Development and internal validation of a time-aware transformer model for predicting pediatric myopia progression from irregular longitudinal school screening data

Abstract Background Rising global myopia rates are a major public health challenge because of the risk of irreversible vision loss in high myopia, and this creates a need for early identification of children on rapidly progressing trajectories. School-based screening characterises a child’s current refractive state but does not forecast where that trajectory is heading. We developed and internally validated a time-aware deep learning model that forecasts refractive progression directly from irregularly sampled school screening records, and assessed whether school-level geospatial context adds prognostic information. Methods A Time-Aware Transformer was adapted to process irregularly sampled refractive screening sequences without imputation. It combines an Adaptive-Frequency Time Embedding, which tunes a sinusoidal frequency spectrum to clinical sampling intervals using two learnable parameters, with a temperature-scaled Gated Residual Network that selectively integrates school-level environmental indices. The model was developed on a Gold Standard cohort of 2874 students from Yecheng County, China with complete four-year screening trajectories (2020 to 2023). Outcomes were one-year-ahead spherical equivalent refraction (SER) and classification of rapid myopic progression ( $$\:{\Delta\:}$$ SER $$\:\le\:-0.75$$ D/year). Internal validation used a held-out test set, five-fold cross-validation, a ten-seed stability analysis, a school-level grouped split and leave-one-school-out validation. Discrimination, calibration and net benefit were assessed, and nine baseline models were compared using paired test-set bootstrap tests with post hoc multiplicity control. Results The model achieved a mean squared error (MSE) of 0.168 D 2 and an $$\:{R}^{2}$$ of 0.929 for one-year-ahead SER, and an area under the receiver operating characteristic curve of 0.891 for identifying rapid progressors, with good calibration (calibration slope 0.968, intercept $$\:-0.014$$ D) and higher net benefit than referring all or no children across referral thresholds of 0.10 to 0.55. Performance was stable in five-fold cross-validation (MSE 0.171 ± 0.017) and across ten random seeds (MSE 0.168 ± 0.004). Accuracy was comparable to the strongest baselines rather than clearly superior: the difference from ContiFormer was 0.010 D in root mean squared error, well below the precision of non-cycloplegic autorefraction, while the proposed model used 42% fewer parameters (52 K versus 89 K) and trained 2.7 times faster. When whole schools were held out, MSE rose to 0.191 and the benefit attributable to environmental features fell from 0.027 to 0.005 D 2 , indicating that most of the apparent geospatial signal reflects school identity rather than measured environment. Prediction was hardest for children who converted to myopia during follow-up (MSE 0.243) and easiest for persistent non-myopes (MSE 0.105). Conclusion A compact time-aware transformer forecasts one-year-ahead refractive error from routinely collected school screening data with accuracy comparable to substantially larger continuous-time models, with calibrated risk estimates and clinically interpretable attention. The case for this architecture rests on efficiency, stability and interpretability rather than on an accuracy advantage. School-level environmental indices should be understood as geospatial baseline priors rather than as individual-level exposures.

Authors

Institutions

Publication Details

Journal
Journal of Translational Medicine
Published
2026-11-16
DOI
https://doi.org/10.1186/s12967-026-09221-8
Primary Topic
Ophthalmology and Visual Impairment Studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Development and internal validation of a time-aware transformer model for predicting pediatric myopia progression from irregular longitudinal school screening data

Emmanuel Eric Pazo, Salissou Moutari, 步绍翀, Mingxuan Zhang et al.
4 links
Journal of Translational Medicine
Ophthalmology and Visual Impairment Studies
article

Development and internal validation of a time-aware transformer model for predicting pediatric myopia progression from irregular longitudinal school screening data

Emmanuel Eric Pazo, Salissou Moutari, 步绍翀, Mingxuan Zhang, Nan Wei, Zhihui Zhang, Yingxiang Zhao, Tuluhong Wumaier, Muhammad Usama, Aixianjiang Maimaiti
article en

Abstract

Abstract Background Rising global myopia rates are a major public health challenge because of the risk of irreversible vision loss in high myopia, and this creates a need for early identification of children on rapidly progressing trajectories. School-based screening characterises a child’s current refractive state but does not forecast where that trajectory is heading. We developed and internally validated a time-aware deep learning model that forecasts refractive progression directly from irregularly sampled school screening records, and assessed whether school-level geospatial context adds prognostic information. Methods A Time-Aware Transformer was adapted to process irregularly sampled refractive screening sequences without imputation. It combines an Adaptive-Frequency Time Embedding, which tunes a sinusoidal frequency spectrum to clinical sampling intervals using two learnable parameters, with a temperature-scaled Gated Residual Network that selectively integrates school-level environmental indices. The model was developed on a Gold Standard cohort of 2874 students from Yecheng County, China with complete four-year screening trajectories (2020 to 2023). Outcomes were one-year-ahead spherical equivalent refraction (SER) and classification of rapid myopic progression ( $$\:{\Delta\:}$$ SER $$\:\le\:-0.75$$ D/year). Internal validation used a held-out test set, five-fold cross-validation, a ten-seed stability analysis, a school-level grouped split and leave-one-school-out validation. Discrimination, calibration and net benefit were assessed, and nine baseline models were compared using paired test-set bootstrap tests with post hoc multiplicity control. Results The model achieved a mean squared error (MSE) of 0.168 D 2 and an $$\:{R}^{2}$$ of 0.929 for one-year-ahead SER, and an area under the receiver operating characteristic curve of 0.891 for identifying rapid progressors, with good calibration (calibration slope 0.968, intercept $$\:-0.014$$ D) and higher net benefit than referring all or no children across referral thresholds of 0.10 to 0.55. Performance was stable in five-fold cross-validation (MSE 0.171 ± 0.017) and across ten random seeds (MSE 0.168 ± 0.004). Accuracy was comparable to the strongest baselines rather than clearly superior: the difference from ContiFormer was 0.010 D in root mean squared error, well below the precision of non-cycloplegic autorefraction, while the proposed model used 42% fewer parameters (52 K versus 89 K) and trained 2.7 times faster. When whole schools were held out, MSE rose to 0.191 and the benefit attributable to environmental features fell from 0.027 to 0.005 D 2 , indicating that most of the apparent geospatial signal reflects school identity rather than measured environment. Prediction was hardest for children who converted to myopia during follow-up (MSE 0.243) and easiest for persistent non-myopes (MSE 0.105). Conclusion A compact time-aware transformer forecasts one-year-ahead refractive error from routinely collected school screening data with accuracy comparable to substantially larger continuous-time models, with calibrated risk estimates and clinically interpretable attention. The case for this architecture rests on efficiency, stability and interpretability rather than on an accuracy advantage. School-level environmental indices should be understood as geospatial baseline priors rather than as individual-level exposures.

Journal of Translational Medicine
Queen's University Belfast (GB), Korea Advanced Institute of Science and Technology (KR), Tianjin Medical University Eye Hospital (CN), Tianjin Medical University (CN)
Natural Science Foundation of Tianjin City
Good health and well-being
Ophthalmology and Visual Impairment Studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon