Experience of neuronet diagnosis and prediction of peptic ulcer disease by results of risk factors’ analysis

Aim. To develop and verify a method for diagnosis of peptic ulcer based on neural network analysis of data on patients’ risk factors.

Materials and methods. This article presents the results of a study based on materials on risk factors of 488 patients. The data was analyzed using internally developed artificial neural network (Certificate of State Registration of Program for Computers (RU) no. 2017613090).

The results of the study. The proposed approach demonstrated the levels of sensitivity of 74.4%, m = 4.3 and specificity of 93.3%, m = 2.46 during clinical testing.

The prediction of the age of probable hospitalization ensured the generation of an array of data for which the Mean Absolute Error (MAE) of the prognosis was 1.8 years, m = 0.11 in the training set and 1.9 years,  m = 0.15 in the clinical testing set. The maximum of absolute prognosis error in the clinical testing set did not exceed 2.2 at p = 0.95 and 2.3 years at p = 0.99.

Conclusion.  A new method is proposed for diagnosis of peptic ulcer based on a neural network analysis of data on patients’ risk factors. During clinical testing of the model, this approach demonstrated Area Under the Curve (AUC) levels reaching 0.943. The use of the artificial neural network also made it possible to predict the age of probable hospitalization. The use of the neural network demonstrated additional advantages including: non-invasiveness, the lack of need to prepare the patient for the study and the possibility to obtain results immediately after the onset of the disease without a time delay for sample processing.

artificial neural network, neuronet, multilayer perceptron, diagnosis, diagnostics, peptic ulcer disease, artificial intelligence, prognosis

1. Antonov A.E., Lazarenko V.A., Novomlinets Yu.P. Surgical aspects of conditionally curative treatment of exacerbated peptic ulcer disease. Vestnik novykh meditsinskikh tekhnologiy – Journal of New Medical Technologies. 2006; 13 (3): 150–152 (in Russ.).

2. Lopukhova V.A., Tarasenko I.V., Korenevskaya E.V. Research of demographic processes: premature mortality and years of potential life lost among the citizens of Kurchatov-city. Sovremennye problemy nauki i obrazovaniya – Modern Problems of Science and Education. 2017; (2): 113 (in Russ.).

3. Kaylanich G.A., Lopukhova V.A., Kaylanich E.A., Tarasenko I.V. Quality assessment of hospital care based on the formalized interview of the population Orel-city. Sovremennye problemy nauki i obrazovaniya – Modern Рroblems of Science and Education. 2017; (2): 5 (in Russ.).

4. Svetyy L.I., Lopukchova V.A., Tarasenko I.V., Klimkin A.S. The use of health technology assessment in making effective management decisions. Zhurnal nauchnyh statej Zdorov’e i obrazovanie v XXI veke – The Journal of Scientific Articles Health and Education Millenium. 2013; 15 (1–4): 234–235 (in Russ.).

5. Lopukhova V.A., Tarasenko I.V., Kaylanich G.A., Kaylanich E.A. The study of outpatient care quality in medical institutions of Orel-city. Sovremennye problemy nauki i obrazovanija – Modern Рroblems of Science and Еducation. 2016; (5). http://www.science-education.ru/ru/article/view?id=25383. (access date 28.11.2016 (in Russ.).

6. Simonyan R.Z., Kailanich G.A., Lopukhova V.A., Tarasenko I.V. The study of medical care quality in the health technology assessment. Mezhdunarodnyj zhurnal prikladnyh i fundamental’nyh issledovanij. 2016; (8): 185–187 (in Russ.).

7. Kuramshina O.A., Kofanova Yu.A., Gabbasova L.V., Kryukova A.Ya. Risk factors of gastroduodenal pathology development. educational programmes in therapeutic strategies applied to youth. Meditsinskiy vestnik Bashkortostana – Bashkortostan Medical Journal. 2011; 6 (3): 19–23 (in Russ.).

8. Soshina A.A., Sergeeva V.V., Zinyaeva T.V. Clinical features and prognosis in patients examined in medical and social expertise bureaus in relation to peptic ulcer disease. Kazanskiy meditsinskiy zhurnal – Kazan Medical Journal. 2013; 94 (1): 124–127 (in Russ.).

9. Malyshenko O.S., Beloborodova E.I., Vavilov A.M. Impact of age and type of behavior on the course of ulcer disease. Terapevticheskiy arkhiv – Therapeutic Archive. 2005; (2): 28–31 (in Russ.).

10. Vakhrushev Ya.M., Efremova L.I., Belova E.V. Age-related comparative characteristics of ulcer disease course. Terapevticheskiy arkhiv – Therapeutic Archive. 2004; (4): 15–18 (in Russ.).

11. Гребенев А.Л., Шептулин А.А. Язвенная болезнь. М.: Медицина, 1995: 187. [Grebenev A.L., Sheptulin A.A. Ulcer Disease. M.: Meditsina Publ., 1995: 187 (in Russ.)].

