Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Observational Study
. 2025 Jul 22;25(1):419.
doi: 10.1186/s12886-025-04256-9.

Artificial intelligence in predicting macular hole surgery outcomes: a focus on optical coherence tomography parameters

Yucel Ozturk  1 , Abdullah Ağın  2 , Burcu Yelmi  3 , Nilufer Zorlutuna Kaymak  4
Affiliations
Observational Study

Artificial intelligence in predicting macular hole surgery outcomes: a focus on optical coherence tomography parameters

Yucel Ozturk et al. BMC Ophthalmol. .

Abstract

Purpose: To evaluate the predictive performance of optical coherence tomography (OCT)-based indices and artificial intelligence (AI) using a Generative Pre-Trained Transformer (GPT) model and compare them with traditional logistic regression in forecasting anatomical success following macular hole (MH) surgery.

Methods: This retrospective observational study included 51 eyes of 51 patients who underwent pars plana vitrectomy for idiopathic MH. Preoperative OCT measurements of macular hole index (MHI), traction hole index (THI), hole form factor (HFF), basal hole diameter (BHD), and minimum hole diameter (MHD) were recorded. GPT-based AI predictions were generated using masked input data. A logistic regression model was developed with the same variables. Predictive performance was assessed using accuracy, area under the curve (AUC), positive predictive value (POPV), negative predictive value (NPV), and Kappa statistics.

Results: Anatomical success was achieved in 72.5% of cases. MHI, THI, and HFF were significantly higher in the successful group (p < 0.0001). GPT achieved an accuracy of 77.0% and AUC of 0.770, with perfect POPV (1.000) but low NPV (0.452). Logistic regression outperformed GPT, achieving an accuracy of 84.3%, an AUC of 0.759, a higher NPV (0.800), and better agreement (Kappa 0.568 vs. 0.392). BHD and MHD showed poor predictive power (AUC 0.291).

Conclusion: OCT-derived indices, especially MHI, THI, and HFF, effectively predict MH surgery outcomes. Logistic regression based on actual patient data demonstrated superior predictive performance compared to GPT. AI models hold potential but require further development, integration of multimodal data, and validation before clinical application.

Keywords: Artificial intelligence; BHD; GPT; HFF; MHI; Macular hole; THI.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: Kartal Dr. Lutfi Kirdar City Hospital Clinical Research Ethics Committee, a body that upholds the highest ethical standards in medical research, approved the study, providing reassurance about the ethical conduct of our research. (2025/010.99/13/26) This research complied with the principles of the Declaration of Helsinki. The requirement for obtaining written informed consent from participants was waived by the Lutfi Kirdar City Hospital Clinical Research Ethics Committee due to the retrospective nature of the study. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
ROC curve for each metric: ROC curves demonstrating the performance of different OCT-derived metrics in predicting macular hole surgery outcomes
Fig. 2
Fig. 2
ROC curve: ChatGPT vs logistic regression: comparison of ROC curves between a logistic regression model and ChatGPT in predicting surgical outcomes of MH using preoperative OCT parameters
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Jiao C, Edupuganti NR, Patel PA, Bui T, Sheth V. Evaluating the artificial intelligence performance growth in ophthalmic knowledge. 2023. 10.7759/cureus.45700. - PMC - PubMed
    1. Sallam M. ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthcare (Basel). 2023;11(6). 10.3390/healthcare11060887. - PMC - PubMed
    1. Yang LWY, Ng WY, Foo LL, Liu Y, Yan M, Lei X, et al. Deep learning-based natural language processing in ophthalmology: applications, challenges and future directions. Curr Opin Ophthalmol. 2021;32(5):397–405. 10.1097/ICU.0000000000000789. - PubMed
    1. OpenAI. GPT-4 Technical Report. 2023. Available from: https://openai.com/research/gpt-4.
    1. Parravano M, Giansanti F, Eandi CM, Yap YC, Rizzo S, Virgili G. Vitrectomy for idiopathic macular hole. Cochrane Database Syst Rev. 2015;2015(5):CD009080. 10.1002/14651858.CD009080.pub2. - PMC - PubMed

Publication types

LinkOut - more resources