DOI: https://doi.org/10.31071/kit2019.15.13

Inventory reference

ISSN 1812-7231 Klin.inform.telemed. Volume 14, Issue 15, 2019, Pages 141-147

Author(s)

N. V. Bondarev

Institution(s)

Karazin National University of Kharkiv Ministry of Education and Science of Ukraine

Article title

Exploration and neural network medical data analysis of patients consuming benzodiazepines

Abstract (resume)

Introduction. Mathematical models and computer technologies are becoming more and more widely used in the various fields of medicine and pharmaceutics, they are constantly being improved and demonstrate modern approaches to the interpretation of clinical research data.

Work goals. Creating grouping models for patients with mental disorders based on the methods of exploratory data analysis and neural network algorithms.

Objects and Methodology. The study used medical data from 57 patients (34 men, 23 women) who were treated with benzodiazepines for various mental disorders in 8 drug treatment centers in a Western European country during 1999–2017. Medical data analysis was conducted in the statistical software STATISTICA 12 and SPSS 23 for Windows.

Results. The next models for grouping patients with mental disorders taking benzodiazepines were created: factor model, cluster model, discriminant model, canonical model, classification tree and neural network models. Three groups of patients were identified: the first group with 8 patients, the second group with 20 patients and the third group with 29 patients. The efficiency of benzo diazepine therapy (stabilization, reduction, cessation of benzodiazepine consumption) is 87,7%. The main factor of effective therapy is the reduction of benzodiazepine consumption (57,9%). The level of predisposition of patients to dependence on benzodiazepines is 37,5% (3/8) in the first, 34,5% (10/29) in the third group, 25% (5/20) in the second group. The lowest efficacy of treating patients with benzodiazepine drugs 44,8% (comparison between the initial goal of treatment and the final result) was found in the third group of patients. Due to a longer course of treatment, patients of the first and second groups are more prone to benzodiazepine abuse. The proposed methodology for medical data analysis for patient grouping and the results obtained in this paper may be useful for psychiatrists and narcologists who are interested in optimizing modern therapeutic strategies for the treatment of mental disorders.

Keywords

Benzodiazepine therapy, Benzodiazepine addiction, Exploratory data analysis, Neural network classifiers, Patient grouping

References

1. Tsanas A., Little M. A., McSharry P. E. A methodology for the analysis of medical data. Handbook of Systems and Complexity in Health. New York, Springer, 2013. p. 113–125.
https://doi.org/10.1007/978-1-4614-4998-0_7

2. Kuznetsov V. A., Kutrunov V. N., Yaroslavskaya E. I., Dyachkov S. M. Statistical methods for analyzing medical data in clinical practice. Scientific Review, 2015. no. 22, p. 313–320. (In Russ.).

3. Yu C. H. Exploratory data analysis in the context of data mining and resampling. Inter. J. Psych. Res. (IJPR), 2010. vol. 3, no. 1, pp. 9–22.
https://doi.org/10.21500/20112084.819

4. Konopka B. M., Lwow F., Owczarz M., Łaczmański Ł. Exploratory data analysis of a clinical study group: Development of a procedure for exploring multidimensional data. PLOS ONE, 2018. vol. 13, no. 8.
https://doi.org/10.1371/journal.pone.0201950
PMid:30138442 PMCid:PMC6107146

5. Royston P., Altman D. G. External validation of a Cox prognostic model: principles and methods. BMC Medical Research Methodology, 2013. vol. 13, no. 1, 33 p.
https://doi.org/10.1186/1471-2288-13-33
PMid:23496923 PMCid:PMC3667097

6. Klempíř O., Shala L., Tesař J., Krupička R. Neuroeda — an interactive web tool for neuroinformatics data analysis and teaching biomedical statistics. Mefanet J., 2017. vol. 5, no. 2, pp. 62–68.

7. Gelman A. Exploratory Data Analysis for Complex Models. J. Comput. Graph. Stat., 2004. vol. 13, no. 4, pp. 755–779.
https://doi.org/10.1198/106186004X11435

8. Mayorov O. Yu. [Searching for methods for quantitative assessment of individual resistance to emotional stress in the norm and in pathology based on the analysis of heart rate variability. Factor model]. Zh. Klin. inform. i Telemed. [J. Klin. inform. telemed.], 2017. vol. 12, iss. 13, pp. 53–63. (In Russ.).
https://doi.org/10.31071/kit2017.13.07

9. Patel J. L., Goyal R. K. Applications of artificial neural networks in medical science. Curr. Clin. Pharmacol., 2007. vol. 2, no. 3, pp. 217–226.
https://doi.org/10.2174/157488407781668811
PMid:18690868

10. Grossi E., Mancini A., Buscema М. International experience on the use of artificial neural networks in gastroenterology. Dig. Liver Dis., 2007. vol. 39, no. 3, pp. 278–285.
https://doi.org/10.1016/j.dld.2006.10.003
PMid:17275425

11. Amato F., López A., Peñ,a-Méndez E. M., Vaňhara P., Hampl A., Havel J. Artificial neural networks in medical diagnosis. J. Appl. Biomed., 2013. vol. 11, no. 2, pp. 47–58.
https://doi.org/10.2478/v10136-012-0031-x

12. Filntisi A., Papangelopoulos N., Bencurova E., Kasampalidis I., Matsopoulos G., Vlachakis D., Kossida S. State-of-the-Art Neural Networks Applications in Biology. IJSBBT, 2013. vol. 2, no. 4, pp. 63–85.
https://doi.org/10.4018/ijsbbt.2013100105

