A.I. Burnasyan Scientific journal FMBC

Clinical Bulletin

ISSN 2782-6430 (print)

State Research Center −Burnasyan Federal Medical Biophysical
Center of Federal Medical Biological Agency

The journal is published in Russian.
Format – A4.
The periodicity of the journal is 4 times a year.

Issue №1 2024 год

more

A.I. Burnasyan  FMBC clinical bulletin. 2022 № 2

Practical Application of Machine Learning Methods on the Example of Determining
the Activity of the Tuberculosis Process in Persons with Minimal Tuberculosis Changes
Detected on Chest X-ray
T.E.Tulkova1, P.F.Chernavin2, N.P.Chernavin2, Yu.P.Chugaev3, I.A.Cherniaev3, V.N.Pankrashchenko4

1National Medical Research Center of Phthisiopulmonology and Infectious Diseases, Moscow, Russia
2Ural Federal University 19, Mira st., 620002, Yekaterinburg, Russian Federation
3Ural State Medical University, Yekaterinburg, Russian Federation
4State Academic University For The Humanities, Moscow, Russiа
Contact person: Pankrashchenko Victor Nicolaevich: vpankrashchenko@gaugn.ru

Abstract
Background: According to the World Health Organization (WHO), over 23% of the human population infected with tuberculosis bacilli – M.tuberculosis. For each infected person, the likelihood of a transition from a state of latent tuberculosis infection (LTBI) to active tuberculosis remains. WHO considers testing and treatment for LTBI in groups at high risk of reactivations as a necessary condition for tuberculosis elimination. Early detection of the transition of LTBI into active tuberculosis presents a certain difficulty due to the absence of clinically and radiographically distinguishable symptoms of the onset of the disease, therefore, immunodiagnostics, including the use of a skin test with a recombinant tuberculosis allergen, and methods of clinical laboratory diagnostics come to the aid of clinicians.

The objective of our study was to demonstrate the possibilities of using an artificial intelligence system to identify the level of activity of tuberculosis infection in children with the presence of small tuberculosis changes in the respiratory organs, detected by X-ray.

Material and methods The total number of patients registered in anti-tuberculosis institutions enrolled in the study was 489, including: the main group – a training sample consisting of patients with confirmed active tuberculosis (n1 = 369); the control group – a test sample of patients in whom the pathogen was in an inactive form (n2 = 120). As variables for calculations: anamnesis, laboratory parameters and X-ray data, were obtained by routine methods and used in accordance with current national standards of care and clinical guidelines, which did not require additional invasive interventions, equipment and material costs. The above survey results: age, gender, medical history, BCG vaccination, blood biochemical parameters in dynamics, X-ray signs, formalized according to the binary principle (presence / absence), were retrieved from patients files into the study database based on MS Excel spreadsheets for further processing.

At the initial stage, the Wolfram Mathematica software package was used for calculations; six classical machine learning (ML) methods were carried out: Logistic Regression, Naive Bayes, Nearest Neighbors, Neural Network and Random Forest.

Results: The results of the calculations based on combinations of categorical features did not suit us in terms of the quality of the forecast, and we proceeded to the search for a decision rule based on quantitative features. All spelled above methods predicted the presence of the disease significantly better than its absence. The Random Forest method showed the best results for both categorical and quantitative traits, however, interpretation of its results was not possible for clinical decision making. Convinced of the non-optimality of applying classical ML methods, it was decided to apply the author’s committee machine method with the possibility of minimal correction of conditions for significantly different cardinalities of the separable sets and subsequent geometric interpretation of the results. As a result of the application of the committee machine method, 7 most informative parameters were identified to create a decision rule that makes possible to distinguish patients with inactive pathogen and who do not require treatment in children with suspected tuberculosis.

Conclusion: the committee machine method in a geometric formulation lead to localize areas in the feature space that correspond to sick and healthy patients from the training sample. That areas were unambiguously described in the form of a system of inequalities and could be easily explained to clinicians and allow moving from a geometric interpretation to a meaningful description of cause-and-effect relationships between the laboratory parameters in a certain area and the patient’s condition.

Keywords: machine learning, latent tuberculosis infection, artificial intelligence, committee machine method

For citation: Tulkova TE, Chernavin PF, Chernavin NP, Chugaev YuP, Cherniaev IA, Pankrashchenko VN. Practical Application of Machine Learning Methods on the Example of Determining the Activity of the Tuberculosis Process in Persons with Minimal Tuberculosis Changes Detected on Chest X-ray Clinical Bulletin. 2022.2:64-73. (In Russian) DOI: 10.33266/2782-6430-2022-2-64-73

REFERENCES                

  1. Disease Prevention and Control. Programmatic management of latent tuberculosis infection in the European Union. Stockholm: ECDC; 2018. 59 P.
  2. Foxa G.J., Doblerab C.C., Maraisc B.J., Denholmde J.T. Preventive therapy for latent tuberculosis infection—the promise and the challenges/International Journal of Infectious Diseases Volume 56, March 2017, Pages 68-76
  3. Global tuberculosis report 2021. Geneva: World Health Organization; 2021. Licence: CC BY-NC-SA 3.0 IGO.
  4. Guidelines for the Treatment of Latent Tuberculosis Infection: Recommendations from the National Tuberculosis Controllers Association and CDC, 2020 MMWR Recomm Rep 2020; 69(No. RR-1): 1-11.
  5. Houben RM, Dodd PJ. The global burden of latent tuberculosis infection: a re-estimation using mathematical modelling. PLoS Med 2016;13:e1002152. https://doi.org/10.1371/journal.pmed.1002152)
  6. Kritski AL, Marques MJ, Rabahi MF, et al. Transmission of tuberculosis to close contacts of patients with multidrug-resistant tuberculosis. Am J Respir Crit Care Med 1996;153:331–5. https://doi.org/10.1164/ ajrccm.153.1.8542139
  7. Recommendations and Reports 2 MMWR / February 14, 2020 / Vol. 69 / No. 1 US Department of Health and Human Services/Centers for Disease Control and Prevention and classified as having latent tuberculosis infection (LTBI).
  8. Shea KM, Kammerer JS, Winston CA, Navin TR, Horsburgh CR Jr. Estimated rate of reactivation of latent tuberculosis infection in the United States, overall and by population subgroup. Am J Epidemiol 2014;179:216–25. https://doi.org/10.1093/aje/kwt246
  9. Sutherland I. Recent studies in the epidemiology of tuberculosis, based on the risk of being infected with tubercle bacilli. Adv Tuberc Res 1976;19:1–63.
  10. Sutherland I. The ten-year incidence of clinical TB following conversion in 2,550 individuals aged 14 to 19 years. Tuberculosis Surveillance Research Unit Progress Report. The Hague, the Netherlands: The Royal Netherlands Tuberculosis Foundation; 1968.
  11. World Health Organization. Guidelines for the programmatic management of drug-resistant tuberculosis – 2011 update. Geneva: WHO, 2011.
  12. Latent tuberculosis infection: updated and consolidated guidelines for programmatic management WHO, 2018, 84 p. ISBN 978-92-4-555023-5
  13. Lönnroth K , Castro K , Chakaya JM et al. . Tuberculosis control and elimination 2010–50: cure, care, and social development . Lancet 2010 ; 375 : 1814 – 29 .
  14. Lönnroth K , Jaramillo E , Williams BG et al. . Drivers of tuberculosis epidemics: The role of risk factors and social determinants . Soc Sci Med 2009 ; 68 : 2240 – 6 .
  15. Bhargava A, Pai M, Bhargava M, Marais BJ, Menzies D. Can social interventions prevent tuberculosis?: the Papworth experiment (1918-1943) revisited. Am J Respir Crit Care Med. 2012 Sep 1;186(5):442-9. doi: 10.1164/rccm.201201-0023OC. Epub 2012 Jul 5. PMID: 22773730.
