Ocular Surface Diseases and Artificial Intelligence
Özet
This chapter discusses how artificial intelligence is increasingly being used to support the diagnosis and follow-up of ocular surface diseases such as dry eye, meibomian gland dysfunction, infectious keratitis, and conjunctival lesions. Since traditional evaluation methods often depend on clinician experience and may produce subjective results, AI offers a more objective and standardized way to analyze slit-lamp photographs, meibography, and other clinical data. The chapter emphasizes that AI should assist, not replace, the physician. It can improve early diagnosis, disease classification, treatment monitoring, and long-term follow-up, especially in complex or uncertain cases. At the same time, the text highlights important limitations, including data quality, lack of generalizability, and the risk of algorithmic bias. Ethical concerns such as patient privacy and informed use are also underlined. Overall, the chapter presents AI as a promising clinical support tool that may make ocular surface disease management more accurate, efficient, and personalized in the future.
Bu bölüm, yapay zekânın kuru göz, meibomian bez disfonksiyonu, enfeksiyöz keratit ve konjonktival lezyonlar gibi oküler yüzey hastalıklarının tanı ve takibinde nasıl destekleyici bir rol üstlendiğini ele alıyor. Geleneksel değerlendirme yöntemleri çoğu zaman hekimin deneyimine bağlı ve kısmen öznel olduğu için, yapay zekâ slit-lamp görüntüleri, meibografi ve benzeri verileri daha standart ve objektif biçimde analiz etme imkânı sunuyor. Bölümde özellikle yapay zekânın hekimi yerine geçmediği, yalnızca klinik karar sürecini güçlendiren bir araç olduğu vurgulanıyor. Erken tanı, hastalık sınıflandırması, tedaviye yanıtın izlenmesi ve kronik olguların uzun dönem takibinde önemli katkılar sağlayabileceği belirtiliyor. Bununla birlikte veri kalitesi, farklı hasta gruplarında değişen performans ve algoritmik yanlılık gibi sınırlılıklar da açıkça tartışılıyor. Hasta mahremiyeti ve etik sorumluluk da önemli başlıklar arasında yer alıyor. Genel olarak bölüm, yapay zekânın gelecekte daha kişiselleştirilmiş ve etkili bir oküler yüzey hastalığı yönetimi sağlayabileceğini savunuyor.
Referanslar
Stapleton, F., Alves, M., Bunya, V. Y., et al. (2017). TFOS DEWS II epidemiology report. The Ocular Surface, 15(3), 334–365. https://doi.org/10.1016/j.jtos.2017.05.003
Craig, J. P., Nichols, K. K., Akpek, E. K., et al. (2017). TFOS DEWS II definition and classification report. The Ocular Surface, 15(3), 276–283. https://doi.org/10.1016/j.jtos.2017.05.008
Bron, A. J., de Paiva, C. S., Chauhan, S. K., et al. (2017). TFOS DEWS II pathophysiology report. The Ocular Surface, 15(3), 438–510. https://doi.org/10.1016/j.jtos.2017.05.011
Gulshan, V., Peng, L., Coram, M., et al. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy. JAMA, 316(22), 2402–2410. https://doi.org/10.1001/jama.2016.17216
Ting, D. S. W., Pasquale, L. R., Peng, L., et al. (2019). Artificial intelligence and deep learning in ophthalmology. British Journal of Ophthalmology, 103(2), 167–175. https://doi.org/10.1136/bjophthalmol-2018-313173
Setu MAK, Horstmann J, Schmidt S, Stern ME, Steven P. Deep learning-based automatic meibomian gland segmentation and morphology assessment in infrared meibography. Sci Rep. 2021 Apr 7;11(1):7649. doi: 10.1038/s41598-021-87314-8.
PMID: 33828177; PMCID: PMC8027879.
Shields, C. L., Alset, A. E., Boal, N. S., et al. (2017). Conjunctival tumors in 5002 cases. Ophthalmology, 124(2), 163–171. https://doi.org/10.1016/j.ophtha.2016.10.020
Ting DSW, Pasquale LR, Peng L, Campbell JP, Lee AY, Raman R, Tan GSW, Schmetterer L, Keane PA, Wong TY. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol. 2019 Feb;103(2):167-175. doi: 10.1136/bjophthalmol-2018-313173. Epub 2018 Oct 25. PMID: 30361278; PMCID: PMC6362807.
Li, J., Shen, Y., Sun, Y., et al. (2022). Deep learning-based diagnosis of dry eye disease using ocular surface images. Translational Vision Science & Technology, 11(3), 12. https://doi.org/10.1167/tvst.11.3.12
Nagendran M, Chen Y, Lovejoy CA, Gordon AC, Komorowski M, Harvey H, Topol EJ, Ioannidis JPA, Collins GS, Maruthappu M. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ. 2020 Mar 25;368:m689. doi: 10.1136/bmj.m689. PMID: 32213531; PMCID: PMC7190037.
Nichols, K. K., Foulks, G. N., Bron, A. J., et al. (2011).The international workshop on meibomian gland dysfunction: Executive summary. Investigative Ophthalmology & Visual Science, 52(4), 1922–1929. https://doi.org/10.1167/iovs.10-6997a
Ung, L., Bispo, P. J. M., Shanbhag, S. S., Gilmore, M. S., & Chodosh, J. (2019).The persistent dilemma of microbial keratitis: Global burden, diagnosis, and antimicrobial resistance. Survey of Ophthalmology,64(3),255-271. https://doi.org/10.1016/j.survophthal.2018.12.003
Austin, A., Lietman, T., & Rose-Nussbaumer, J. (2017).Update on the management of infectious keratitis.Ophthalmology, 124(11), 1678–1689.https://doi.org/10.1016/j.ophtha.2017.05.012
Referanslar
Stapleton, F., Alves, M., Bunya, V. Y., et al. (2017). TFOS DEWS II epidemiology report. The Ocular Surface, 15(3), 334–365. https://doi.org/10.1016/j.jtos.2017.05.003
Craig, J. P., Nichols, K. K., Akpek, E. K., et al. (2017). TFOS DEWS II definition and classification report. The Ocular Surface, 15(3), 276–283. https://doi.org/10.1016/j.jtos.2017.05.008
Bron, A. J., de Paiva, C. S., Chauhan, S. K., et al. (2017). TFOS DEWS II pathophysiology report. The Ocular Surface, 15(3), 438–510. https://doi.org/10.1016/j.jtos.2017.05.011
Gulshan, V., Peng, L., Coram, M., et al. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy. JAMA, 316(22), 2402–2410. https://doi.org/10.1001/jama.2016.17216
Ting, D. S. W., Pasquale, L. R., Peng, L., et al. (2019). Artificial intelligence and deep learning in ophthalmology. British Journal of Ophthalmology, 103(2), 167–175. https://doi.org/10.1136/bjophthalmol-2018-313173
Setu MAK, Horstmann J, Schmidt S, Stern ME, Steven P. Deep learning-based automatic meibomian gland segmentation and morphology assessment in infrared meibography. Sci Rep. 2021 Apr 7;11(1):7649. doi: 10.1038/s41598-021-87314-8.
PMID: 33828177; PMCID: PMC8027879.
Shields, C. L., Alset, A. E., Boal, N. S., et al. (2017). Conjunctival tumors in 5002 cases. Ophthalmology, 124(2), 163–171. https://doi.org/10.1016/j.ophtha.2016.10.020
Ting DSW, Pasquale LR, Peng L, Campbell JP, Lee AY, Raman R, Tan GSW, Schmetterer L, Keane PA, Wong TY. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol. 2019 Feb;103(2):167-175. doi: 10.1136/bjophthalmol-2018-313173. Epub 2018 Oct 25. PMID: 30361278; PMCID: PMC6362807.
Li, J., Shen, Y., Sun, Y., et al. (2022). Deep learning-based diagnosis of dry eye disease using ocular surface images. Translational Vision Science & Technology, 11(3), 12. https://doi.org/10.1167/tvst.11.3.12
Nagendran M, Chen Y, Lovejoy CA, Gordon AC, Komorowski M, Harvey H, Topol EJ, Ioannidis JPA, Collins GS, Maruthappu M. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ. 2020 Mar 25;368:m689. doi: 10.1136/bmj.m689. PMID: 32213531; PMCID: PMC7190037.
Nichols, K. K., Foulks, G. N., Bron, A. J., et al. (2011).The international workshop on meibomian gland dysfunction: Executive summary. Investigative Ophthalmology & Visual Science, 52(4), 1922–1929. https://doi.org/10.1167/iovs.10-6997a
Ung, L., Bispo, P. J. M., Shanbhag, S. S., Gilmore, M. S., & Chodosh, J. (2019).The persistent dilemma of microbial keratitis: Global burden, diagnosis, and antimicrobial resistance. Survey of Ophthalmology,64(3),255-271. https://doi.org/10.1016/j.survophthal.2018.12.003
Austin, A., Lietman, T., & Rose-Nussbaumer, J. (2017).Update on the management of infectious keratitis.Ophthalmology, 124(11), 1678–1689.https://doi.org/10.1016/j.ophtha.2017.05.012
