Advertisement

Auto-MeDiSine: an auto-tunable medical decision support engine using an automated class outlier detection method and AutoMLP

  • Maham Jahangir
  • Hammad Afzal
  • Mehreen Ahmed
  • Khawar Khurshid
  • Muhammad Faisal Amjad
  • Raheel Nawaz
  • Haider AbbasEmail author
Original Article
  • 15 Downloads

Abstract

With advanced data analysis techniques, efforts for more accurate decision support systems for disease prediction are on the rise. According to the World Health Organization, diabetes-related illnesses and mortalities are on the rise. Hence, early diagnosis is particularly important. In this paper, we present a framework, Auto-MeDiSine, that comprises an automated version of enhanced class outlier detection using a distance-based algorithm (AutoECODB), combined with an ensemble of automatic multilayer perceptron (AutoMLP). AutoECODB is built upon ECODB by automating the tuning of parameters to optimize outlier detection process. AutoECODB cleanses the dataset by removing outliers. Preprocessed dataset is then used to train a prediction model using an ensemble of AutoMLPs. A set of experiments is performed on publicly available Pima Indian Diabetes Dataset as follows: (1) Auto-MeDiSine is compared with other state-of-the-art methods reported in the literature where Auto-MeDiSine realized an accuracy of 88.7%; (2) AutoMLP is compared with other learners including individual (focusing on neural network-based learners) and ensemble learners; and (3) AutoECODB is compared with other preprocessing methods. Furthermore, in order to validate the generality of the framework, Auto-MeDiSine is tested on another publicly available BioStat Diabetes Dataset where it outperforms the existing reported results, reaching an accuracy of 97.1%.

Keywords

Classification Disease prediction Machine learning Multilayer perceptron Outlier detection 

Notes

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Ahmed M, Afzal H, Siddiqi I, Khan B (2017) Mcs: multiple classifier system to predict the churners in the telecom industry. In: SAI Intelligent Systems Conference 2017, London, UKGoogle Scholar
  2. 2.
    Ahmed M, Rasool AG, Afzal H, Siddiqi I (2017) Improving handwriting based gender classification using ensemble classifiers. Expert Syst Appl 85(1):158–168Google Scholar
  3. 3.
    Aibinu AM, Salami MJE, Shafie AA (2011) A novel signal diagnosis technique using pseudo complex-valued autoregressive technique. Expert Syst Appl 38(8):9063–9069Google Scholar
  4. 4.
    Al Jarullah AA (2011) Decision tree discovery for the diagnosis of type ii diabetes. In: 2011 International conference on innovations in information technology (IIT). IEEE, pp 303–307Google Scholar
  5. 5.
    Al Shalabi L, Shaaban Z (2006) Normalization as a preprocessing engine for data mining and the approach of preference matrix. In: International conference on dependability of computer systems, 2006. DepCos-RELCOMEX’06. IEEE, pp 207–214Google Scholar
  6. 6.
    Ali R, Siddiqi MH, Idris M, Kang BH, Lee S (2014) Prediction of diabetes mellitus based on boosting ensemble modeling. In: International conference on ubiquitous computing and ambient intelligence. Springer, pp 25–28Google Scholar
  7. 7.
    Anbarasi M, Anupriya E, Iyengar N (2010) Enhanced prediction of heart disease with feature subset selection using genetic algorithm. Int J Eng Sci Technol 2(10):5370–5376Google Scholar
  8. 8.
    Apolloni B, Avanzini G, Cesa-Bianci N, Ronchini G (1990) Diagnosis of epilepsy via backpropagation. In: Proceedings of the 1990 international joint conference on neural networks, vol 2, pp 571–574Google Scholar
  9. 9.
    Baudat G, Anouar F (2000) Generalized discriminant analysis using a kernel approach. Neural Comput 12(10):2385–2404Google Scholar
  10. 10.
    Bay SD, Schwabacher M (2003) Mining distance-based outliers in near linear time with randomization and a simple pruning rule. In: Proceedings of the ninth ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 29–38Google Scholar
  11. 11.
    Bounds DG, Lloyd PJ, Mathew B, Waddell G (1988) A multilayer perceptron network for the diagnosis of low back pain. In: IEEE international conference on neural networks 1988. IEEE, pp 481–489Google Scholar
  12. 12.
    Breuel T, Shafait F (2010) Automlp: simple, effective, fully automated learning rate and size adjustment. In: The learning workshop. UtahGoogle Scholar
  13. 13.
    Daho MEH, Settouti N, Lazouni MEA, Chikh MA (2013) Recognition of diabetes disease using a new hybrid learning algorithm for nefclass. In: 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA). IEEE, pp 239–243Google Scholar
  14. 14.
    DeGroff CG, Bhatikar S, Hertzberg J, Shandas R, Valdes-Cruz L, Mahajan RL (2001) Artificial neural network-based method of screening heart murmurs in children. Circulation 103(22):2711–2716Google Scholar
  15. 15.
    Delen D, Walker G, Kadam A (2005) Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med 34(2):113–127Google Scholar
  16. 16.
    Ding C, Peng H (2005) Minimum redundancy feature selection from microarray gene expression data. J Bioinform Comput Biol 3(02):185–205Google Scholar
  17. 17.
    Dreiseitl S, Ohno-Machado L (2002) Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform 35(5):352–359Google Scholar
  18. 18.
    Farhanah S, Jafan B, Ali DM (2005) Diabetes mellitus forecast using artificial neural networks (ann). In: Asian conference on sensors and the international conference on new techniques in pharmaceutical and medical research proceedings (IEEE), pp 135–138Google Scholar
  19. 19.
    Floyd CE, Lo JY, Yun AJ, Sullivan DC, Kornguth PJ (1994) Prediction of breast cancer malignancy using an artificial neural network. Cancer 74(11):2944–2948Google Scholar
  20. 20.
    Guo Y, Bai G, Hu Y (2012) Using bayes network for prediction of type-2 diabetes. In: 2012 international conference for internet technology and secured transactions. IEEE, pp 471–472Google Scholar
  21. 21.
    Gysels E, Renevey P, Celka P (2005) Svm-based recursive feature elimination to compare phase synchronization computed from broadband and narrowband eeg signals in brain-computer interfaces. Signal Process 85(11):2178–2189zbMATHGoogle Scholar
  22. 22.
    Hall MA (2000) Correlation-based feature selection of discrete and numeric class machine learning (Working paper 00/08). University of Waikato, Hamilton, New ZealandGoogle Scholar
  23. 23.
    Han J, Rodriguez JC, Beheshti M (2008) Diabetes data analysis and prediction model discovery using rapidminer. In: 2008 Second international conference on future generation communication and networking, vol 3. IEEE, pp 96–99Google Scholar
  24. 24.
    Han L, Luo S, Yu J, Pan L, Chen S (2015) Rule extraction from support vector machines using ensemble learning approach: an application for diagnosis of diabetes. IEEE J Biomed Health Inform 19(2):728–734Google Scholar
  25. 25.
    Hewahi NM, Saad MK (2007) Class outliers mining: distance-based approach. Int J Intell Technol 2(1):55–68Google Scholar
  26. 26.
    Hilger F, Molau S, Ney H et al (2002) Quantile based histogram equalization for online applications. In: INTERSPEECHGoogle Scholar
  27. 27.
    Imbens GW, Lancaster T (1996) Efficient estimation and stratified sampling. J Econom 74(2):289–318MathSciNetzbMATHGoogle Scholar
  28. 28.
    Jahangir M, Afzal H, Ahmed M, Khurshid K, Nawaz R (2017) An expert system for diabetes prediction using auto tuned multi-layer perceptron. In: Intelligent systems conference (IntelliSys) 2017. IEEE, pp 722–728Google Scholar
  29. 29.
    Johns MV (1988) Importance sampling for bootstrap confidence intervals. J Am Stat Assoc 83(403):709–714MathSciNetzbMATHGoogle Scholar
  30. 30.
    Kalaiselvi C, Nasira G (2014) A new approach for diagnosis of diabetes and prediction of cancer using anfis. In: 2014 World congress on computing and communication technologies (WCCCT). IEEE, pp 188–190Google Scholar
  31. 31.
    Kayaer K, Yıldırım T (2003) Medical diagnosis on pima indian diabetes using general regression neural networks. In: Proceedings of the international conference on artificial neural networks and neural information processing (ICANN/ICONIP), pp 181–184Google Scholar
