UDC

616+004.67

Authors

Mariya V. Vyucheyskaya*, Irina N. Kraynova*, Anatoliy V. Gribanov*
*Northern (Arctic) Federal University named after M.V. Lomonosov (Arkhangelsk, Russian Federation)
Corresponding author: Mariya Vyucheyskaya, address: proezd Badigina 3, Arkhangelsk, 163045, Russian Federation; e-mail: m.viuchejskaya@narfu.ru

Abstract

This review analysed the use of neural network technologies in diagnosis of various diseases within cardiology, oncology, pulmonology, gastroenterology, neurology, psychology, etc. The aim was to identify the areas of medicine applying neural network technologies in the most effective way. We considered the structures, learning algorithms and the accuracy of artificial neural networks. The analysis of literature showed that the best model of artificial neural networks for medical diagnosis and prediction is the multilayer perceptron, which is a feedforward network wherein each neuron in one layer has directed connections to the neurons of the subsequent layer, without forming any backward or recurrent connections. We also revealed that the best learning algorithms for a multilayer perceptron are the algorithm of backward propagation of errors and the genetic algorithm. The high accuracy of neural network diagnostic models, described in literature, implies their considerable potential for diagnosis and prediction of various diseases in different areas of medicine. Introducing neural network diagnostic models into clinical practice can provide substantial assistance in medical decision-making, improve the quality and accuracy of diagnosis and reduce the time for patient examination. It is also noteworthy that artificial neural networks can be used in medicine as mathematical models. By changing the input parameters of a neural network model and observing the behaviour of the output signals, one can explore the relevant area, identify and study the medical patterns that the artificial neural network has found in the course of training. The obtained data will contribute to theoretical knowledge in various spheres of medicine.

