Actionable companion · Assessment & reasoning

Learning with agency: Artificial intelligence-based quantitative analysis of interocular retinal vascular differences in school-age children with mild to moderate anisometropia

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paper Search paper agent CC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): K–12 · mixed / unspecified, Children · stage unspecified. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Objective To apply artificial intelligence (AI) technology for the quantitative analysis of interocular retinal vascular differences in color fundus photographs (CFP) among school-age children with mild to moderate anisometropia and to investigate their correlation with the degree of anisometropia. Methods In this retrospective cross-sectional study, 33 children aged 6–9 years with mild to moderate anisometropia were enrolled. CFPs of both eyes were acquired. A deep learning-based AI algorithm was employed to quantitatively analyze interocular differences in the degree of fundus tessellation (FT), the extent of peripapillary atrophy (PPA), optic disc morphology, and retinal vascular characteristics. The correlations between these differences and the interocular spherical equivalent (SE) difference were assessed. Results Eyes with lower SE values exhibited significantly higher FT density, larger FT areas across all regions, greater PPA area and extent, a larger optic disc ovality index, higher total vessel length density, and higher arterial fractal dimensions (D0, D1) compared to eyes with higher SE values. In contrast, the horizontal cup-to-disc ratio and the average venous tortuosity were significantly lower in the lower SE eyes (all P 0.05). Conclusion Significant interocular differences in fundus structures are present in children with mild to moderate anisometropia. The magnitude of interocular difference in the PPA-to-optic disc diameter ratio shows a significant correlation with the degree of anisometropia. AI-based quantitative analysis provides an objective imaging basis for the early identification of anisometropia.

What kind of evidence is this?

Supporting AI learning science · Survey / observational study

Stage: K–12 · mixed / unspecified; Children · stage unspecified. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Participant ages · source passage

Methods In this retrospective cross-sectional study, 33 children aged 6–9 years with mild to moderate anisometropia were enrolled.

Study methods · source passage

We retrospectively analyzed the clinical data of children aged 6–9 years who visited the Shenzhen Eye Hospital between 2023 and 2025. All participants had undergone at least one cycloplegic refraction examination and one CFP examination during the same visit. Mild to moderate anisometropia was defined as an interocular difference in spherical equivalent (SE) of 1.00 diopters (D) ≤ SE < 3.00 D (17–20). Hyperopic anisometropia was defined as both eyes having SE ≥ 0.00 D. Myopic anisometropia was defined as both eyes having SE < 0.00 D. Mixed anisometropia was defined as one eye having SE ≥ 0.00 D and the fellow eye having SE ≤ 0.00 D (21). Based on the interocular SE difference, eyes were categorized into a higher-SE group and a lower-SE group. Participants meeting any of the following criteria were excluded: (1) corrected visual acuity < 0.7, or a prior diagnosis of amblyopia; (2) high myopia (spherical power ≥ −6.00 D in either eye); (3) the presence of severe inflammation, photophobia, or epiphora in either eye; (4) the presence of organic ocular disease in either eye; (5) a diagnosis of color vision deficiency (color weakness or color blindness); or (6) incomplete data.

Limitations and uncertainty · source passage

This study employed AI technology to conduct a quantitative analysis of color fundus photographs from both eyes of children with mild to moderate anisometropia. It systematically revealed significant interocular differences in fundus structural parameters, including fundus tessellation, optic disc morphology, and retinal vascular characteristics. Notably, the correlation analysis demonstrated a significant linear association between the degree of anisometropia and the magnitude of the interocular difference in the PPA-to-optic disc diameter ratio. In summary, AI-based quantitative analysis of fundus images offers a promising objective imaging tool for the early identification and follow-up monitoring of anisometropia; however, given the limitations of the current study, particularly its sample size, further validation through larger-scale longitudinal studies is warranted.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.

A 90-day district pilot

Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
Days 16–30 · Design. Verify the grades and participant ages in each included study before selecting a classroom pilot. Use teacher-led hints and preserve a non-AI route; a K–12 label does not establish the same benefit across every school year. Name an accountable owner and set the baseline, success threshold and budget before implementation.
Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
Days 61–90 · Decide. Compare independent learning, delayed retention and transfer within the locally selected grade band. Report age-stage uncertainty rather than pooling young children and adolescents as one population. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Zhixing Xu; Yuke Ji; Yuting Hu; Zhengyang Tao; Zongyue Lv; Guorui Hu; Minmin Li; Xiaoyan Wang; Hongwei Deng; Zefeng Kang. Artificial intelligence-based quantitative analysis of interocular retinal vascular differences in school-age children with mild to moderate anisometropia. Frontiers in Medicine (2026-07-01). https://doi.org/10.3389/fmed.2026.1829476

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.