The Effectiveness of Large Language Models in the Diagnosis and Treatment of Glaucoma
DOI:
https://doi.org/10.5281/zenodo.17045246Keywords:
Glaucoma, Artificial Intelligence, ReadabilityAbstract
Objective The objective of this study is to compare the readability levels of texts generated by Open AI and GEMINI, which are artificial intelligence language models. The present study focuses on the readability analysis of texts on glaucoma, with the objective of determining which model is more suitable for specific purposes and target audiences.
Methods In the course of the research, 20 inquiries were presented to both language models using the same topic and guidelines. The inquiries were posed on various days across ten repeated experiments, and the responses obtained were meticulously documented. The generated texts were then subjected to an analytical process that involved the application of various readability formulas.
Results: The analysis results indicate statistically significant differences between the readability scores of OpenAI and GEMINI. A comparative analysis revealed that GEMINI exhibited superior performance in terms of average scores across a range of metrics when compared with OpenAI. This observation suggests that GEMINI's texts are characterized by a heightened level of complexity. P-values were determined to be 0.001 for the Flesch Readability, FOG scale, and a multitude of additional metrics. However, a lack of statistical significance was observed in the Forecast Readability Formula (p = 0.050).
Conclusion The findings indicate that GEMINI might be more appropriate for texts intended for an academic or professional audience, while OpenAI could be a more suitable option for content directed towards a broader audience.
References
1. Shan S, Wu J, Cao J, Feng Y, Zhou J, Luo Z, Song P, Rudan I; Global Health Epidemiology Research Group (GHERG). Global incidence and risk factors for glaucoma: A systematic review and meta-analysis of prospective studies. J Glob Health. 2024 Nov 8;14:04252. doi: 10.7189/jogh.14.04252. PMID: 39513294; PMCID: PMC11544525.
2. Tham YC, Li X, Wong TY, Quigley HA, Aung T, Cheng CY.Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology. 2014;121:2081–90. 10.1016/j.ophtha.2014.05.013
3. 3.Ramulu PY, Mihailovic A, West SK, Gitlin LN, Friedman DS.Predictors of Falls per Step and Falls per Year At and Away From Home in Glaucoma. Am J Ophthalmol. 2019;200:169–78. 10.1016/j.ajo.2018.12.021
4. 4.Zhang X, Olson DJ, Le P, Lin FC, Fleischman D, Davis RM.The Association Between Glaucoma, Anxiety, and Depression in a Large Population. Am J Ophthalmol. 2017;183:37–41. 10.1016/j.ajo.2017.07.021 [
5. 5.Varma R, Lee PP, Goldberg I, Kotak S.An assessment of the health and economic burdens of glaucoma. Am J Ophthalmol. 2011;152:515–22. 10.1016/j.ajo.2011.06.004
6. 6.Leite MT, Sakata LM, Medeiros FA.Managing glaucoma in developing countries. Arq Bras Oftalmol. 2011;74:83–4. 10.1590/S0004-27492011000200001
7. 7.George R, Vijaya L.First World Glaucoma day, March 6, 2008: tackling glaucoma challenges in India. Indian J Ophthalmol. 2008;56:97–8. 10.4103/0301-4738.39111
8. 8.Liang Y, Jiang J, Ou W, Peng X, Sun R, Xu X, et al. Effect of Community Screening on the Demographic Makeup and Clinical Severity of Glaucoma Patients Receiving Care in Urban China. Am J Ophthalmol. 2018;195:1–7. 10.1016/j.ajo.2018.07.013
9. Gür ÖE, Bedel C, Selvi F. Comparison of Chat GPT and Gemini in ENT Evaluation Questions. Journal Of Medical Sciences. 2024 Dec 20;3(12):17-22.
10. Bedel HA, Bedel C, Selvi F, Zortuk Ö, Karancı Y. Emergency Medicine Assistants in the Field of Toxicology, Comparison of ChatGPT-3.5 and GEMINI Artificial Intelligence Systems. Acta Medica Lituanica. 2024 Dec 4;31(2):294.
11. Mutlucan UO, Bedel C, Selvi F. Comparison of Chat GPT and Gemini in Neurosurgical Evaluation Questions. Journal Of Medicine And Surgery. 2024 Dec 8;3(12):10-5.
12. Tonti E, Tonti S, Mancini F, Bonini C, Spadea L, D'Esposito F, Gagliano C, Musa M, Zeppieri M. Artificial Intelligence and Advanced Technology in Glaucoma: A Review. J Pers Med. 2024 Oct 16;14(10):1062. doi: 10.3390/jpm14101062. PMID: 39452568; PMCID: PMC11508556.
