Background/Objectives: Myopia is a growing global health concern, especially among school-aged children in East Asia. Topical atropine is a key treatment for pediatric myopia control, but individual responses vary, with some children showing rapid progression despite higher doses. This retrospective observational study aims to develop an interpretable machine learning model to predict individualized treatment responses and support personalized clinical decisions, based on data collected over a 3-year period without a control group. Methods: A total of 1545 pediatric eyes treated with topical atropine for myopia control at a single tertiary medical center are analyzed. Classification and regression tree (CART) is constructed to predict changes in spherical equivalent (SE) and identify influencing risk factors. These factors are mainly received treatments for myopia including atropine dosage records, treatment duration, and ophthalmic examinations. Furthermore, decision rules that closely resemble the clinical diagnosis process are provided to assist clinicians with more interpretable insights into personalized treatment decisions. The performance of CART is evaluated by comparing with the benchmark model of least absolute shrinkage and selection operator regression (Lasso) to confirm the practicality of CART usage. Results: Both the CART and Lasso models demonstrated comparable predictive performance. The CART model identified baseline SE as the primary determinant of myopia progression. Children with a baseline SE more negative than −3.125 D exhibited greater myopic progression, particularly those with prolonged treatment duration and higher cumulative atropine dosage. Conclusions: Baseline SE has been identified as the key factor affecting SE difference. The generated decision rules from CART demonstrate the use of explainable machine learning in precision myopia management.

Accurately forecasting the interval-valued green electricity (GE) supply is challenging due to the unpredictable and instantaneous nature of its source; yet, reliable multi-step-ahead forecasting is essential for providing the lead time required in operations, resource allocation, and system management. This study proposes an augmented-feature multi-step interval-valued forecasting (AFMIF) scheme that aims to address the challenges in forecasting interval-valued GE supply data by extracting additional features hidden within an interval. Unlike conventional methods that rely solely on original interval bounds, AFMIF integrates augmented features that capture statistical and dynamic properties to reveal hidden patterns. These features include basic interval boundaries and statistical distributions from an interval. Three effective forecasting methods, based on gated recurrent units (GRUs), long short-term memory (LSTM), and a temporal convolutional network (TCN), are constructed under the proposed AFMIF scheme, while the mean ratio of exclusive-or (MRXOR) is used to evaluate the forecasting performance. Two different real datasets of wind-based GE supply data from Belgium and Germany are used as illustrative examples. Empirical results demonstrate that the proposed AFMIF scheme with GRUs can generate promising results, achieving a mean MRXOR of 0.7906 from the Belgium data and 0.9719 from the Germany data for one-step- to three-steps-ahead forecasting. Moreover, the TCN yields an average improvement of 13% across all time steps with the proposed scheme. The results highlight the potential of the AFMIF scheme as an effective alternative approach for accurate multi-step-ahead interval-valued GE supply forecasting that offers practical benefits supporting GE management.