12. Lopatina V.V. Risk factors in the development of ulcer disease. Zdorov’e naseleniya i sreda obitaniya. 2011; (12): 16–18 (in Russ.).

13. Boytsov S.A., Samorodskaya I.V., Tret’yakov V.V. Gradient of mortality of persons aged 40–59 in regions of the Russian federation. Vestnik Rossiyskoy akademii meditsinskikh nauk – Annals of the Russian Аcademy of Мedical Sciences. 2014; (7): 106–111 (in Russ.).

14. Galea S., Tracy M., Hoggatt K.J., Di Maggio C., Karpati A. Estimated deaths attributable to social factors in the United States. Am. J. of Publ. Health. 2011; 101 (8): 1456–1465.

15. Karamnova N.S., Shal’nova S.A., Deev A.D., Boytsov S.A. Habits of nutrition, characterizing the level of cardiovascular health in the Russian population. The results of the epidemiological study essay-RF. CardioSomatika. 2015; (S1): 47 (in Russ.).

16. Rosenstock S., Jorgensen T., Bonnevie O., Andersen L. Risk factors for peptic ulcer disease: a population based prospective cohort study comprising 2416 Danish adults. Gut. 2003; (52): 186–93.

17. Solov’eva S.V. NSAID-gastropathies – the problem of the elderly. Akademicheskiy zhurnal Zapadnoy Sibiri – Academic Journal of West Siberia. 2012; (3): 28 (in Russ.).

18. Konstantinova E.D., Varaksin A.N., Zhovner I.V. Identification of the main risk factors for non-infectious diseases: method of classification trees. Gigiena i sanitarija. 2013; (5): 69–72 (in Russ.).

19. Bezrukov N.S., Eremin E.L. Construction and modeling of the adaptive neuro-fuzzy system in the problem of medical diagnostics. Informatika i sistemy upravleniya – Information Science and Control Systems. 2005; 2 (10): 36–46 (in Russ.).

20. Skvortsova V.I. Seven principles of organization of healthcare. Voprosy ekonomiki i upravlenija dlja rukovoditelej zdravoohranenija. 2010; (5): 7–14 (in Russ.).

21. Lazarenko V.A., Antonov A.E., Novomlinec Ju.P. Visual environment for nonparametric correlation analysis of risk factors in patients with surgical diseases. Zhurnal nauchnyh statej Zdorov’e i obrazovanie v XXI veke – The Journal of Scientific Articles Health and Education Millenium. 2017; 19 (4): 34–37 (in Russ.).

22. Lazarenko V.A., Antonov A.E., Prasolov A.V., Churilin M.I. The problem of regression analysis optimization in evaluation of risk factors influencing the development of surgical diseases of hepatopancreatoduodenal zone. Zhurnal nauchnyh statej Zdorov’e i obrazovanie v XXI veke – The Journal of Scientific Articles Health and Education Millenium. 2017; 19 (5): 24–27 (in Russ.).

23. Lazarenko V.A., Antonov A.E. The role of social risk factors in peptic ulcer development in Kursk Region. Kurskij nauchno-prakticheskij vestnik “Chelovek i ego zdorov’e” – Kursk Scientific and Practical Bulletin “Man and His Health”. 2016; 2: 35–39 (in Russ.). DOI: 10.21626/vestnik/2016-2/06.

24. Shhepin V.O., Rastorgueva T.I., Proklova T.N. More on prospective directions of healthcare development in the Russian Federation. Bjulleten’ Nacional’nogo nauchnoissledovatel’skogo instituta obshhestvennogo zdorov’ja imeni N.A. Semashko. 2012; (1): 147–152 (in Russ.).

25. Mustafaev A.G. Use of artificial neural networks in early diagnosis of diabetes mellitus disease. Kibernetika i programmirovanie – Cybernetics and Programming. 2016; (2): 1–7 (in Russ.). DOI: 10.7256/2306-4196.2016.2.17904.

26. Lazarenko V.A., Antonov A.E. System for Intellectual Analysis and Diagnosis of Diseases. Certificate for State Registration of Programs for Computers (RU) no. 2017613090. Applicant FSBEI HE “Kursk State Medical University” MOH Russia no. 2016664120 on 22.12.2016; published on 10.03.2017 (in Russ.).

27. Lazarenko V.A., Antonov A.E. Experience of the development of the software package for neural network diagnosis and prediction of diseases of hepatopancreatoduodenal zone. Physitians and IT. 2017; (4): 132–140 (in Russ.).

28. Lazarenko V.A., Antonov A.E. Evaluation of the quality of functioning of artificial neural network with logic outputs in the diagnosis of diseases of hepatopancreatoduodenal zone. Kazan Medical Journal. 2017; 98 (6): 928–932 (in Russ.). DOI: 10.17750/KMJ2017-928.