Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1770
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-18T01:10:01.029914Z
status: published
lens: trace
sector: health
headline: Diagnostic Performance of Deep Learning Models for Ocular Toxoplasmosis Using Fundus Photography: A Systematic Review and Meta-Analysis
dek: Background Ocular toxoplasmosis (OT) is the leading infectious cause of posterior uveitis worldwide, yet diagnosis remains challenging without a universal gold standard. Although deep learning (DL) shows significant promise for automated image analysis, a rigorous synthesis of its diagnostic accuracy across heterogeneous architectures and datasets is lacking. Methods Following PRISMA-DTA and CLAIM-AI guidelines, we searched major databases through January 2026 for studies evaluating DL models for OT detection us…
gain_title: Across nine meta-analyzed studies, deep learning models detected ocular toxoplasmosis on fundus photographs with high pooled sensitivity and specificity.
problem_title: Most included studies used one Paraguayan dataset and lacked multicentric external validation, which limits how far the accuracy can be generalized to other populations.
trace_subject: Deep learning detection of ocular toxoplasmosis from fundus photography
gain_reading: Across nine meta-analyzed studies, deep learning models detected ocular toxoplasmosis on fundus photographs with high pooled sensitivity and specificity.
gain_evidence: Pooled sensitivity was 0.965 (95% CI: 0.944-0.978) and pooled specificity was 0.955 (95% CI: 0.929-0.972).
problem_reading: Most included studies used one Paraguayan dataset and lacked multicentric external validation, which limits how far the accuracy can be generalized to other populations.
problem_evidence: 81.2% of included studies relied exclusively on a single Paraguayan dataset (OTFID) | the absence of multicentric external validation
quick_read: A systematic review and meta-analysis searched databases through January 2026 for studies testing deep learning on fundus photographs to detect ocular toxoplasmosis. Sixteen studies were synthesized qualitatively, and nine with usable contingency data were pooled, showing sensitivity of 0.965 and specificity of 0.955.

The results suggest automated image analysis could support diagnosis of a leading infectious cause of posterior uveitis, where no universal gold standard exists. Yet the evidence base is geographically narrow and heterogeneous, so real-world clinical performance in diverse populations remains unproven.
limitation: Most included studies used a single Paraguayan dataset, with high heterogeneity and no multicentric external validation, so global generalizability is uncertain.
tag: Dual reading
key_points: Sixteen studies covering 38 model configurations were included; nine studies with 24 architectures were pooled. | The pooled diagnostic odds ratio was 594.1, with positive and negative likelihood ratios of 21.6 and 0.036. | Between-study heterogeneity was substantial, with I^2 of 87.9%. | 81.2% of studies relied exclusively on the single OTFID dataset from Paraguay. | The authors call for diverse international cohorts, explainable AI, and federated learning.
rundown: The review followed PRISMA-DTA and CLAIM-AI guidelines, appraised study quality with QUADAS-2, and used a bivariate random-effects model to pool sensitivity and specificity, with HSROC curves to visualize discriminatory performance.

Beyond accuracy, the authors report the pooled diagnostic odds ratio of 594.1 and note the performance is comparable to established ophthalmic AI benchmarks. They caution that the high heterogeneity complicates interpretation of the pooled figures.

The authors raise concerns about phenotypic bias from reliance on one dataset and say clinical translation is constrained by the lack of multicentric external validation. They recommend future work prioritize diverse international cohorts, explainable AI, and federated learning.
sources:
- peer_reviewed | Ocular Immunology and Inflammation | https://doi.org/10.1080/09273948.2026.2736177 | 2026-10-07
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

4d6c050f7d84281f6878c60c109cabc3a3737851631be84e78a9908da2b05d7c

previous

0000000000000000000000000000000000000000000000000000000000000000