ARTIFICIAL NEURAL NETWORKS - A NEW APPROACH IN NON-INVASIVE MONITORING OF INFLAMMATORY BOWEL DISEASES

Authors

  • Iolanda Valentina POPA “Grigore T. Popa” University of Medicine and Pharmacy Iasi
  • Miaela DRANGA “Grigore T. Popa” University of Medicine and Pharmacy Iasi
  • Otilia GAVRILESCU “Grigore T. Popa” University of Medicine and Pharmacy Iasi
  • Raluca Cezara POPA “Grigore T. Popa” University of Medicine and Pharmacy Iasi
  • Anca CARDONEANU “Grigore T. Popa” University of Medicine and Pharmacy Iasi
  • B. CUCUTEANU “Grigore T. Popa” University of Medicine and Pharmacy Iasi
  • Cristina CIJEVSCHI-PRELIPCEAN “Grigore T. Popa” University of Medicine and Pharmacy Iasi
  • Catalina MIHAI “Grigore T. Popa” University of Medicine and Pharmacy Iasi

Keywords:

INFLAMMATORY BOWEL DISEASE, NON-INVASIVE METHODS, ARTIFICIAL NEURAL NETWORKS

Abstract

Our aim was to use artificial neural networks (ANN) for assessing inflammatory bowel disease (IBD) activity using various biological and historical data. Material and methods: The study group included 100 patients aged 18-80 years, diagnosed with ulcerative colitis (UC) - 59% and Crohn’s Disease (CD) - 41% based on clinical, biological, imaging and histopathological criteria. Both pre-diagnosed and newly diagnosed cases were included. Study database contains multiple parameters obtained through anamnesis, physical exam, evaluation of nutritional status (body mass index), laboratory tests, imaging investigations. We built the neural network using MATLAB 7.0. Results: The accuracy of the mathematical model was measured in terms of mean square error (MSE) and mean absolute percentage error (MAPE). Calculated MAPE values for Ulcerative Colitis Disease Activity Index (UCDAI) score and Rachmilewitz score were 52,34% and 47,15% respectively. None of the scores were estimated with excellent or high precision. The Rachmilewitz score was estimated with average accuracy because the network included currently few registered patients. All other scores were estimated with low precision. Conclusions: The partial results obtained in the first stage of this study are encouraging given the small number of patients enrolled. Thus, for the next phases of the study, with the ongoing development of the database, we expect to achieve results with higher accuracy.

Author Biographies

  • Iolanda Valentina POPA, “Grigore T. Popa” University of Medicine and Pharmacy Iasi

    Faculty of Medicine
     Department of Medical Specialties (I)

  • Miaela DRANGA, “Grigore T. Popa” University of Medicine and Pharmacy Iasi

    Faculty of Medicine
    Department of Medical Specialties (I)

  • Otilia GAVRILESCU, “Grigore T. Popa” University of Medicine and Pharmacy Iasi

    Faculty of Medicine
    Department of Medical Specialties (I)

  • Raluca Cezara POPA, “Grigore T. Popa” University of Medicine and Pharmacy Iasi

    Faculty of Medicine
    Department of Medical Specialties (I)

  • Anca CARDONEANU, “Grigore T. Popa” University of Medicine and Pharmacy Iasi

    Faculty of Medicine
    Department of Medical Specialties (II)

  • B. CUCUTEANU, “Grigore T. Popa” University of Medicine and Pharmacy Iasi

    Faculty of Medicine
    Department of Surgery (II)

  • Cristina CIJEVSCHI-PRELIPCEAN, “Grigore T. Popa” University of Medicine and Pharmacy Iasi

    Faculty of Medicine
    Department of Medical Specialties (I)

  • Catalina MIHAI, “Grigore T. Popa” University of Medicine and Pharmacy Iasi

    Faculty of Medicine
    Department of Medical Specialties (I)

References

1. Lewis JD. The utility of biomarkers in the diagnosis and therapy of inflammatory bowel disease. Gastroenterol 2011; 140(6): 1817-1826.
2. Cioffi M, Rosa AD, Serao R, Picone I, Vietri MT. Laboratory markers in ulcerative colitis: Current insights and future advances. World J Gastroint Pathophysiol 2015; 6(1): 13-22.
3. Conklin L, Alex P. New serological biomarkers of inflammatory bowel disease. World J Gastroenterol 2008; 14: 5115-5124.
4. Dranga M, Dumitrescu G, Badea M, et al. The semi-quantitative calprotectin rapid test - it is useful in inflammatory bowel disease? Rev Med Chir Soc Med Nat Iasi 2012; 116(3): 761-765.
5. Gavrilescu O, Dranga M, Mihaic C, Cijevschi Prelipcean C. Quality of life in Crohn’s disease patients. Rev Med Chir Soc Med Nat Iasi 2015; 119(2): 340-345.
6. Heard BJ, Rosvold JM, Fritzler M J, El-Gabalawy H, Wiley JP, Krawetz R J. A computational method to differentiate normal individuals, osteoarthritis and rheumatoid arthritis patients using serum biomarkers. J R Soc Interface 2014; 11(97): 1234-1254.
7. Shepherd SF, McGuire ND, De Lacy Costello BPJ et al. The use of a gas chromatograph coupled to a metal oxide sensor for rapid assessment of stool samples from irritable bowel syndrome and inflammatory bowel disease patients. J Breath Res 2014; 8(2): 1034-1054.
8. Peng JC, Ran ZH, Shen J. Seasonal variation in onset and relapse of IBD and a model to predict the frequency of onset, relapse, and severity of IBD based on artificial neural network. Int J Colorectal Dis 2015; 30(9): 1267-1273.
9. Hardalaç F, Basaranoglu M, Yüksel M, Kutbay U. The rate of mucosal healing by azathioprine therapy and prediction by artificial systems. Turk.J Gastroenterol 2015; 26(4): 315-321.
10. Zheng MH, Shi KQ, Lin XF, Xiao DD, Chen LL, Liu WY, Fan YC, Chen YP. A model to predict 3-month mortality risk of acute-on-chronic hepatitis B liver failure using artificial neural network. J Viral Hepat 2013; 20(4): 248-255.
11. Liu X, Li NS, Lv LS, Huang JH, Tang H, Chen JX, Ma HJ, Wu XM, Lou TQ. A comparison of the performances of an artificial neural network and a regression model for GFR estimation. Am J Kidney Dis 2013; 62(6): 1109-1115.
12. Baxt WG (1995) Application of artificial neural networks to clinical medicine. Lancet 1995; 46(8983): 1135-1138.
13. Wang D, Wang Q, Shan F, Liu B, Lu C (2010) Identification of the risk for liver fibrosis on CHB patients using an artificial neural network based on routine and serum markers. BMC Infect Dis 2010; 5: 12456-1362.
14. Baxt WG. Application of artificial neural networks to clinical medicine. Lancet 1995; 346(8983): 1135-1138.
15. Cross SS, Harrison RF, Kennedy RL. Introduction to neural networks. Lancet 1995; 346(8982): 1075-1079.
16. Traeger M, Eberhart A, Geldner G, Morin AM, Putzke C, Wulf H, Eberhart LH. Artificial neural networks. Theory and applications in anesthesia, intensive care and emergency medicine. Anaesthesist 2003; 52(11): 1055-1061.
17. Wei CH, Lee Y. Sequential forecast of incident duration using artificial neural network models. Accid Anal Prev 2007; 39(5): 944-954.

Additional Files

Published

2017-12-22

Issue

Section

INTERNAL MEDICINE - PEDIATRICS