ORIGINAL RESEARCH

Ophthalmology

doi: 10.25005/2074-0581-2024-26-4-587-595
A NEW METHOD OF ASSESSING OCULAR INFLAMMATION IN THE ANTERIOR SEGMENT USING SOFTWARE

P.K. MIRAKHMEDOVA1, P.M. OSTANAEVA1, S.A. YULDASHEVA1, A.Z. DZHABAROV2

1LLC «Jarrohii chashm Nigoh», Dushanbe, Republic of Tajikistan
2Freelancer, Dushanbe, Republic of Tajikistan

Objective: To create a Telegram bot as a new tool for assessing anterior uveitis.

Methods: A total of 132 images, including radial and linear sections in the AC-OCT mode, were captured for a study using the SOCT Copernicus REVO 60 tomography device (Optopol Technology SA, Zawiercie, Poland). The study involved eight patients with uveitis of varying degrees of inflammatory severity, classified according to the Standardization of Uveitis Nomenclature (SUN) criteria. These examinations were conducted at the Nigoh Eye Surgery Clinic in Dushanbe, Republic of Tajikistan, from March to May 2024. For the study, an independent observer selected 27 high-quality images with a resolution of 1566×956, which were saved in an identical format, with the same contrast and negligible variations in the level of brightness (from -10 to 4), on which inflammatory cells were distinguishable, he also counted the cells in the application. Twenty-seven results of cell counting by the standard method served as a control. The ROC curve was constructed as a statistical processing method; sensitivity, specificity, accuracy, completeness, and F1-measure were calculated. The images were subjected to an assessment of the activity of the inflammatory process in anterior uveitis in a specially developed Telegram bot to detect and count the number of inflammatory cells.

Results: The method correctly identified cases as negative or "healthy" in 96.5%. The positive predictive value (PPV), or precision, was 0.964. This means the method was correct among all the cases predicted as positive – i.e., "sick" – in 96.4% of cases. The recall was 0.926, i.e., of all true positives (TP), the method was correct in 92.6% of cases. The F1-score, the harmonic mean of precision and recall, was 0.945, indicating a good balance between these two parameters.

Conclusion: The Telegram bot provides an impressively accurate and intuitive platform for evaluating the activity of the inflammatory process in anterior uveitis. Designed as a complimentary tool, it aims to reach a wide range of medical professionals, allowing easy access without requiring specialized training, advanced medical skills, or complex equipment. Users only need a device compatible with Telegram and a reliable internet connection to get started. This straightforward approach enhances the tool's usability and transforms it into an essential resource for healthcare providers aspiring to improve their diagnostic capabilities.

Keywords: Specialized software, Telegram bot, uveitis, optical coherence tomography, inflammation in the anterior chamber.

Download file:


References
  1. Li Y, Lowder C, Zhang X, Huang D. Anterior chamber cell grading by optical coherence tomography. Invest Ophthalmol Vis Sci. 2013;54(1):258-65. https:// doi.org/10.1167/iovs.12-10477
  2. Jabs DA, Nussenblatt RB, Rosenbaum JT; Standardization of Uveitis Nomenclature (SUN) Working Group. Standardization of uveitis nomenclature for reporting clinical data. Results of the First International Workshop. Am J Ophthalmol. 2005;140(3):509-16. https://doi.org/10.1016/j.ajo.2005.03.057
  3. Sharma S, Lowder CY, Vasanji A, Baynes K, Kaiser PK, Srivastava SK. Automated analysis of anterior chamber inflammation by spectral-domain optical coherence tomography. Ophthalmology. 2015;122(7):1464-70. https://doi.org/10.1016/j. ophtha.2015.02.032
  4. Kesim C, Chehab Z, Hasanreisoglu M. Laser flare photometry in uveitis. Saudi Journal of Ophthalmology. 2022;36(4):337-43. https://doi.org/10.4103/sjopt. sjopt_119_22
  5. Kempen JH, Ganesh SK, Sangwan VS, Rathinam SR. Interobserver agreement in grading activity and site of inflammation in eyes of patients with uveitis. Am J Ophthalmol. 2008;146(6):813-8.e1. https://doi.org/10.1016/j.ajo.2008.06.004
  6. Maring M, Saraf SS, Blazes M, Sharma S, Srivastava S, Pepple KL, Lee CS. Grading anterior chamber inflammation with anterior segment optical coherence tomography: An overview. Ocul Immunol Inflamm. 2022;30(2):357-63. https:// doi.org/10.1080/09273948.2022.2028289
  7. Kang TS, Lee Y, Lee S, Kim K, Lee WS, Lee W, et al. Development of fully automated anterior chamber cell analysis based on image software. Sci Rep. 2021;11(1):10670. https://doi.org/10.1038/s41598-021-89794-0

Authors' information:


Mirakhmedova Parvina Kulievna,
Ophthalmologist, LLC «Jarrohii chashm Nigoh»
ORCID ID: 0009-0006-6430-9973
SPIN: 3535-4031
Author ID: 1240991
E-mail: mirakhmedova89@gmail.com

Ostanaeva Parvin Murtazoevna,
Candidate of Medical Sciences, Chief Physician, LLC «Jarrohii chashm Nigoh»
ORCID ID: 0009-0000-9482-6724
E-mail: Ostanaeva@yahoo.com

Yuldasheva Sayyora Abdinazarovna,
Ophthalmologist, LLC «Jarrohii chashm Nigoh»
ORCID ID: 0009-0006-7835-3617
E-mail: Yuldashevas@gmail.com

Dzhabarov Anvar Zakirovich,
Software Developer, Freelancer
E-mail: anvardzhabarov@gmail.com

Information about support in the form of grants, equipment, medications

The authors did not receive financial support from manufacturers of medicines and medical equipment

Conflicts of interest: No conflict

Address for correspondence:


Mirakhmedova Parvina Kulievna
Ophthalmologist, LLC «Jarrohii chashm Nigoh»

734024, Republic of Tajikistan, Dushanbe, Ayni Ave., 50/51A

Tel.: +992 (935) 721248

E-mail: mirakhmedova89@gmail.com


This work is licensed under a Creative Commons Attribution 4.0 International License.

Materials on the topic: