Neural Computing and Applications

, Volume 31, Issue 12, pp 8441–8453 | Cite as

Analysis of computational techniques for diabetes diagnosis using the combination of iris-based features and physiological parameters

  • Piyush SamantEmail author
  • Ravinder Agarwal
Original Article


Digital image processing and advanced machine vision techniques are popular for the diagnosis of disease(s) in biomedical science. This paper presents a detailed comparative analysis of machine learning-based classification techniques to diagnose type 2 diabetes using the combination of iris-based features and physiological parameters. A set of 334 subjects are investigated which are divided into diabetic and non-diabetic groups. Moreover, the diabetic group is classified into three different subgroups according to the duration of the diabetic state. Statistical features, gray-level co-occurrence matrix, and gray-level run length matrix-based features are extracted from the specific areas of iris. Nine classifiers of different application areas are selected, and subsequently, six parameters (accuracy, precision, sensitivity, specificity, F-score, and area under the curve) of each classifier are analyzed. The analysis provided promising results with more than 95% of accuracy. The proposed technique can be used as a noninvasive and non-contact diabetes diagnosis tool which can help to find out the duration of diabetes in patients and the prevalence of diabetes.


Diabetes diagnosis Iris Physiological parameters Iridology Classification 



  1. 1.
    Bengtsson E, Danielsen H, Treanor D et al (2017) Computer-aided diagnostics in digital pathology. J Int Soc Adv Cytom 91:551–554. CrossRefGoogle Scholar
  2. 2.
    Oliveira FPM, Tavares JMRS (2014) Medical image registration: a review. Comput Methods Biomech Biomed Eng 17:73–93CrossRefGoogle Scholar
  3. 3.
    Kanawong R, Obafemi-Ajayi T, Liu D, Zhang M, Dong X, Duan Y (2017) Tongue image analysis and its mobile app development for health diagnosis. Adv Exp Med Biol 1005:99–121CrossRefGoogle Scholar
  4. 4.
    Pang B, Zhang D, Wang K (2005) Tongue image analysis for appendicitis diagnosis. Inf Sci (NY) 175:160–176. CrossRefGoogle Scholar
  5. 5.
    Goyal K, Agarwal R (2017) Pulse based sensor design for wrist pulse signal analysis and health diagnosis. Biomed Res 28:5187–5195Google Scholar
  6. 6.
    Leung TS, Kapur K, Guilliam A et al (2015) Screening neonatal jaundice based on the sclera color of the eye using digital photography. Biomed Opt Express 6:132–140. CrossRefGoogle Scholar
  7. 7.
    Xiong T, Qu Y, Cambier S, Mu D (2011) The side effects of phototherapy for neonatal jaundice: what do we know? What should we do? Eur J Pediatr 170:1247–1255. CrossRefGoogle Scholar
  8. 8.
    Laddi A, Kumar S, Sharma S et al (2014) Non-invasive Jaundice detection using machine vision. IETE J Res 59:591–595. CrossRefGoogle Scholar
  9. 9.
    Sharan F (1992) Iridology: A complete guide to diagnosing through the iris and to related forms of treatment. HarperCollins, LondonGoogle Scholar
  10. 10.
    Hollingsworth K, Bowyer KW, Flynn PJ (2009) Pupil dilation degrades iris biometric performance. Comput Vis Image Underst 113:150–157. CrossRefGoogle Scholar
  11. 11.
    Hussein SE, Hassan OA, Granat MH (2013) Assessment of the potential iridology for diagnosing kidney disease using wavelet analysis and neural networks. Biomed Signal Process Control 8:534–541. CrossRefGoogle Scholar
  12. 12.
    Levin LA, Nilsson SF, Hoeve JV, Wu SM (2011) ADLER’S physiology of the eye, 11th edn. Elsevier Saunders Publishers, PhiladelphiaGoogle Scholar
  13. 13.
    Bowyer KW, Hollingsworth K, Flynn PJ (2008) Image understanding for iris biometrics: a survey. Comput Vis Image Underst 110:281–307. CrossRefGoogle Scholar
  14. 14.
    Buchanan TJ, Sutherland CJ, Strettle RJ et al (1996) An investigation of the relationship between anatomical features in the iris and systemic disease, with reference to iridology. Complement Ther Med 4:98–102. CrossRefGoogle Scholar
  15. 15.
    Daugman J (2003) The importance of being random: statistical principles of iris recognition. Pattern Recognit 36:279–291. CrossRefGoogle Scholar
  16. 16.
    Othman Z, Satria Prabuwono A (2010) Preliminary study on iris recognition system: tissues of body organs in iridology. In: Proceedings of 2010 IEEE EMBS conference on biomedical engineering and sciences IECBES 2010, pp 115–119.
  17. 17.
    Ma L, Zhang D, Li N et al (2013) Iris-based medical analysis by geometric deformation features. IEEE J Biomed Heal Informatics 17:223–231. CrossRefGoogle Scholar
  18. 18.
    Um J-Y, An N-H, Yang G-B et al (2005) Novel approach of molecular genetic understanding of iridology: relationship between iris constitution and angiotensin converting enzyme gene polymorphism. Am J Chin Med 33:501–505. CrossRefGoogle Scholar
