ISI Journals

The integration of artificial intelligence into digital medicine has introduced transformative capabilities in ocular disease classification and progression prediction. Yet, persistent concerns regarding algorithmic fairness remain, especially in the context of long-term glaucoma prediction. This study proposes TransFair, a methodological framework for transferring fairness principles from ocular disease classification models to progression prediction tasks. By leveraging transfer learning and equity-aware regularization, the framework seeks to mitigate performance disparities across demographic subgroups while maintaining predictive robustness. Existing research in healthcare AI demonstrates that biased datasets, imbalanced representation, and opaque model architectures contribute to inequitable clinical outcomes. In ocular medicine, such disparities can exacerbate the risk of delayed diagnosis or mismanagement of glaucoma, particularly among vulnerable populations. The novelty of this work lies in aligning fairness-aware feature extraction from large-scale classification models with longitudinal progression modeling. Through empirical evaluation, we explore how transferable fairness metrics—such as equalized odds, demographic parity, and subgroup calibration— can be incorporated into digital medicine pipelines. Preliminary findings suggest that applying fairness- aware transfer learning enhances generalizability and reduces bias propagation, without significantly sacrificing accuracy. Moreover, the proposed methodology demonstrates potential in advancing personalized healthcare by integrating both predictive performance and ethical responsibility. This research contributes to the emerging paradigm of fairness in AI for healthcare by addressing a dual challenge: ensuring accuracy in glaucoma progression prediction and embedding fairness constraints during knowledge transfer. Ultimately, TransFair highlights the importance of equity-driven design in digital medicine, aiming to safeguard trust, inclusivity, and sustainability in clinical decision-support systems.