The Evolution of Artificial Intelligence in Ocular Toxoplasmosis Detection: A Scoping Review on Diagnostic Models, Data Challenges, and Future Directions

Ocular Toxoplasmosis (OT), a leading cause of infectious posterior uveitis, presents significant diagnostic challenges in atypical cases due to phenotypic overlap with other retinochoroiditides and a reliance on expert interpretation of multimodal imaging. This scoping review systematically maps the burgeoning application of artificial intelligence (AI), particularly deep learning, in automating OT diagnosis. We synthesized 22 studies to characterize the current evidence, data landscape, and clinical translation readiness. Findings reveal a field in its nascent yet rapidly accelerating phase, dominated by convolutional neural networks (CNNs) applied to fundus photography for binary classification tasks, often reporting high accuracy (87-99.2%). However, development is critically constrained by small, imbalanced, single-center datasets, a near-universal lack of external validation, and insufficient explainable AI (XAI), creating a significant gap between technical promise and clinical utility. While AI demonstrates strong potential to standardize diagnosis and reduce subjectivity, its path to integration is hampered by over-reliance on internal validation, the "black box" nature of models, and an absence of implementation strategies. Future progress hinges on collaborative multi-center data curation, mandatory external and prospective validation, the integration of XAI for transparency, and a focused shift towards developing AI tools that assist in the complex differential diagnosis of posterior uveitis, ultimately bridging the translational chasm to clinical practice.