13. Yang Z., Huang Y., Jiang Y., Sun Y., Zhang Y. J., Luo P. Clinical Assistant Diagnosis for Electronic Medical Record Based on Convolutional Neural Network. Sci. Rep. 2018. vol. 8, no. 1, pp. 6329.
https://doi.org/10.1038/s41598-018-24389-w
PMid:29679019 PMCid:PMC5910396

14. Siqueira-Batista R., Vitorino R. R., Gomes A. P., Oliveira A. P., Ferreira R. S., Esperidiгo Antonio V., Santana L. A., Cerqueira F. R. Artificial neural networks and medical education. Rev. Bras. Edu. Med., 2014. vol. 38, no. 4, pp. 548–556.
https://doi.org/10.1590/S0100-55022014000400017

15. Martov V. Yu., Okorokov A. N. Lekarstvennyye sredstva v praktike vracha [Medicines in the practice of a doctor]. 3rd ed., Revised. and add. M., Medical literature, 2016. 944 p.

16. Puustinen J., Lähteenmäki R., Nurminen J., Vahlberg T., Aarnio P., Partinen M., Räihä I., Neuvonen P. J., Kivelä S-L. Long-term persistence of withdrawal of temazepam, zopiclone, and zolpidem in older adults: a 3-year follow-up study. BMC Geriatr., 2018. vol. 18, no. 142.
https://doi.org/10.1186/s12877-018-0829-9
PMid:29907085 PMCid:PMC6003076

17. Rudolph U., Crestani F., Benke D., Brünig I., Benson J. A., Fritschy J. M., Martin J. R., Bluethmann H., Möhler H. Benzodiazepine actions mediated by specific gamma-aminobutyric acid (A) receptor subtypes. Nature, 1999. vol. 01б iss. 6755, pp. 796–800.
https://doi.org/10.1038/44579
PMid:10548105

18. Griffin C. E., Kaye A. M., Bueno F. R., Kaye A. D. Benzodiazepine pharmacology and central nervous system-mediated effects. Ochsner J., 2013. vol. 13, no. 22. pp. 214–223.

19. Ne meditsinskoye ispol'zovaniye benzodiazepinov: rastushchaya ugroza dlya zdorov'ya naseleniya? [Non-medical use of benzodiazepines: a growing threat to public health?]. Bulletin of the SMART Global Program. UNODC. Vena, Austria. 2017. iss. 18. (In Russ.).

20. Mezhdunarodnyy komitet po kontrolyu nad narkotikami (MKKN) [International Narcotics Control Board (INCB). Doklad za 2017 god. [Report for 2017]. E INCB 2017/1, UN, Vienna, Austria, 2018. (In Russ.).

21. Osadhiy Yu. Yu., Voblenko R. A., Archakov D. S., Tarakanova E. A. Mesto benzodiazepineov v sovremennoy terapii psikhicheskikh rasstroystv (obzor dokazatel'nykh issledovaniy) [The place of benzodiazepine sinmodern therapy of mental disorders (review of evidence-based research)]. Sovremennaya terapiya psikhicheskikh rasstroystv [Modern therapy of mental disorders]. 2016. vol. 1, pp. 2–10. (In Russ.).

22. OON. Lecheniye narkomanii i reabilitatsiya: prakticheskoye rukovodstvo poplanirovaniyu i osushchestvleniyu [UN. Drug treatment and rehabilitation: a practical guide to planning and implementation]. OON Upravleniye po narkotikam i prestupnosti. NY, UN Publ. 2003. 122 p. (In Russ.).

23. Rebrova O. Yu. Statisticheskiy analiz meditsinskikh dannykh. Primeneniye paketa prikladnykh programm STATISTICA [Statistical analysis of medical data. Application software package STATISTICA]. M., Media Sfera, 2002. 312 p. (In Russ.).

24. Bondarev N. V. [Classification and Prediction of Sodium and Potassium Coronates Stability in Aqueous-Organic Media by Exploratory Data Analysis Methods]. Russ. J. Gen. Chem., 2019. vol. 89, no. 2, pp. 281–291.
https://doi.org/10.1134/S1070363219020191

25. Bondarev N. V. [Artificial Neural Network and Multiple Linear Regression for Prediction and Classification of Sustainability of Sodium]. Russ. J. Gen. Chem., 2019. vol. 89, no. 7, pp. 1085–1095. (In Russ.).
https://doi.org/10.1134/S0044460X1907014X

26. Borovikov V. STATISTICA. Iskusstvo analiza dannykh na komp'yutere: Dlya professionalov [The art of analyzing data on a computer: For professionals]. SPb., Piter, 2003, 686 p. (In Russ.).

27. Nasledov A. IBM SPSS Statistics 20 i AMOS. Professional'nyy statisticheskiy analiz dannykh [IBM SPSS Statistics 20 and AMOS. Professional statistical data analysis]. SPb., Piter, 2013. 416 p. (In Russ.).

28. Khaikin S. Neyronnyye seti [Neural networks]. M., Williams, 2006. 1104 p. (In Russ.).

29. Kholin Yu. V., Pushkar'ova Ya. M., Panteleymonov A. V., Nekos A. N. Khemometrychni metody v rozv'yazanni zadachy akisnoho khimichnoho analizu ta klasyfikatsiyi fizyko-khimichnykh danykh [Chemometric methods in solving the problems of qualitative chemical analysis and classification of physical and chemical data]. V. N. Karazin KhNU, 2016. 184 p. (In Ukr.).

Full-text version http://kit-journal.com.ua/en/viewer_en.html?doc/2019_15/013.pdf