  32. 32.
    Kharya S (2012) Using data mining techniques for diagnosis and prognosis of cancer disease. arXiv preprint arXiv:1205.1923
  33. 33.
    Kumari VA, Chitra R (2013) Classification of diabetes disease using support vector machine. Int J Eng Res Appl 3(2):1797–1801Google Scholar
  34. 34.
    Li L (2014) Diagnosis of diabetes using a weight-adjusted voting approach. In: 2014 IEEE international conference on bioinformatics and bioengineering (BIBE). IEEE, pp 320–324Google Scholar
  35. 35.
    Nnamoko NA, Arshad FN, England D, Vora J (2014) Meta-classification model for diabetes onset forecast: a proof of concept. In: 2014 IEEE international conference on bioinformatics and biomedicine (BIBM). IEEE, pp 50–56Google Scholar
  36. 36.
    Ohno-Machado L, Musen MA (1997) Sequential versus standard neural networks for pattern recognition: an example using the domain of coronary heart disease. Comput Biol Med 27(4):267–281Google Scholar
  37. 37.
    Park J, Edington DW (2001) A sequential neural network model for diabetes prediction. Artif Intell Med 23(3):277–293Google Scholar
  38. 38.
    PObi S, Hall LO (2006) Predicting juvenile diabetes from clinical test results. In: The 2006 IEEE international joint conference on neural network proceedings. IEEE, pp 2159–2165Google Scholar
  39. 39.
    Polat K, Güneş S, Arslan A (2008) A cascade learning system for classification of diabetes disease: generalized discriminant analysis and least square support vector machine. Expert Syst Appl 34(1):482–487Google Scholar
  40. 40.
    Polikar R (2006) Ensemble based systems in decision making. IEEE Circuits Syst Mag 6(3):21–45Google Scholar
  41. 41.
    Price AL, Patterson NJ, Plenge RM, Weinblatt ME, Shadick NA, Reich D (2006) Principal components analysis corrects for stratification in genome-wide association studies. Nat Genet 38(8):904–909Google Scholar
  42. 42.
    Raicharoen T, Lursinsap C (2002) Critical support vector machine without kernel function. In: Proceedings of the 9th international conference on neural information processing, 2002. ICONIP’02, vol 5. IEEE, pp 2532–2536Google Scholar
  43. 43.
    Rashid SF, Shafait F, Breuel TM (2012) Scanning neural network for text line recognition. In: 2012 10th IAPR international workshop on document analysis systems (DAS). IEEE, pp 105–109Google Scholar
  44. 44.
    Saad MK, Hewahi NM (2009) A comparative study of outlier mining and class outlier mining. Comput Sci Lett 1(1)Google Scholar
  45. 45.
    Sabariah MMK, Hanifa SA, Sa’adah MS (2014) Early detection of type ii diabetes mellitus with random forest and classification and regression tree (cart). In: 2014 International conference of advanced informatics: concept, theory and application (ICAICTA). IEEE, pp 238–242Google Scholar
  46. 46.
    Saha S, Raghava G (2006) Prediction of continuous b-cell epitopes in an antigen using recurrent neural network. Proteins Struct Funct Bioinform 65(1):40–48Google Scholar
  47. 47.
    Salami M, Shafie A, Aibinu A (2010) Application of modeling techniques to diabetes diagnosis. In: IEEE EMBS conference on biomedical engineering & sciencesGoogle Scholar
  48. 48.
    Sathyadevi G (2011) Application of cart algorithm in hepatitis disease diagnosis. In: 2011 International conference on recent trends in information technology (ICRTIT). IEEE, pp 1283–1287Google Scholar
  49. 49.
    Saxena K, Sharma R et al (2015) Diabetes mellitus prediction system evaluation using c4. 5 rules and partial tree. In: 2015 4th international conference on reliability, infocom technologies and optimization (ICRITO) (trends and future directions). IEEE, pp 1–6Google Scholar
  50. 50.
    Shanker MS (1996) Using neural networks to predict the onset of diabetes mellitus. J Chem Inf Comput Sci 36(1):35–41Google Scholar
  51. 51.
    Specht DF (1991) A general regression neural network. IEEE Trans Neural Netw 2(6):568–576Google Scholar
  52. 52.
    Srinivas K, Rani BK, Govrdhan A (2010) Applications of data mining techniques in healthcare and prediction of heart attacks. Int J Comput Sci Eng (IJCSE) 2(02):250–255Google Scholar
  53. 53.
    Sumathy M, Thirugnanam M, Kumar P, Jishnujit T, Kumar KR (2010) Diagnosis of diabetes mellitus based on risk factors. Int J Comput Appl 10(4):1–4Google Scholar
  54. 54.
    Suykens JA, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Process Lett 9(3):293–300Google Scholar
  55. 55.
    Tafa Z, Pervetica N, Karahoda B (2015) An intelligent system for diabetes prediction. In: 2015 4th Mediterranean conference on embedded computing (MECO). IEEE, pp 378–382Google Scholar
  56. 56.
    Temurtas H, Yumusak N, Temurtas F (2009) A comparative study on diabetes disease diagnosis using neural networks. Expert Syst Appl 36(4):8610–8615Google Scholar
  57. 57.
    Venkatesan P, Anitha S (2006) Application of a radial basis function neural network for diagnosis of diabetes mellitus. Curr Sci 91(9):1195–1199Google Scholar
  58. 58.
    Wang MH, Lee CS, Li HC, Ko WM (2007) Ontology-based fuzzy inference agent for diabetes classification. In: NAFIPS 2007–2007 annual meeting of the north American fuzzy information processing society. IEEE, pp 79–83Google Scholar
  59. 59.
    Wettayaprasit W, Sangket U (2006) Linguistic knowledge extraction from neural networks using maximum weight and frequency data representation. In: 2006 IEEE conference on cybernetics and intelligent systems. IEEE, pp 1–6Google Scholar
  60. 60.
    Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemom Intell Lab Syst 2(1–3):37–52Google Scholar
  61. 61.
    Yoo I, Alafaireet P, Marinov M, Pena-Hernandez K, Gopidi R, Chang JF, Hua L (2012) Data mining in healthcare and biomedicine: a survey of the literature. J Med Syst 36(4):2431–2448Google Scholar
  62. 62.
    Yu L, Liu H (2003) Feature selection for high-dimensional data: a fast correlation-based filter solution. In: Proceedings of the 20th international conference on machine learning (ICML-03), pp 856–863Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.National University of Sciences and TechnologyIslamabadPakistan
  2. 2.Manchester Metropolitan UniversityManchesterUK

Personalised recommendations