Keywords

artificial neural networks, medical diagnosis, mathematical modelling

References

1. Gribanov A.V., Dzhos Yu.S. O strategicheskikh napravleniyakh mediko-biologicheskikh issledovaniy [Strategic Areas of Medical and Biological Research]. Vestnik Severnogo (Arkticheskogo) federal’nogo universiteta. Ser.: Medikobiologicheskie nauki, 2013, no. 1, pp. 10–18.
2. Golovinova V.Yu., Kireev S.G., Kotenko P.K., Minaev Yu.L., Shtamburg I.N., Kuz’min S.G. Neyrosetevye modeli prognozirovaniya zabolevaemosti v organizovannykh kollektivakh [Neural Network Models for Prediction of Morbidity in Organized Personnel Groups]. Vestnik Rossiyskoy voenno-meditsinskoy akademii, 2014, no. 3, pp. 150–154.
3. Chasha T.V., Kharlamova N.V., Klimova O.I., Yasinskiy F.N., Yasinskiy I.F. Primenenie neyronnykh setey dlya prognozirovaniya techeniya postgipoksicheskikh narusheniy serdechno-sosudistoy sistemy u novorozhdennykh detey [The Use of Neural Networks to Predict the Course of Posthypoxic Cardiovascular Disorders in Newborns]. Vestnik IGEU, 2009, no. 4, pp. 57–59.
4. Sboev A.G., Gorokhova S.G., Cherniy N.N. Razrabotka neyrosetevoy metodiki rannego diagnostirovaniya ishemicheskoy bolezni serdtsa i koronarnogo ateroskleroza [Developing Artificial Neural Network Techniques for Diagnosing Early Ischaemic Heart Disease and Coronary Atherosclerosis]. Vestnik VGU. Ser.: Khimiya. Biologiya. Farmatsiya, 2011, no. 2, pp. 204–213.
5. Colak M.C., Colak C., Kocatürk H., Sağiroğlu S., Barutçu I. Predicting Coronary Artery Disease Using Different Artificial Neural Network Models. Anadolu Kardiyol. Derg., 2008, vol. 8, no. 4, pp. 249–254.
6. Atkov O.Yu., Gorokhova S.G., Sboev A.G., Generozov E.V., Muraseyeva E.V., Moroshkina S.Y., Cherniy N.N. Coronary Heart Disease Diagnosis by Artificial Neural Networks Including Genetic Polymorphisms and Clinical Parameters. J. Cardiol., 2012, vol. 59, no. 2, pp. 190–194.
7. Niranjana Murthy H.S., Meenakshi M. ANN Model to Predict Coronary Heart Disease Based on Risk Factors. Bonfring Int. J. Man Mach. Interface, 2013, vol. 3, no. 2, pp. 13–18.
8. Moghaddasi H., Mahmoudi I., Sajadi S. Comparing the Efficiency of Artificial Neural Network and Gene Expression Programming in Predicting Coronary Artery Disease. J. Health Med. Inform., 2017, vol. 8, no. 2.
9. Arabasadi Z., Alizadehsani R., Roshanzamir M., Moosaei H., Yarifard A.A. Computer Aided Decision Making for Heart Disease Detection Using Hybrid Neural Network-Genetic Algorithm. Comput. Methods Programs Biomed., 2017, vol. 141, pp. 19–26.
10. Caliskan A., Yuksel M.E. Classification of Coronary Artery Disease Data Sets by Using a Deep Neural Network. EuroBiotech J., 2017, vol. 1, no. 4, pp. 271–277.
11. Yasnitskiy L.N., Dumler A.A., Poleshchuk A.N., Bogdanov K.V., Cherepanov F.M. Neyrosetevaya sistema ekspress-diagnostiki serdechno-sosudistykh zabolevaniy [Neuronetwork System of Cardiovascular Diseases Express-Diagnosis]. Permskiy meditsinskiy zhurnal, 2011, vol. 28, no. 4, pp. 77–86.
12. Yasnitsky L.N., Bogdanov K.V., Cherepanov F.M., Makurina T.V., Dumler A.A., Chugaynov S.V., Poleshchuk A.N. Diagnosis and Prognosis of Cardiovascular Diseases on the Basis of Neural Networks. Biomed. Eng., 2013, vol. 47, no. 3, pp. 160–163.
13. Aravin O.I. Primenenie iskusstvennykh neyronnykh setey dlya analiza patologiy v krovenosnykh sosudakh [Application of Artificial Neural Networks to Analyze Abnormalities in Blood Vessels]. Rossiyskiy zhurnal biomekhaniki, 2011, vol. 15, no. 3, pp. 45–51.
14. Olenko E.S., Kirichuk V.F., Kodochigova A.I., Kolopkova T.A., Demina T.A., Subbotina V.G., Sulkovskaya L.S., Bukotkina E.A. Ispol’zovanie iskusstvennykh neyronnykh setey v prognozirovanii riska razvitiya arterial’noy gipertenzii u penitentsiarnykh sub”ektov [The Use of Artificial Neural Networks in Predicting the Risk of Developing Arterial Hypertension in Penitentiary Subjects]. Mezhdunarodnyy zhurnal prikladnykh i fundamental’nykh issledovaniy, 2009, no. 5, p. 119. Available at: https://www.applied-research.ru/ru/article/view?id=200 (accessed 22 November 2017).