  19. 19.
    Ramlee RA, Aziz KA, Ranjit S, Esro M et al (2011) Automated detecting arcus senilis, symptom for cholesterol presence using iris recognition algorithm. J Telecommun Electron Comput Eng 3:29–39Google Scholar
  20. 20.
    Ramlee RA, Azha K, Singh R, Singh S (2011) Detecting cholesterol presence with iris recognition algorithm. NTECH Open Access Publisher, pp 129–148Google Scholar
  21. 21.
    Ramlee RA, Ranjit S (2009) Using iris recognition algorithm, detecting cholesterol presence. In: International conference on information management and engineering, ICIME. IEEE Computer Society, pp 714–717Google Scholar
  22. 22.
    Bansal A, Agarwal R, Sharma RK (2015) Determining diabetes using iris recognition system. Int J Diabetes Dev Ctries 35:432–438. CrossRefGoogle Scholar
  23. 23.
    Banzi JF, Xue Z (2015) An automated tool for non-contact, real time early detection of diabetes by computer vision. Int J Mach Learn Comput 5:225–229. CrossRefGoogle Scholar
  24. 24.
    Salles LF, Júlia M, De EAC (2008) The prevalence of iridologic signs in individuals with Diabetes Mellitus *. Acta Paul Enferm 21:474–480CrossRefGoogle Scholar
  25. 25.
    Salles LF, Silva MJ (2015) The sign of the Cross of Andreas in the iris and Diabetes Mellitus: a longitudinal study. Rev Esc Enferm USP 49:626–631. CrossRefGoogle Scholar
  26. 26.
    Bhatia PSK, Atole P, Kamble S, Telang P (2015) Methodology for detecting diabetic presence from iris image analysis. Int J Adv Res Comput Eng Technol 4:776–779Google Scholar
  27. 27.
    Pergad ND, More SB (2015) Detection of diabetic presence from iris by using support vector machine. Int J Eng Sci Res 4:562–565Google Scholar
  28. 28.
    Heydari M, Teimouri M, Heshmati Z (2015) Comparison of various classification algorithms in the diagnosis of type 2 diabetes in Iran. Int J Diabetes Dev Ctries 36:167–173. CrossRefGoogle Scholar
  29. 29.
    Zahirnia K, Teimouri M, Rahmani R, Salaq A (2015) Diagnosis of Type 2 diabetes using cost-sensitive learning. In: International conference on computer knowledge engineering diagnosis. IEEE, pp 58–63.
  30. 30.
    Dwivedi AK (2017) Analysis of computational intelligence techniques for diabetes mellitus prediction. Neural Comput Appl. CrossRefGoogle Scholar
  31. 31.
    Sudha M (2017) Evolutionary and neural computing based decision support system for disease diagnosis from clinical data sets in medical practice. J Med Syst 41:178. CrossRefGoogle Scholar
  32. 32.
    Tama BA, Rhee KH (2017) Tree-based classifier ensembles for early detection method of diabetes: an exploratory study. Artif Intell Rev. CrossRefGoogle Scholar
  33. 33.
    Dwivedi AK (2016) Performance evaluation of different machine learning techniques for prediction of heart disease. Neural Comput Appl. CrossRefGoogle Scholar
  34. 34.
    Meng XH, Huang YX, Rao DP et al (2013) Comparison of three data mining models for predicting diabetes or prediabetes by risk factors. Kaohsiung J Med Sci 29:93–99. CrossRefGoogle Scholar
  35. 35.
    Alvarez-betancourt Y, Garcia-silvente M (2016) A keypoints-based feature extraction method for iris recognition under variable image quality conditions. Knowl Based Syst 92:169–182. CrossRefGoogle Scholar
  36. 36.
    Samant P, Agarwal R (2018) Comparative analysis of classification based algorithms for diabetes diagnosis using iris images. J Med Eng Technol 42:35–42. CrossRefGoogle Scholar
  37. 37.
    Daugman J (2004) How iris recognition works. IEEE Trans Circuits Syst Video Technol 14:715–739. CrossRefGoogle Scholar
  38. 38.
    Kaur N, Juneja M (2014) A review on Iris recognition. Recent Adv Eng Comput Sci RAECS 2014:6–8Google Scholar
  39. 39.
    Wildes RP (1997) Iris recognition: an emerging biometric technology. Proc IEEE 85:1348–1363. CrossRefGoogle Scholar
  40. 40.
    Daugman J (2007) New methods in iris recognition. IEEE Trans Syst Man Cybern 37:1167–1175. CrossRefGoogle Scholar
  41. 41.
    Zhou N, Wang L (2007) A Modified T-test feature selection method and its application on the hapmap genotype data. Genomics Proteomics Bioinform 5:242–249. CrossRefGoogle Scholar
  42. 42.
    Karamizadeh S, Abdullah SM, Manaf AA et al (2013) An overview of principal component analysis. J Signal Inf Process 04:173–175. CrossRefGoogle Scholar
  43. 43.
    Samant P, Agarwal R (2018) Machine learning techniques for medical diagnosis of diabetes using iris images. Comput Methods Progr Biomed 157:121–128. CrossRefGoogle Scholar

Copyright information

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

Authors and Affiliations

  1. 1.Thapar Institute of Engineering and TechnologyPatialaIndia

Personalised recommendations