  16. Lönnroth K, Castro KG, Chakaya JM, Chauhan LS, Floyd K, Glaziou P, Raviglione MC. Tuberculosis control and elimination 2010–50: cure, care, and social development. Lancet 2010;375:1814–1829.
  17. Lönnroth K, Jaramillo E, Williams BG, Dye C, Raviglione M. Drivers of tuberculosis epidemics: the role of risk factors and social determinants. Soc Sci Med 2009;68:2240–2246.
  18. Lienhardt C. From exposure to disease: the role of environmental factors in susceptibility to and development of tuberculosis. Epidemiol Rev 2001;23:288–301.
  19. Hargreaves JR, Boccia D, Evans CA, Adato M, Petticrew M, Porter JDH. The social determinants of tuberculosis: from evidence to action. Am J Public Health 2011;101:654–662.
  20. Rasanathan K, Sivasankara Kurup A, Jaramillo E, Lonnroth K. The social determinants of health: key to global tuberculosis control. Int J Tuberc Lung Dis 2011;15(Suppl 2):S30–S36
  21. Federal clinical guidelines for diagnostics and treatment of latent tuberculosis infection in children. Moscow. «Zdorovie Cheloveka», 2015. 36 p. (In Russ).
  22. Kagramanov AI. Skrytaya tuberkuleznaya infektsiya i ee znachenie v patogeneze i immunitete. [dissertation abstract] Moscow; 1952. 52 p. (In Russ).
  23. Tyulkova, Tatyana & Mezentseva, Alesya. (2017). Latent Tuberculosis Infection and Residual Post-Tuberculous Changes in Children. Current pediatrics. 16. 452-456. 10.15690/vsp.v16i6.1817. doi: 10.15690/vsp.v16i6.1817
  24. Dolgich T.I.  Problems of laboratory medicine and health care modernization [Journal Article]. [Problemny`e voprosy` laboratornoj mediciny` v usloviyax modernizacii zdravooxraneniya] Clinico – Laboratorny Consilium. 2012; 42(2):4-6. (In Russ).
  25. Ministry of Health of the Russian Federation Order No. 186 dated 24.04.2018 “On approval of the Concept of predictive, preventive and personalized medicine” (In Russ).
  26. Ministry of Health of the Russian Federation Order No. 951 dated 29.12.2014 “On approval of methodological recommendations for improvement …”, Order of the Ministry of Health of the Russian Federation No. 124n dated 21.03.2017 “On approval of the procedure and timing of preventive medical examinations …”[ Prikaz MZ RF №951 ot 29.12.2014 «Ob utverzhdenii metodicheskih rekomendacij po sovershenstvovaniyu…», Prikaz MZ RF №124n ot 21.03.2017 «Ob utverzhdenii poryadka i srokov provedeniya profilakticheskih medicinskih osmotrov…»] (In Russ).
  27. Perelman M.I. et al., Phthiziatria, Moscow: Medicina, 2004, 519 p., [Textbook]. p. 95 (In Russ).
  28. Aksenova V.A., Ovsyankina E.S., Aleksandrova T.M. Methods of `quality control of work` in mass tuberculin diagnostics [Journal Article]. [Metody` kontrolya kachestva raboty` pri massovoj tuberkulinodiagnostike]// Problemy` tuberkuleza. – 2002, №2. p.3-5, (In Russ).
  29. Borodulina E.A., Borodulin B.E. Differential diagnosis of post-vaccination infectious tuberculin allergy in children with atopic diseases [Journal Article]. [Differencial`naya diagnostika postvakcinal`noj i infekcionnoj tuberkulinovoj allergii u detej s atopicheskimi zabolevaniyami], Problemy` tuberkuleza i boleznej organov dy`haniya – 2006, №1. – p. 9-13; (In Russ).
  30. Poddubnaya L.V., Shilova E.P., Silajkina S.T. Tuberculosis screening in modern conditions [Journal Article]. [Skrining tuberkuleza v sovremenny`h usloviyah]. Tuberkulez i bolezni legkih. – №6. – 2013. – p. 071-072
  31. Aksenova V.A., Senchixin P.V. Methods of laboratory diagnostics of latent tuberculosis infection [Journal Article] [Metody` laboratornoj diagnostiki latentnoj tuberkuleznoj infekcii]. Klinicheskaya laboratornaya diagnostika. – №9. – 2013. – s. 53-54 (In Russ).
