Interpretable machine learning framework for predicting Urban air quality

by Rana Muhammad Amir Latif, Tahir Iqbal, Ismaeel Abdel Qader, Atif Ikram, Hadeel Alsolai, Bayan Alabdullah, Fatimah Alhayan, Taher M. Ghazal

Urban air pollution remains a critical challenge for public health and environmental sustainability. This study investigates the predictive capabilities of five machine learning (ML) models: Linear Regression (LR), Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Regression (SVR) for forecasting the Air Quality Index (AQI) using the widely adopted Air Quality dataset from the UCI ML Repository. Although collected in 2004–2005, the dataset continues to serve as a benchmark in recent literature and provides a reproducible testbed for methodological evaluation. After structured pre-processing, feature engineering, and chronological train–validation–test splitting, models were rigorously tuned and assessed using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2), with 95% bootstrap confidence intervals and corrected resampled t-tests confirming statistical significance. Ensemble models achieved the best performance, with Random Forest obtaining the lowest RMSE (12.48) and MAE (9.35), and XGBoost achieving the highest R2 (0.89). Feature importance analysis identified NOx, PM2.5, and CO as the most influential predictors. We incorporated Shapley Additive exPlanations (SHAP) analyses and case-level visualizations to support interpretability, providing transparent insights for practical decision-making. While the study is limited by the absence of external validation and genetic variables (e.g., APOE), it establishes a reproducible, interpretable, and computationally efficient ML framework for AQI forecasting. The findings highlight the continuing relevance of benchmark datasets for reproducible evaluation and demonstrate the potential of interpretable ML-based approaches for smart city air quality management and public health policy.

Improving reproducibility of data analysis and code in medical research: 5 recommendations to get started

Due to the growing use of high-dimensional data and methodological advances in medical research, reproducibility of research is increasingly dependent on the availability of reproducible code. However, code is rarely made available and too often only partly reproducible. Here, we aim to provide practical and easily implementable recommendations for medical researchers to improve the reproducibility of their code. We reviewed current coding practices in the population-based Rotterdam Study cohort. Based on this review, we formulated the following five recommendations to improve the reproducibility of code used in data analysis: (1) make reproducibility a priority and allocate time and resources; (2) implement systematic code review by peers, as it further strengthens reproducibility. We provide a code review checklist, which serves as a practical tool to facilitate structured code review; (3) write comprehensible code that is well-structured; (4) report decisions transparently, for instance by providing the annotated workflow code for data cleaning, formatting and sample selection; and (5) focus on accessibility of code and data and share both, when possible, via an open repository to foster accessibility. Ideally, this repository should be managed by the institution and should be accessible to everyone. Based on these five recommendations, medical researchers can take actionable steps to improve the reproducibility of their research. Importantly, these recommendations are thought to provide a practical starting point for enhancing reproducibility rather than mandatory guidelines.