Random forest method for interpreting results obtained by bioluminescence analysis of saliva in personalized diagnostics

UDC: 
519.254:519.257
DOI: 
10.21668/health.risk/2025.2.14.eng
Authors: 

G.V. Zhukova1, P.А. Martyshuk1, Е.R. Afer1, А.N. Shuvaev1, N.А. Rozanova2, D.V. Sergeev2, V.А. Kratasyuk1,3

Organization: 

1Siberian Federal University, 79 Svobodnyi Av., Krasnoyarsk, 660041, Russian Federation
2Research Center for Neurology, 80 Volokolamskoe highway, Moscow, 125367, Russian Federation
3Institute of Biophysics, Siberian Department of the RAS, separate division of the Federal Research Center Krasnoyarsk Scientific Center of the Siberian Department of the Russian Academy of Sciences, 50 Akademgorodok, build. 50, Krasnoyarsk, 660036, Russian Federation

Abstract: 

Development of personalized medicine and biotechnologies is directly linked to obtaining relevant data, which largely depend on individual characteristics of examined patients. Permissible ranges of analyzed indicators that are commonly used in conventional medicine do not always describe a patient’s health adequately. It seems necessary to search for such data analysis techniques, which allow considering variable individual peculiarities of patients’ bodies and their lifestyles.

The aim of this study is to determine whether it is possible to use the Random Forest method for biomedical data analysis in order to achieve correct interpretation of results obtained by personalized diagnostic tests. Bioluminescent testing is used as an example since it estimates effects produced by various characteristics of examined patients and their living conditions. The method allows minimizing risks of incorrect diagnosis and adjusting monitoring schemes for specific patients.

This study relies on using the results obtained by diagnosing workloads of railway workers using the bioluminescence method. A patient’s health is assessed by examining effects produced by a patient’s saliva on intensity of the bi-enzyme system luminescence: NAD(P)H:FMN oxidoreductase + luciferase. This analysis is integral and responses to many factors, each of which can influence the analysis result. Effectiveness of various methods for data analysis is assessed on an example group made of traffic controllers employed by the Krasnoyarsk Branch of Russian Railways JSC. Both statistical methods and the Random Forest machine learning algorithm were used for data analysis.
As a result, our study has revealed that it is advisable to use the Random Forest method for assessing significance of some biochemical saliva indicators to predict health of railway workers. The method makes it possible to identify the most significant factors and create graphs to show partial influence exerted by various factors on the target variable. This study allows optimizing the system for health diagnostics using integral bioluminescence analysis. The Random Forest method can become a component of a personalized bioluminescent biosensor for assessing effects produced by stress and workloads on the body.

Keywords: 
personalized diagnostics, machine learning, data analysis, multifactorial analysis, saliva, bioluminescence, biosensor, signal systems
Zhukova G.V., Martyshuk P.А., Afer Е.R., Shuvaev А.N., Rozanova N.А., Sergeev D.V., Kratasyuk V.А. Random Forest method for interpreting results obtained by bioluminescence analysis of saliva in personalized diagnostics. Health Risk Analysis, 2025, no. 2, pp. 166–174. DOI: 10.21668/health.risk/2025.2.14.eng
References: 
  1. Tabak L.A. Point-of-care diagnostics enter the mouth. Ann. N Y Acad. Sci., 2007, vol. 1098, pp. 7–14. DOI: 10.1196/annals.1384.043
  2. Kubala E., Strzelecka P., Grzegocka M., Lietz-Kijak D., Gronwald H., Skomro P., Kijak E. A Review of Selected Studies That Determine the Physical and Chemical Properties of Saliva in the Field of Dental Treatment. BioMed Res. Int., 2018, vol. 2018, pp. 6572381. DOI: 10.1155/2018/657238
  3. Kaczor-Urbanowicz K.E., Carreras-Presas C.M., Aro K., Tu M., Garcia-Godoy F., Wong D.T. Saliva diagnostics – Cur-rent views and directions. Exp. Biol. Med. (Maywood), 2017, vol. 242, no. 5, pp. 459–472. DOI: 10.1177/1535370216681550
  4. Esimbekova E.N., Torgashina I.G., Kalyabina V.P., Kratasyuk V.A. Enzymatic Biotesting: Scientific Basis and Appli-cation. Contemp. Probl. Ecol., 2021, vol. 14, pp. 290–304. DOI: 10.1134/S1995425521030069
  5. Kratasyuk V.A., Stepanova L.V., Ranjan R., Sutormin O.S., Pande S., Zhukova G.V., Miller O.M., Maznyak N.V., Kolenchukova O.A. A noninvasive and qualitative bioluminescent assay for express diagnostics of athletes' responses to physical exertion. Luminescence, 2021, vol. 36, no. 2, pp. 384–390. DOI: 10.1002/bio.3954
  6. Jordan M.I., Mitchell T.M. Machine learning: Trends, perspectives, and prospects. Science, 2015, vol. 349, no. 6245, pp. 255–260. DOI: 10.1126/science.aaa8415
  7. Bel’skaya L., Sarf E. The use of Fourier transform IR spectroscopy of saliva for rapid assessment of the level of lipid peroxidation products. Biomedical Chemistry: Research and Methods, 2019, vol. 2, no. 2, pp. e00094. DOI: 10.18097/BMCRM00094 (in Russian).
  8. Bel’skaya L.V., Sarf E.A., Kosenok V.K. Correlation interrelations between the composition of saliva and blood plasmain norm. Klinicheskaya laboratornaya diagnostika, 2018, vol. 63, no. 8, pp. 477–482. DOI: 10.18821/0869-2084-2018-63-8-477-482 (in Russian).
  9. Nikonorova M.L. Building optimal models for analysis of biomedical data. Vestnik novykh meditsinskikh tekhnologii, 2021, vol. 28, no. 1, pp. 55–59. DOI: 10.24412/1609-2163-2021-1-55-59 (in Russian).
  10. Berestneva O.G., Osadchaya I.A., Nemerov E.V. Methods for studying the medical data structure. Vestnik nauki Sibiri, 2012, vol. 1, no. 2, pp. 333–338 (in Russian).
  11. Klimenko A.V., Slashchev I.S. Klasternyi analiz dannykh [Cluster data analysis]. Vestnik nauki, 2019, no. 1 (10), vol. 1, pp. 159–163 (in Russian).
  12. Braz D.C., Popolin Neto M., Shimizu F.M., Sá A.C., Lima R.S., Gobbi A.L., Melendez M.E., Arantes L.M.R.B. [et al.]. Using machine learning and an electronic tongue for discriminating saliva samples from oral cavity cancer patients and healthy individual. Talanta, 2022, vol. 243, pp. 123327. DOI: 10.1016/j.talanta.2022.123327
  13. Lee E., Park S., Um S., Kim S., Lee J., Jang J., Jeong H.-O., Shin J. [et al.]. Microbiome of Saliva and Plaque in Children According to Age and Dental Caries Experience. Diagnostics (Basel), 2021, vol. 11, no. 8, pp. 1324. DOI: 10.3390/diagnostics11081324
  14. Kouznetsova V.L., Li J., Romm E., Tsigelny I.F. Finding distinctions between oral cancer and periodontitis using saliva metabolites and machine learning. Oral Dis., 2021, vol. 27, no. 3, pp. 484–493. DOI: 10.1111/odi.13591
  15. Zarrin, P.S., Roeckendorf N., Wenger C. In-Vitro Classification of Saliva Samples of COPD Patients and Healthy Con-trols Using Machine Learning Tools. IEEE Access, 2020, vol. 8, pp. 168053–168060. DOI: 10.1109/ACCESS.2020.3023971
  16. Murata T., Yanagisawa T., Kurihara T., Kaneko M., Ota S., Enomoto A., Tomita M., Sugimoto M. [et al.]. Salivary metabolomics with alternative decision tree-based machine learning methods for breast cancer discrimination. Breast Cancer Res. Treat., 2019, vol. 177, no. 3, pp. 591–601. DOI: 10.1007/s10549-019-05330-9
  17. Rabbani N., Kim G.Y.E., Suarez C.J., Chen J.H. Applications of machine learning in routine laboratory medicine: Current state and future directions. Clin. Biochem., 2022, vol. 103, pp. 1–7. DOI: 10.1016/j.clinbiochem.2022.02.011
  18. Li X., Zheng J., Ma X., Zhang B., Zhang J., Wang W., Sun C., Wang Y. [et al.]. The oral microbiome of pregnant women facilitates gestational diabetes discrimination. J. Genet. Genomics, 2021, vol. 48, no. 1, pp. 32–39. DOI: 10.1016/j.jgg.2020.11.006
  19. Kuwabara H., Katsumata K., Iwabuchi A., Udo R., Tago T., Kasahara K., Mazaki J., Enomoto M. [et al.]. Salivary metabolomics with machine learning for colorectal cancer detection. Cancer Sci., 2022, vol. 113, no. 9, pp. 3234–3243. DOI: 10.1111/cas.15472
  20. Alam M.Z., Rahman M.S., Rahman M.S. A Random Forest based predictor for medical data classification using feature ranking. Informatics in Medicine Unlocked, 2019, vol. 15, pp. 100180. DOI: 10.1016/j.imu.2019.100180
  21. Stepanova L.V., Kolenchukova O.A., Zhukova G.V., Sutormin O.S., Kratasyuk V.A. The Use of the Bioluminescent Enzyme Bioassay for the Analysis of Saliva of Railway Transport Workers to Monitor the Functional State of the Body in the Conditions of Labor Activity. Biofizika, 2024, vol. 69, no. 3, pp. 674–683. DOI: 10.31857/S0006302924030224 (in Russian).
Received: 
22.12.2024
Approved: 
07.05.2025
Accepted for publication: 
14.06.2025

You are here

Home