Looking for low vision: Predicting visual prognosis by fusing structured and free-text data from electronic health records.
Source check: Source checked. Not independent scientific confirmation.
Finding: Deep-learning models fused structured EHR data and ophthalmology notes to predict whether low vision would improve within a year; on 300 held-out patients, domain-specific text embeddings improved AUROC to about 0.82 versus structured-only and entity-based approaches. This is a bounded retrospective clinical prognosis result. Organization is unavailable in the deposited bibliographic metadata.
Technology: Deep-learning models combining EHR text and structured data
Publication: Publication status unspecified in annotation · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Author manuscript Methods/Results reviewed: single-center Stanford cohort (5,547), structured/text model comparisons, independent held-out test (300). No intervention or generalization claim; catalog search found no same result.
- Test and result
- Deep-learning models fused structured EHR data and ophthalmology notes to predict whether low vision would improve within a year; on 300 held-out patients, domain-specific text embeddings improved AUROC to about 0.82 versus structured-only and entity-based approaches. This is a bounded retrospective clinical prognosis result.
- Limitation / still unknown
- This is a bounded retrospective clinical prognosis result.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://benjamintseng.com/wp-content/uploads/2022/01/Looking-for-low-vision-Predicting-visual-prognosis-by-fusing-structured-and-free-text-data-from-ehrs.pdf
The legacy label “Not reported” does not distinguish information absent from reviewed material from information not assessed. It is not a scientific finding of absence.
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.