DIAGNOSIS AND PREDICTION OF CHOLECYSTITIS DEVELOPMENT ON THE BASIS OF NEURAL NETWORK ANALYSIS OF RISK FACTORS

Purpose. To develop an artificial neural network for diagnosing and predicting the development of cholecystitis based on an analysis of data on risk factors, and to explore the possibilities of its application in real clinical practice.

Materials and methods. The collection of materials was held in at the hospitals of the city of Kursk and included a survey of 488 patients with hepatopancreatoduodenal diseases. 203 patients were suffering from cholecystitis, in 285 patients the diagnosis of cholecystitis was excluded. Analysis of risk factors’ data (such as sex, age, bad habits, profession, family relationships, etc.) was carried out using an internally developed artificial neural network (multilayer perceptron with hyperbolic tangent as the activation function). The computer program “System of Intellectual Analysis and Diagnosis of Diseases” was registered in accordance with established procedure (Certificate No. 2017613090).

Results. The use of neural network analysis of data on risk factors in comparison with the processing of information that forms a clinical picture allows the diagnosis of a potential disease with cholecystitis before the onset of symptoms. The training of the artificial neural network with a quantitative output coding the age of probable hospitalization made it possible to generate an array of values, signifficantly (α ≤ 0.001) not differing from the empirical data. The difference between the mean calculated and mean empirical values was 0.45 for the training set and 1.75 for the clinical approbation group. The mean absolute error was within the range of 1.87–2.07 years.

Conclusion. 1. The proposed new approach to the diagnosis and prognosis of cholecystitis has demonstrated its effectiveness, which is confirmed in clinical approbation by the levels of sensitivity (94.44%, m = 2.26) and specificity (80.6%, m = 3.9).

2. The error in predicting the age of probable hospitalization of patients with cholecystitis did not exceed 2.29 and 2.38 years for p = 0.95 and p = 0.99, respectively.

1. Strasberg SM. Clinical practice. Acute calculous cholecystitis. N Engl J Med. 2008 Jun 26;358 (26):2804–11. DOI: 10.1056/NEJMcp0800929

2. Friedman LS. Liver, Biliary Tract, & Pancreas Disorders. In Papadakis MA, McPhee SJ, Rabow MW, editors. Current Medical Diagnosis & Treatment. McGraw-Hill, 2015.

3. Diseases and Conditions. Cholecystitis [Internet] Available at: http://www.mayoclinic.org/diseases-conditions/cholecystitis/basics/risk-factors/con-20034277 Accessed 2.06.2016

4. Svetyy LI, Lopukchova VA, Tarasenko IV, Klimkin AS. The use of health technology assessment in making effective management decisions. Health & Education Millemmium. 2013; 15 (1–4): 234–235. (In Russian).

5. Lopukhova VA, Tarasenko IV, Kaylanich GA, Kaylanich EA. The study of outpatient care quality in medical institutions of the Orel-city. Modern Problems of Science and Education. 2016; 5: 137. Available at: http://www.science-education.ru/ru/article/view?id=25383. Accesed 28.11.2016. (In Russian).

6. Simonyan RZ, Kailanich GA, Lopukhova VA, Tarasenko IV. The study of medical care quality in the health technology assessment. International Journal of Applied and Fundamental Research. 2016; 8–2: 185–187. (In Russian).

7. Dotdaeva AA, Khasanova ZB, Egorova LA, Shiganova GM, Sobenin IA, Postnov AYu, Boytsov SA. The association of genetic risk factors of atherosclerosis with traditional risk factors of atherosclerosis in patients with coronary heart disease living in highlands (at the example of Karachay-Cherkessia). The Journal of Atherosclerosis and Dyslipidemias (Ateroskleroz i Dislipidemii). 2015; 2 (19): 35–40. (In Russian).

8. Boytsov SA, Samorodskaya IV, Semenov VYu. The impact of economic crisises on population health. Profilakticheskaya meditsina (The Russian Journal of Preventive Medicine and Public Health). 2016; 19 (2): 4–10. DOI: 10.17116/profmed20161924–10 (In Russian).

9. Kaprin AD, Aleksandrova LM, Starinsky VV. Malignancy prophylaxis in the Russian Federation as part of global strategy for the prevention of noncommunicable diseases. Onkologiya. Zhurnal imeni P. A. Gerzena (P. A. Herzen Journal of Oncology). 2016; 5 (5): 42–50. DOI: 10.17116/onkolog20165542–50 (In Russian).

10. Zharikov O. G., Litvin A. A., Kovalev V. A. Ekspertnye sistemy v meditsine. Meditsinskie novosti. 2008;10:15–18. (In Russian).

11. Schepin VO, Rastorguyeva TI, Proklova TN. Towards prospective directions of healthcare development in the Russian Federation. Bjulleten’ Nacional’nogo nauchno-issledovatel’skogo instituta obshhestvennogo zdorov’ja imeni N. A. Semashko. 2012; 1: 147–152. (In Russian).

12. Skvortsova VI. Sem’ printsipov modernizatsii zdravookhraneniya. Voprosy ekonomiki i upravleniya dlya rukovoditelei zdravookhraneniya. 2010; 5: 7–14. (In Russian).

13. Greenes RA. Clinical decision support: the road ahead. Amsterdam; Boston: Elsevier; 2007.

14. Lazarenko VA, Antonov AE, Novomlinets UP. Visual environment for nonparametric correlation analysis of risk factors in patients with surgical diseases. Health & Education Millemmium. 2017; 19 (4): 34–37. (In Russian).

15. Lazarenko VA, Antonov AE, Prasolov AV, Churilin MI. The problem of regression analysis optimization in evaluation of risk factors influencing the development of surgical diseases of hepatopancreatoduodenal zone. Health & Education Millemmium. 2017; 19 (5): 24–27. (In Russian).

16. Lazarenko VA, Antonov AE. The role of social risk factors in peptic ulcer development in Kursk region. Man and his health. 2016; 2: 35–39. DOI: 10.21626/vestnik/2016–2/06 (In Russian).

17. Ruspatent. Registered on 10.03.2017. The certificate of state registration of computer programs № 2017613090. Lazarenko VA, Antonov AE. System of Intellectual Analysis and Diagnosis of Diseases.a