl 03(03):1176–1179

    Google Scholar 

  • Vapnik V (1995) The nature of statistical learning theory. Second edition. Springer, Vienna

    Book  Google Scholar 

  • Werning JW (2007) Oral cancer: diagnosis, management, and rehabilitation. p 1. ISBN 978-1588903099

  • Woolgar JA, Scott J, Vaughan ED, Brown JS, West CR, Rogers S (1995) Survival, metastasis and recurrence of oral cancer in relation to pathological features. Ann R Coll Surg Engl 1995(77):325–331

    Google Scholar 

Download references

Acknowledgments

The authors devote their sincere thanks to the management and staff of Indian School of Mines, for their constant support and motivation.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Neha Sharma.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sharma, N., Om, H. Using MLP and SVM for predicting survival rate of oral cancer patients. Netw Model Anal Health Inform Bioinforma 3, 58 (2014). https://doi.org/10.1007/s13721-014-0058-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13721-014-0058-x

Keywords

  • Oral cancer
  • Data mining
  • Multilayer perceptron
  • Support vector machine
  • Classification
  • Early detection