13. Mirzania D., Yazdani A., Nouri-Mahdavi K. Deep Learning Methods for Detecting Glaucoma Using Fundus Pho-tographs, OCT, or Standard Automated Perimetry. Eur. J. Ophthalmol. 2021;31:1230–1240.
14. Islam M., Kamruzzaman M., Rahman M. Performance of Deep Learning Algorithms in the Detection of Glauco-matous Optic Neuropathy (GON) Stud. Health Technol. Inform. 2020;270:451–462.
15. Murtagh P., Zhao W., Ramachandran R. Diagnostic Accuracy of OCT and Fundus Photography in Glaucoma De-tection: A Machine Learning Perspective. Int. J. Ophthalmol. 2020;13:460–468.
16. Ran A.R., Tham C.C., Chan P.P., Cheng C.Y., Tham Y.C., Rim T.H., Cheung C.Y. Deep learning in glaucoma with optical coherence tomography: A review. Eye. 2021;35:188–201. doi: 10.1038/s41433-020-01191-5.
17. Akter N., Fletcher J., Perry S., Simunovic M.P., Briggs N., Roy M. Glaucoma diagnosis using multi-feature analysis and a deep learning technique. Sci. Rep. 2022;12:8064. doi: 10.1038/s41598-022-12147-y.
18. Zhang Y., Wang N., Liu H. Re: Christopher et al.: Deep learning approaches predict glaucomatous visual field damage from OCT optic nerve head en face images and retinal nerve fiber layer thickness maps (Ophthalmology. 2020;127:346–356) Ophthalmology. 2022;129:e4–e5. doi: 10.1016/j.ophtha.2021.07.035.
19. 17.Muhammad H., Fuchs T.J., De Cuir N., De Moraes C.G., Blumberg D.M., Liebmann J.M., Ritch R., Hood D.C. Hybrid Deep Learning on Single Wide-field Optical Coherence tomography Scans Accurately Classifies Glaucoma Suspects. J. Glaucoma. 2017;26:1086–1094. doi: 10.1097/IJG.0000000000000765.
20. Andersson S., Heijl A., Bizios D., Bengtsson B. Comparison of clinicians and an artificial neural network regarding accuracy and certainty in performance of visual field assessment for the diagnosis of glaucoma. Acta Ophthalmol. 2013;91:413–417. doi: 10.1111/j.1755-3768.2012.02435.x.
21. Ran A., Li Y., Chen X., Zhao L. Deep Learning for Glaucoma Detection Using OCT Images: High Accuracy in Detecting Disease Progression. Eye. 2022;36:15–25.
22. Barella K.A., Costa V.P., Gonçalves Vidotti V., Silva F.R., Dias M., Gomi E.S. Glaucoma Diagnostic Accuracy of Machine Learning Classifiers Using Retinal Nerve Fiber Layer and Optic Nerve Data from SD-OCT. J. Ophthalmol. 2013;2013:789129. doi: 10.1155/2013/789129. [DOI] [PMC free article] [PubMed] [Google Scholar]
23. Yousefi S., Balasubramanian M., Goldbaum M.H., Medeiros F.A., Zangwill L.M., Weinreb R.N., Liebmann J.M., Girkin C.A., Bowd C. Unsupervised Gaussian Mixture-Model With Expectation Maximization for Detecting Glaucomatous Progression in Standard Automated Perimetry Visual Fields. Transl. Vis. Sci. Technol. 2016;5:2. doi: 10.1167/tvst.5.3.2. [DOI] [PMC free article] [PubMed] [Google Scholar]
24. Zhang Y., Wang J., Li H., Sun Z. Deep Learning for Glaucoma Risk Prediction Using Fundus Photographs: Effective Risk Stratification. Ophthalmology. 2021;128:1234–1245. doi: 10.1016/j.ophtha.2021.03.012. [DOI] [Google Scholar]
25. Wagner I.V., Stewart M.W., Dorairaj S.K. Updates on the Diagnosis and Management of Glaucoma. Mayo Clin. Proc. Innov. Qual. Outcomes. 2022;6:618–635. doi: 10.1016/j.mayocpiqo.2022.09.007. [DOI] [PMC free article] [PubMed] [Google Scholar]
26. Seker E., Talburt J.R., Greer M.L. Preprocessing to Address Bias in Healthcare Data. Stud. Health Technol. Inform. 2022;294:327–331. doi: 10.3233/shti220468. [DOI] [PubMed] [Google Scholar]
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Yavuz Fatih Yavuz, Alper Sevdimbaş
This work is licensed under a Creative Commons Attribution 4.0 International License.
