Variable selection (VS) is a critical step in developing predictive binary classification (BC) models. Many traditional methods for assessing the added value of a candidate variable provide global performance summaries and lack an interpretable graphical summary of results. To address this limitation, we developed the U-smile method, a residual-based, post hoc evaluation approach for assessing prediction improvements and worsening separately for events and non-events. The U-smile method produces three families of interpretable BA-RB-I coefficients at three levels of generality and a standardized graphical summary through U-smile and prediction improvement–worsening (PIW) plots, enabling transparent, interpretable, and explainable VS. Validated in balanced and imbalanced BC scenarios, the method proved robust to class imbalance and collinearity, and more sensitive than traditional metrics in detecting subtle but meaningful effects. Moreover, the method’s intuitive visual output (U-smile plot) facilitates the rapid communication of results to non-technical stakeholders, bridging the gap between data science and applied decision-making. The U-smile method supports both local and global evaluations and complements existing explainable machine learning (XML) and artificial intelligence (XAI) tools without overlapping in their functions. The U-smile method offers a transparency-enhancing and human-oriented approach for ethical and fair VS, making it highly suited for high-stakes domains, e.g., healthcare and public health.

Background: Poland was one of only 10 European countries listed teachers as a priority group for vaccination against COVID-19 among National Vaccination Program (NVP). The aim of this study was to analyse post-vaccination symptoms self-reported by teachers vaccinated under the national COVID-19 vaccination programme. Methods: The presented cross-sectional survey was conducted among teachers from all levels of education in public and non-public institutions, who received the SARS-CoV-2 virus vaccination campaign with the vaccine from AstraZeneca as part of the NVP. The survey was conducted using an original, self-designed questionnaire prepared for this study and distributed to teachers in the form of an online survey via email. Bayesian logistic and linear regression were used to estimate the relationship between predictors and dependent variables. Results: A total of 4622 teachers took part in the survey. Of this number, 3908 teachers declared that they had taken the vaccine. (84.5%). In the study group, self-reported late post-vaccination reactions were very strongly [logBF > 3.4] associated with both gender and age. In contrast, self-reporting of serious late post-vaccination symptoms other than fever was very strongly associated only with gender. Only a small proportion of teachers (from 1.45% to 5.34% depending on age and gender) self-reported immediate post-vaccination reaction (up to 15 min after injection). Conclusions: Self-reporting of symptoms is a valuable tool for monitoring the effectiveness and safety of vaccinations and can also contribute to increased satisfaction with the vaccination process, especially when patients are made aware that post-vaccination symptoms are a natural sign of the body’s immune response.