Predicting atropine treatment response heterogeneity in pediatric myopia using explainable machine learning: an on-treatment longitudinal monitoring framework
4 affiliations
- 1Department of Medical Education, Guishan Dist, Linkou Chang Gung Memorial Hospital
- 2Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Johns Hopkins University
- 3Graduate Institute of Business Administration, Fu Jen Catholic University
- 4Department of Ophthalmology, Shin Kong Wu Ho-Su Memorial Hospital
Abstract
To establish an explainable machine learning framework to monitor longitudinal refractive changes in children receiving atropine therapy and visualize individual treatment-response heterogeneity. This retrospective cohort included 1,545 eyes from pediatric patients treated with 0.1%–1.0% atropine at a tertiary center. Eight cumulative clinical and treatment-related features: baseline spherical equivalent (SE), intraocular pressure (IOP), IOP change, age, sex, treatment duration, cumulative dosage, and average monthly dosage were analyzed. Four machine learning models (Lasso, CART, XGBoost, Random Forest) were compared using 100 repeated runs, and the best-performing model was interpreted with SHapley Additive exPlanations (SHAP) to quantify global and individual feature contributions. Random Forest achieved the lowest average error metrics (RMSE 0.531 ± 0.030; MAE 0.388 ± 0.016). SHAP identified baseline SE as the most influential determinant of final refractive change, followed by followed by cumulative dosage and average monthly dosage. Negative SHAP contributions from higher doses captured clinician-driven titration patterns (confounding by indication) rather than a causal hazard. Case-level SHAP waterfall plots revealed successfully mapped response profiles, distinguishing effective stabilization in mild baseline myopia from pharmacologic saturation in high baseline myopia. Integrating Random Forest with SHAP delivers transparent, high-fidelity monitoring of atropine response in pediatric myopia. Rather than relying solely on static baseline predictors, this explainable framework leverages accumulated clinical process metrics to bridge data science and clinical reasoning. It provides a robust tool for longitudinal treatment tracking, retrospective clinical audit, and early risk stratification.
Related
- Predicting subsequent-year physical fitness assessment failure in university students using longitudinal data and explainable machine learning
- MRI-based intratumoral and peritumoral heterogeneity for predicting intracranial progression in EGFR-mutant lung adenocarcinoma patients with treatment-naive brain metastases receiving first-line third-generation EGFR-TKIs.
- Explainable machine learning and deep learning models for predicting in-hospital mortality in burn patients
- Development and internal temporal validation of an explainable XGBoost model for predicting clinical pregnancy after frozen embryo transfer
- Ultrasound-based deep learning radiomics with explainable machine learning for predicting benign and malignant thyroid nodules in lymphocytic thyroiditis: a multicenter study
BibTeX
@article{chen2026predicting,
title = {{Predicting atropine treatment response heterogeneity in pediatric myopia using explainable machine learning: an on-treatment longitudinal monitoring framework}},
author = {Jun-Wei Chen and Chieh-Han Yu and Tzu-Chi Liu and Tzu-En Wu and Chi-Jie Lu},
journal = {Scientific Reports},
year = {2026},
month = aug,
doi = {10.1038/s41598-026-67166-w},
url = {https://doi.org/10.1038/s41598-026-67166-w},
note = {CC BY},
}
RIS
TY - JOUR
TI - Predicting atropine treatment response heterogeneity in pediatric myopia using explainable machine learning: an on-treatment longitudinal monitoring framework
AU - Jun-Wei Chen
AU - Chieh-Han Yu
AU - Tzu-Chi Liu
AU - Tzu-En Wu
AU - Chi-Jie Lu
PY - 2026
DA - 2026/08/01
JO - Scientific Reports
DO - 10.1038/s41598-026-67166-w
UR - https://doi.org/10.1038/s41598-026-67166-w
AB - To establish an explainable machine learning framework to monitor longitudinal refractive changes in children receiving atropine therapy and visualize individual treatment-response heterogeneity. This retrospective cohort included 1,545 eyes from pediatric patients treated with 0.1%–1.0% atropine at a tertiary center. Eight cumulative clinical and treatment-related features: baseline spherical equivalent (SE), intraocular pressure (IOP), IOP change, age, sex, treatment duration, cumulative dosage, and average monthly dosage were analyzed. Four machine learning models (Lasso, CART, XGBoost, Random Forest) were compared using 100 repeated runs, and the best-performing model was interpreted with SHapley Additive exPlanations (SHAP) to quantify global and individual feature contributions. Random Forest achieved the lowest average error metrics (RMSE 0.531 ± 0.030; MAE 0.388 ± 0.016). SHAP identified baseline SE as the most influential determinant of final refractive change, followed by followed by cumulative dosage and average monthly dosage. Negative SHAP contributions from higher doses captured clinician-driven titration patterns (confounding by indication) rather than a causal hazard. Case-level SHAP waterfall plots revealed successfully mapped response profiles, distinguishing effective stabilization in mild baseline myopia from pharmacologic saturation in high baseline myopia. Integrating Random Forest with SHAP delivers transparent, high-fidelity monitoring of atropine response in pediatric myopia. Rather than relying solely on static baseline predictors, this explainable framework leverages accumulated clinical process metrics to bridge data science and clinical reasoning. It provides a robust tool for longitudinal treatment tracking, retrospective clinical audit, and early risk stratification.
SN - 2045-2322
ER -