Two-component organizational model for clinical and radiological screening for pulmonary tuberculosis in a sparsely populated territory of the Sakha Republic (Yakutia)

Background. The challenges of organizing tuberculosis detection in sparsely populated areas are primarily associated with poor transportation access and a shortage of medical personnel. Under these conditions, the implementation of modern information technologies in clinical and radiological screening for the disease becomes highly relevant.

Aim. To optimize methods for the detection and diagnosis of pulmonary tuberculosis using information technologies in the sparsely populated territory of the Republic of Sakha (Yakutia).

Methods. A pilot study was conducted in seven medical organizations of the Republic of Sakha (Yakutia) to test a two-component organizational model for clinical and radiological tuberculosis screening utilizing information technologies: a central medical image archive and telemedicine for remote diagnosis, as well as artificial intelligence for double reading of fluorograms. Effectiveness was assessed by monthly monitoring of population coverage with fluorographic examinations, measuring the time spent on double reading of fluorograms, and assessing the time to tuberculosis diagnosis.

Results. The pilot implementation of the two-component organizational model for clinical and radiological tuberculosis screening, employing information technologies and artificial intelligence in medical organizations, led to increased fluorographic examination coverage of the general population and individuals at risk for tuberculosis. This implementation also reduced the time required for double reading of fluorograms and shortened tuberculosis diagnostic timelines, both in the general medical network and at the specialized tuberculosis service level. Considering the specific characteristics of tuberculosis detection organization across different socio-territorial zones of the Far North, a model for clinical and radiological screening of pulmonary tuberculosis was developed. This model comprises two organizational variants tailored for use in the Arctic and industrial zones. The model consists of three stages (radiological, clinical, and specialized) implemented at the level of the central district hospital departments.

Conclusion. The proposed model for tuberculosis screening using information technologies is recommended for implementation in sparsely populated districts of the Far North.

1. Borodulina EA. Issues of tuberculosis detection in general medical practice. Doctor. 2023; 34(2): 5–10. (In Russ). doi: 10.29296/25877305-2023-02-01

2. Guseynalieva VN. Improved detection of tuberculosis in primary health care and its impact on the incidence. Tuberculosis and Lung Diseases. 2020; 98(10): 41–46. (In Russ.). doi: 10.21292/2075-1230-2020-98-10-41-46

3. Sterlikov SА, Gаlkin VB, Mаliev BM, Shirokovа АА, Khorotetto VA, Mаyzhegishevа АS. Impact of active case finding on treatment outcomes in adult pulmonary tuberculosis patients. Tuberculosis and Lung Diseases. 2021; 99(7): 33–40. (In Russ.). doi. 10.21292/2075-1230-2021-99-7-33-40

4. Burtseva TE, Sleptsova SS, Gogolev NM, Afanaseva LN, Borisova EA, Korosteleva AV, et al. Features of medical care and medical-demographic indicators in the Arctic regions of the Republic of Sakha (Yakutia). Yakut Medical Journal. 2021; (1): 73-77. (In Russ.). doi: 10.25789/YMJ.2021.73.20

5. Kalashnikov KN, Artamonov IV. Health care in rural areas: spatial and temporal aspects of accessibility. Problems of Territory’s Development. 2020; 2(106): 120–132. (In Russ.). DOI: 10.15838/ptd.2020.2.106.9

6. Stupac VS, Manoshkina EM, Deev IA, Kobyakova OS, Bantyeva MN, Sokolovskaya TA. Climatogeographic background for organizing medical care for the Far North Russian Federation population. Russian Journal of Preventive Medicine. 2023; 26(12): 109–115. (In Russ.). doi: 10.17116/profmed202326121109

7. Tsybikova EB, Zubova NA. Approaches to organization of respiratory tuberculosis detection when its prevalence is decreasing. Tuberculosis and Lung Diseases. 2019; 97(9): 33–39. (In Russ.). doi: 10.21292/2075-1230-2019-97-9-33-39

8. Korovka VG, Galkin VB, Panidi EA, et al. Potential of geoinformation technologies to improve the monitoring of socially significant infections outbreaks. Russian Journal of Preventive Medicine. 2021; 24(10): 713. (In Russ.). doi: 10.17116/profmed2021241017

9. Morozov SP, Kokina DYu, Pavlov NA, Kirpichev YuS, et al. Clinical aspects of using artificial intelligence for the interpretation of chest X-rays. Tuberculosis and Lung Diseases. 2021; 99(4): 58–64. (In Russ.). doi: 10.21292/2075-1230-2021-99-4-58-64

10. Arzamasov K, Vasilev Y, Vladzymyrskyy A, Omelyanskaya O, Shulkin I, Kozikhina D, et al. An international noninferiority study for the benchmarking of AI for routine radiology cases: chest x-ray, fluorography and mammography. Healthcare. 2023; 11(12): 1684. doi: 10.3390/healthcare11121684

11. Seah JCY, Tang CHM, Buchlak QD, Holt XG, Wardman JB, Aimoldin A, et al. Effect of a comprehensive deep-learning model on the accuracy of chest x-ray interpretation by radiologists: a retrospective, multireader multicase study. Lancet Digit Health. 2021; 3(8): 496-506. doi: 10.1016/S2589-7500(21)00106-0

12. Tyrylgin MA. Health protection problems in the population of the Extreme North. Novosibirsk: Nauka Publ.; 2008. (In Russ.).

13. On the approval of the list of constituent entities of the Russian Federation and certain regions of the Russian Federation belonging to territories with low or high population density. Order of the Government of the Russian Federation dated 25.05.2004 No. 707R (as amended by orders of the Government of the Russian Federation dated 08.09.2004 No. 1165-r, dated 04.11.2004 No. 1397-r). (In Russ.). URL: https://normativ.kontur.ru/document?moduleId=1&documentId=67386

14. Pchelintsev Ya, Khvostikov A, Buchatskaia O, Nikiforova N, Shepeleva L, Prokopev E, et al. Robustness analysis of chest x-ray computer tuberculosis diagnosis. Computational Mathematics and Modeling. 2023; 33(4): 472-486. doi: 10.1007/s10598-023-09587-0