  32. Starshinova A.A., Pavlova M.V., Dovgalyuk I.F., Yakunova O.A. Diagnostic capabilities of modern immunological tests in determining the activity of tuberculosis infection in children [Journal Article] [Diagnosticheskie vozmozhnosti sovremenny`h immunologicheskix testov pri opredelenii aktivnosti tuberkuleznoj infekcii u detej]. Tuberkulez i bolezni legkih. – №8. – 2012. – p. 040-043 (In Russ).
  33. Tarabaeva A.S., Abil`baeva A.A., Rakisheva A.S., Kurmashev R.Zh., Sarniyazova K.S., Abubakirov A.Ya.. Prognostic immunological biomarkers of diagnosis and progression of latent tuberculosis no go (mini-review) [Journal Article] [Prognosticheskie immunologicheskie biomarkery diagnostiki i progressirovaniya latentnogo tuberkuleza (mini-obzor)]/ Vestnik KazNMU. – №4. – 2017. – p. 471-474
  34. Belyan Zh.E., BujnevichI.V., Goponyako S.V. . Methods ofdiagnosis of latent tuberculosis infection [Journal Article] [ Metody diagnostiki latentnoj tuberkuleznoj infekcii]. Problemy zdorovya i ekologii. – №3 (53). – 2017. – p. 9-14 (In Russ).
  35. Doroshenkova A.E., Staviczkaya N.V., Anorina E.E. Immunogenetic activity of latent tuberculosis infection in children [Journal Article] [Immunogeneticheskie pokazateli aktivnosti latentnoj tuberkuleznoj infekcii u detej]. International journal on immunorehabilitation. – №1. 2009. p. 124 (In Russ).
  36. Patent RU 2586279,2016. 06.10. Method of evaluation of activity of tuberculosis infection in children and undergrowth [Sposob ocenki aktivnosti tuberkuleznoj infekcii u detej i podrostkov] (In Russ).
  37. Vladimirskij M.A., Mordovskaya L.I., Shipina L.K., Sazykin A.Yu., Nedospasov S.A. Antigen-specific induction of tumor necrosis factor in assessing tuberculosis infection activity [Journal article] [Antigen-specificheskaya indukciya faktora nekroza opuholi v ocenke aktivnosti tuberkuleznoj infekcii] / Tuberkulez i bolezni legkih. – №11. – 2011. – p. 045-049(In Russ).
  38. Zemskova Z.S, Dorozhkova I.R. Latent tuberculosis infection [Textbook] [Skryto protekayushhaya tuberkuleznaya infekciya]. M.: Medicina. 1984: 11 (In Russ).
  39. Ministry of Heath of Russian Federation Order #127n dated 13.03.2013 On Approval of the Procedure for Providing Medical Care to Tuberculosis Patients to Persons in Contact with Tuberculosis Patients or in Contact with Tuberculosis Patients, as Well as to Persons in Contact with Tuberculosis Patients and in Contact with Tuberculosis Patients, approved by Order of the Ministry of Health of the Russian Federation dated November 15, 2012. [Prikaz Ministerstva zdravoohraneniya Rossijskoj Federacii ot 13.03.2019 № 127n «Ob utverzhdenii poryadka dispansernogo nablyudeniya za bol`ny`mi tuberkulezom, liczami, naxodyashhimisya ili naxodivshimisya v kontakte s istochnikom tuberkuleza, a takzhe liczami s podozreniem na tuberkulez i izlechenny`mi ot tuberkuleza i priznanii utrativshimi silu punktov 16-17 Poryadka okazaniya medicinskoj pomoshhi bol`ny`m tuberkulezom, utverzhdennogo prikazom Ministerstva zdravooxraneniya Rossijskoj Federacii ot 15 noyabrya 2012 g. № 932n»]. p. 16-17 (In Russ).
  40. Kamensky S. Artifificial Intelligence and Technology in Health Care : Overview and Possible Legal Implications // DePaul journal of health care law. – Chicago, 2020. – Vol. 21, N 3. – P. 1–18. (In Russ).
  41. Tschider C.A. The healthcare privacy-artificial intelligence impasse // Santa Clara high technology law journal. – Santa Clara, 2020. – Vol. 36, N 4. – P. 439–443.