15. Mustafaev A.G. Primenenie iskusstvennykh neyronnykh setey dlya ranney diagnostiki zabolevaniya sakharnym diabetom [The Use of Artificial Neural Networks for Early Diagnosis of Diabetes Mellitus]. Kibernetika i programmirovanie, 2016, no. 2, pp. 1–7.
16. Soltani Z., Jafarian A. A New Artificial Neural Networks Approach for Diagnosing Diabetes Disease Type II. Int. J. Adv. Comput. Sci. Appl., 2016, vol. 7, no. 6.
17. Maclin P.S., Dempsey J. How to Improve a Neural Network for Early Detection of Hepatic Cancer. Cancer Lett., 1994, vol. 77, no. 2-3, pp. 95–101.
18. Sanoob M.U., Madhu A., Ajesh K., Varghese S.M. Artificial Neural Network for Diagnosis of Pancreatic Cancer. IJCI, 2016, vol. 5, no. 2, pp. 41–49.
19. Poloz T.L., Shkurupiy V.A., Poloz V.V., Demin A.V. Rezul’taty kolichestvennogo tsitologicheskogo analiza stroeniya follikulyarnykh opukholey shchitovidnoy zhelezy s pomoshch’yu komp’yuternykh i neyrosetevykh tekhnologiy [The Results of Quantitative Cytological Analysis of the Structure of Follicular Thyroid Tumors Using Computer and Neural Network Technologies]. Vestnik RAMN, 2006, no. 8, pp. 7–10.
20. Kirsanova A.V., Dmitriev G.A. Neyrosetevaya sistema diagnostiki vnutricherepnykh obrazovaniy [Neuronet Diagnostic System for Intracranial Formations]. Programmnye produkty i sistemy, 2009, no. 3, pp. 123–125.
21. Gantsev Sh.Kh., Zimichev A.A., Khrisanov N.N., Kliment’eva M.S. Primenenie neyronnoy seti v prognozirovanii raka mochevogo puzyrya [The Use of Neural Network to Predict Bladder Cancer]. Meditsinskiy vestnik Bashkortostana, 2010, no. 3, pp. 44–47.
22. Esin S.V., Osipov V.V., Pamurzin I.L., Poddubnaya N.N. Neyrosetevoy skrining v opredelenii grupp povyshennogo riska zabolevaniya rakom molochnoy zhelezy [Neural Network Screening in Identifying High-Risk Groups for Breast Cancer]. Al’manakh klinicheskoy meditsiny, 2007, no. 16, pp. 65–68.
23. Snow P.B., Smith D.S., Catalona W.J. Artificial Neural Networks in the Diagnosis and Prognosis of Prostate Cancer: A Pilot Study. J. Urol., 1994, vol. 152, no. 5, pp. 1923–1926.
24. Solovov V.A., Frolova I.G. Ispol’zovanie logisticheskikh regressiy i neyronnykh setey v vyyavlenii raka predstatel’noy zhelezy [The Use of Logistic Regressions and Neural Networks in Prostate Cancer Detection]. Sibirskiy onkologicheskiy zhurnal, 2006, no. 1, pp. 14–17.
25. Ahmed F.E. Artificial Neural Networks for Diagnosis and Survival Prediction in Colon Cancer. Mol. Cancer., 2005, vol. 4, no. 29.
26. Asada N., Doi K., MacMahon H., Montner S.M., Giger M.L., Abe C., Wu Y. Potential Usefulness of an Artificial Neural Network for Differential Diagnosis of Interstitial Lung Diseases: Pilot Study. Radiology, 1990, vol. 177, no. 3, pp. 857–860.
27. Abe H., Ashizawa K., Li F., Matsuyama N., Fukushima A., Shiraishi J., MacMahon H., Doi K. Artificial Neural Networks (ANNs) for Differential Diagnosis of Interstitial Lung Disease: Results of a Simulation Test with Actual Clinical Cases. Acad. Radiol., 2004, vol. 11, no. 1, pp. 29–37.
28. Patil S., Henry J.W., Rubenfire M., Stein P.D. Neural Network in the Clinical Diagnosis of Acute Pulmonary Embolism. Chest, 1993, vol. 104, no. 6, pp. 1685–1689.
29. Eng J. Predicting the Presence of Acute Pulmonary Embolism: A Comparative Analysis of the Artificial Neural Network, Logistic Regression, and Threshold Models. AJR. Am. J. Roentgenol., 2002, vol. 179, no. 4, pp. 869–874.
30. Makarova L.S., Semeryakova E.G. Razrabotka reshayushchikh pravil dlya sistemy podderzhki prinyatiya resheniy differentsial’noy diagnostiki bronkhial’noy astmy [Development of Decision Rules for a Decision Support System for Differential Diagnosis of Bronchial Asthma]. Vestnik nauki Sibiri, 2012, no. 3, pp. 162–167.
31. Alekseeva O.V., Rossiev D.A., Il’enkova N.A. Primenenie iskusstvennykh neyronnykh setey v differentsial’noy diagnostike retsidiviruyushchego bronkhita u detey [The Use of Artificial Neural Networks for Differential Diagnosis of Recurrent Bronchitis in Children]. Sibirskoe meditsinskoe obozrenie, 2010, no. 6, pp. 75–79.
32. Alekseeva O.V., Il’enkova N.A., Rossiev D.A., Solov’eva N.A. Optimizatsiya differentsial’noy diagnostiki retsidiviruyushchey bronkholegochnoy patologii u detey [Optimization of Differential Diagnosis of Recurrent Bronchitis in Children]. Sibirskiy meditsinskiy zhurnal, 2013, no. 2, pp. 37–41.
33. Maclin P.S., Dempsey J. Using an Artificial Neural Network to Diagnose Hepatic Masses. J. Med. Syst., 1992, vol. 16, no. 5, pp. 215–225.
34. Kazmierczak S.C., Catrou P.G., Van Lente F. Diagnostic Accuracy of Pancreatic Enzymes Evaluated by Use of Multivariate Data Analysis. Clin. Chem., 1993, vol. 39, no. 9, pp. 1960–1965.
35. Mironov P.I., Lutfarakhmanov I.I., Ishmukhametov I.Kh., Timerbulatov V.M. Iskusstvennye neyronnye seti v prognozirovanii razvitiya sepsisa u bol’nykh tyazhelym ostrym pankreatitom [Predictive Value of Artificial Neural Networks for Sepsis in Severe Acute Pancreatitis Patients]. Annaly khirurgicheskoy gepatologii, 2008, vol. 13, no. 2, pp. 85–89.
36. Afonin P.N., Afonin D.N., Doru-Tovt V.P. Primenenie iskusstvennykh neyronnykh setey dlya prognozirovaniya narusheniy zhiznedeyatel’nosti bol’nykh gematogennym osteomielitom pozvonochnika [The Use of Artificial Neural Networks to Predict Impairments in Patients with Hematogenous Osteomyelitis of the Spine]. Vestnik novykh meditsinskikh tekhnologiy, 2007, vol. 14, no. 3, pp. 42–44.
37. Efimov A.A., Zhurova O.V., Korovin E.N., Rodionov O.V. Analiz i modelirovanie protsessa diagnostiki stadiy osteoporoza na osnove neyronnykh setey [Analysis and Modelling of the Process of Diagnosing the Stages of Osteoporosis Based on Neural Networks]. Vestnik Voronezhskogo gosudarstvennogo tekhnicheskogo universiteta, 2006, vol. 2, no. 12, pp. 13–16.
38. Mantzaris D., Vrizas M., Trougkakos S., Priska E., Vadikolias K. Artificial Neural Networks for Estimation of Dementias Types. Artif. Intell. Appl., 2014, vol. 1, no. 1, pp. 74–82.
39. Bertè F., Lamponi G., Calabrò R.S., Bramanti P. Elman Neural Network for the Early Identification of Cognitive Impairment in Alzheimer’s Disease. Funct. Neurol., 2014, vol. 29, no. 1, pp. 57–65.
40. Quintana M., Guàrdia J., Sánchez-Benavides G., Aguilar M., Molinuevo J.L., Robles A., Barquero M.S., Antúnez C., Martínez-Parra C., Frank-García A., Fernández M., Blesa R., Peña-Casanova J., Neuronorma Study Team. Using Artificial Neural Networks in Clinical Neuropsychology: High Performance in Mild Cognitive Impairment and Alzheimer’s Disease. J. Clin. Exp. Neuropsychol., 2012, vol. 34, no. 2, pp. 195–208.
41. Lins A.J.C.C., Muniz M.T.C., Garcia A.N.M., Gomes A.V., Cabral R.M., Bastos-Filho C.J.A. Using Artificial Neural Networks to Select the Parameters for the Prognostic of Mild Cognitive Impairment and Dementia in Elderly Individuals. Comput. Methods Programs Biomed., 2017, vol. 152, pp. 93–104.
42. Reznichenko N.S. Neyrosetevoy podkhod pri reshenii mediko-biologicheskikh problem [Neural Network Approach to the Solution of Biomedical Problems]. Vestnik KGPU im. V.P. Astaf’eva, 2013, no. 4, pp. 279–283. Available at: http://cyberleninka.ru/article/n/neyrosetevoy-podhod-pri-reshenii-mediko-biologicheskih-problem (accessed 22 November 2017).
43. Reznichenko N.S., Shilov S.N. Ispol’zovanie neyrosetevoy sistemy dlya diagnostiki sindroma defitsita vnimaniya s giperaktivnost’yu [The Use of Neural Network System for Diagnosing Attention Deficit Hyperactivity Disorder]. Vestnik Severnogo (Arkticheskogo) federal’nogo universiteta. Ser.: Mediko-biologicheskie nauki, 2014, no. 1, pp. 48–54.
44. Berebin M.A., Pashkov S.V. Opyt primeneniya iskusstvennykh neyronnykh setey dlya tseley differentsial’noy diagnostiki i prognoza narusheniy psikhicheskoy adaptatsii [Experience of Using Artificial Neural Networks for Differential Diagnosis and Prediction of Mental Maladaptation]. Vestnik YuUrGU. Ser.: Komp’yuternye tekhnologii, upravlenie, radioelektronika, iss. 4, 2006, no. 14, pp. 41–45.
45. Slavutskaya E.V., Slavutskiy L.A. Ispol’zovanie iskusstvennykh neyronnykh setey dlya analiza gendernykh razlichiy mladshikh podrostkov [Using Artificial Neural Networks for Analysis of Gender Differences in Younger Teenagers]. Psikhologicheskie issledovaniya, 2012, vol. 5, no. 23, p. 4. Available at: http://psystudy.ru.0421200116/0028 (accessed 11 November 2017).