Background and Objectives: Early detection of chronic diseases is essential for improving health outcomes and reducing long-term complications. In Poland, the POZ PLUS pilot programme introduced the Health Check-up (Bilans Zdrowia, BZ) tool, a structured preventive assessment designed to support early identification of chronic conditions in primary care. This study aimed to assess the association between participation in the Health Check-up and the detection (diagnostic yield) of hypertension, type 2 diabetes, lipid metabolism disorders, elevated fasting blood glucose, hypothyroidism, and non-toxic goiter by comparing outcomes in an intervention group and a control group. Materials and Methods: A non-randomised comparative study was conducted using routine clinical data from Health Check-ups performed within the POZ PLUS pilot. Detection rates were compared with those obtained in standard primary care practice during the same period. The study group consisted of 865 adults who met the inclusion criteria and underwent the BZ procedure, while the control group comprised 3199 patients with comparable eligibility who received usual care. Data analysis was performed using R and RStudio. Results: Hypertension detection was similar in both groups: 4.6% (95% CI: 3.3–6.3%) in the intervention group versus 4.5% (95% CI: 3.8–5.3%) in the control group (p = 0.9505). No significant difference was observed in type 2 diabetes detection: 0.7% (95% CI: 0.3–1.5%) versus 0.4% (95% CI: 0.2–0.7%) (p = 0.4134). In contrast, detection rates were significantly higher in the Health Check-up group for lipid metabolism disorders (10.3% vs. 2.6%; p < 0.001), abnormal fasting glucose (2.9% vs. 1.8%; p = 0.0465), and thyroid diseases, including hypothyroidism and non-toxic goiter (4.3% vs. 2.3%; p = 0.0016). Conclusions: The Health Check-up tool was associated with higher detection rates of lipid disorders, impaired fasting glucose, and thyroid diseases compared with usual care, suggesting increased diagnostic yield under a structured preventive assessment pathway. Further research should evaluate downstream clinical outcomes and cost-effectiveness. Given the non-randomised design and differential diagnostic intensity between groups, these findings should be interpreted as associations with diagnostic yield rather than causal effects on disease incidence or clinical outcomes.

Real-life binary classification problems often involve imbalanced datasets, where the majority class outnumbers the minority class. We previously developed the U-smile method, which comprises the U-smile plot and the BA, RB and I coefficients, to assess the usefulness of a new variable added to a reference prediction model and validated it under class balance. In this study, we evaluated the U-smile method under class imbalance, proposed a three-level approach of the U-smile method, and used the I coefficients as a weighting factor for point size in the U-smile plots of the BA and RB coefficients. Using real data from the Heart Disease dataset and generated random variables, we built logistic regression models to assess four new variables added to the reference model (nested setting). These models were evaluated at seven pre-defined imbalance levels of 1%, 10%, 30%, 50%, 70%, 90% and 99% of the event class. The results of the U-smile method were compared to those of certain traditional measures: Brier skill score, net reclassification index, difference in F1-score, difference in Matthews correlation coefficient, difference in the area under the receiver operating characteristic curve of the new and reference models, and the likelihood-ratio test. The reference model overfitted to the majority class at higher imbalance levels. The BA-RB-I coefficients of the U-smile method identified informative variables across the entire imbalance range. At higher imbalance levels, the U-smile method indicated both prediction improvement in the minority class (positive BA and I coefficients) and reduction in overfitting to the majority class (negative RB coefficients). The U-smile method outperformed traditional evaluation measures across most of the imbalance range. It proved highly effective in variable selection for imbalanced binary classification, making it a useful tool for real-life problems, where imbalanced datasets are prevalent.

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: Abortion is one of the most common medical procedures worldwide. Despite this, access to abortion on demand remains restricted in many countries, including Poland. As a result, many women resort to undergoing the procedure without medical supervision, putting themselves at risk of serious health consequences such as drug poisoning, excessive bleeding, and hypovolemia. Unfortunately, some abortions also lead to severe infections. Objective: This study aims to qualitatively identify key themes in abortion forums to analyze the issues faced by individuals. The forums were then quantitatively analyzed to determine which problems were most prevalent. Methods: The most popular abortion forums were identified. A preliminary thematic analysis was conducted for the qualitative phase, followed by a manual quantitative analysis. Two independent researchers reviewed forum posts, categorizing them into specific themes. Results: An analysis of 13,397 responses from 370 threads across 4 forums revealed “Abortion Process Progression” as the most discussed theme, highlighting a strong demand for information, emotional support, and medical guidance. The highest percentage of threads (162/886, 18.3%) focused on the need for mental support and the desire to have someone in contact during the abortion process. Concerns about the effectiveness of the termination also emerged as a significant topic, accounting for 83 of the 886 (9.4%) discussions. “Emotional and Psychological Aspects” and “Medical and Pharmacological Aspects” were also significant, highlighting the need for holistic care. Anxiety and fear related to the process were frequently discussed, accounting for 60 of the 886 (6.8%) responses. The issue of isolation and lack of support was also a common topic, appearing in 30 of the 886 (3.4%) threads. Notably, “Social and Ethical Perception” accounted for only 13 of the 886 (1.5%) responses and appeared in just 13 threads. Conclusions: This study highlights the critical need for information and support for women navigating abortion, particularly in regions where access is restricted. It emphasizes the importance of addressing the multifaceted challenges women face and calls for policy changes and strengthened support networks to improve the health and rights of women, as well as all those seeking gynecological care in abortion contexts. Further research is encouraged to refine and expand support strategies.

Evaluating a classifier's performance is critical for its successful application. This paper explores various metrics used for binary classification tasks, highlighting their strengths and limitations. Simple threshold metrics, such as Accuracy and Sensitivity, are efficient for binary data and a single cutoff point. However, their reliance on a single threshold and sensitivity to imbalanced data can be drawbacks. For more robust evaluation, ranking metrics such as Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves provide a threshold-agnostic approach, enabling comparison across different cutoff points. Additionally, probabilistic metrics like Brier Score and Log Loss assess the model's ability to predict class probabilities. The choice of metric depends on the specific classification problem and the characteristics of the data. When dealing with imbalanced data or complex decision-making processes, using multiple metrics is recommended to gain a comprehensive understanding of the model's performance. This paper emphasises the importance of understanding metric limitations and of selecting appropriate metrics for a specific classification task. By doing so, researchers and practitioners can ensure a more accurate and informative evaluation of their models, ultimately leading to the development of reliable tools for various applications.

BACKGROUND Abortion is one of the most common medical procedures worldwide. Despite this, access to abortion on demand remains restricted in many countries, including Poland. As a result, many women resort to undergoing the procedure without medical supervision, putting themselves at risk of serious health consequences such as drug poisoning, excessive bleeding, and hypovolemia. Unfortunately, some abortions also lead to severe infections. OBJECTIVE This study aims to qualitatively identify key themes in abortion forums to analyze the issues faced by individuals. The forums were then quantitatively analyzed to determine which problems were most prevalent. METHODS The most popular abortion forums were identified. A preliminary thematic analysis was conducted for the qualitative phase, followed by a manual quantitative analysis. Two independent researchers reviewed forum posts, categorizing them into specific themes. RESULTS An analysis of 13,397 responses from 370 threads across 4 forums revealed “Abortion Process Progression” as the most discussed theme, highlighting a strong demand for information, emotional support, and medical guidance. The highest percentage of threads (162/886, 18.3%) focused on the need for mental support and the desire to have someone in contact during the abortion process. Concerns about the effectiveness of the termination also emerged as a significant topic, accounting for 83 of the 886 (9.4%) discussions. “Emotional and Psychological Aspects” and “Medical and Pharmacological Aspects” were also significant, highlighting the need for holistic care. Anxiety and fear related to the process were frequently discussed, accounting for 60 of the 886 (6.8%) responses. The issue of isolation and lack of support was also a common topic, appearing in 30 of the 886 (3.4%) threads. Notably, “Social and Ethical Perception” accounted for only 13 of the 886 (1.5%) responses and appeared in just 13 threads. CONCLUSIONS This study highlights the critical need for information and support for women navigating abortion, particularly in regions where access is restricted. It emphasizes the importance of addressing the multifaceted challenges women face and calls for policy changes and strengthened support networks to improve the health and rights of women, as well as all those seeking gynecological care in abortion contexts. Further research is encouraged to refine and expand support strategies.