  42. Hasanov A. G., Shajbakov D. G., Zhernakov S. V., Menshikov A. M., Badretdinova F. F., Sufiyarov I. F., Sagadatova Yu. R.. Neural networks for predicting the dynamics of disease development [Journal Article] [Nejronny`e seti dlya prognozirovaniya dinamiki razvitiya zabolevanij] Kreativnaya hirurgiya i onkologiya, № 3, 2020, p. 198-204. (In Russ).
  43. zdrav.expert [Internet]. Zdrav-Expert [cited 2021 Dec 25].: Laboratory Diagnostics: Market in Russia [Laboratornaya_diagnostika_(rynok_Rossii)] Available from: https://zdrav.expert/a/541553 (In Russ).
  44. Samorodskaya I.V., Perxov V.I., Tretyakov A.A. Modern problems of individual and public health assessment [Sovremennye problemy ocenki individualnogo i obshhestvennogo zdorovya] [Journal Article]// «Sovremenny`e problemy zdravoohraneniya i medicinskoj statistiki» 2021 ., № 3 (In Russ).
  45. Borodulina E. A. Artificial intelligence in the detection of tuberculosis [Journal Article] [Iskusstvennyj intellekt v vyyavlenii tuberkuleza] /Vrach №5, 2020, https://doi.org/10.29296/25877305-2020-05-06 (In Russ).
  46. Morozov S. P., Vladzimirskij A. V. Ledihova N.V. Ocenka diagnosticheskoj tochnosti sistemy skrininga Tuberkuleza legkih na osnove iskusstvennogo intellekta Tuberkulez i bolezni legkih T 96, №8, 2018 https://doi.org/10.21292/2075-1230-2018-96-8-42-49 (In Russ).
  47. Patent RU 2 728 943 C1, 2020.08.03 Tyulkova T.E., Vladimirskij M.A., Habibullina N.F., Chernavin P.F., Chernavin N.P. Method for determining the activity of specific inflammation in the presence of minimal tuberculosis changes in children and adolescents [Sposob opredeleniya aktivnosti specificheskogo vospaleniya pri nalichii minimalnyh tuberkuleznyh izmenenij u detej i podrostkov] (In Russ).
  48. Mazurov V. D. The method of committees in classification and optimization problems [Textbook][Metod komitetov v zadachah klassifikacii i optimizacii]. M., Fizmatlit, 1990, 248p. (In Russ).
  49. Mazurov V. D. Mathematical methods of pattern recognition: a textbook [Matematicheskie metody raspoznavaniya obrazov: uchebnoe posobie / Ural. gos. un-t im. A. M. Gorkogo. 2-e izd., dop. i pererab. — Yekaterinburg: Izdatel`stvo Ural`skogo universiteta, 2010. 101 p. (In Russ).
  50. Mazurov V.D., Polyakova E.Yu. Existential issues of committee constructions. Part II [Textbook] [Ekzistencialnye voprosy` komitetnyh konstrukcij. Chast II]. Vestnik Yuzhno-Uralskogo gosudarstvennogo universiteta, 2019, t.19 №1, p.114-120 (In Russ).
  51. Chernavin N.P. Forecasting the volatility of the exchange rate by the committee method [Journal Article] [Prognozirovanie volatilnosti kursa valyut metodom komitetov] / Vestnik Chelyabinskogo gosudarstvennogo universiteta. – №109. – 2019. № 11(433). S. 82-94. (In Russ).
  52. Chernavin P.F, Gajnanov D.N., Pankrashhenko V.N, Chernavin N. P, Chernavin F. P. Machine learning based on mathematical programming problems [Textbook][Mashinnoe obuchenie na osnove zadach matematicheskogo programmirovaniya]. M., Nauka, 2021, 128 p. (In Russ).
  53. Donald PR. Antituberculosis drug-induced hepatotoxicity in children. Pediatric reports 2011;3:E16]

Conflict of interest. The authors declare no conflict of interest. 
Financing. The study had no sponsorship. Участие авторов.
Contribution. Article was prepared with equal participation of the authors. 
Article received: 21.05.2022. Accepted for publication: 09.06.2022

© 2024 Scientific journal - "Clinical Bulletin of the FMBС im. A.I. Burnasyan"
Scroll to Top