Background/Objectives: Breast cancer is the most common cancer in women worldwide, requiring strategic efforts to reduce its mortality. This study aimed to develop a predictive classification model for breast cancer mortality using real-world data, including various clinical features. Methods: A total of 11,286 patients with breast cancer from the National Cancer Center were included in this study. The mortality rate of the total sample was approximately 6.2%. Propensity score matching was used to reduce bias. Several machine learning models, including extreme gradient boosting, were applied to 31 clinical features. To enhance model interpretability, we used the SHapley Additive exPlanations method. ML analyses were also performed on the samples, excluding patients who developed other cancers after breast cancer. Results: Among the ML models, the XGB model exhibited the highest discriminatory power, with an area under the curve of 0.8722 and a specificity of 0.9472. Key predictors of the mortality classification model included occurrence in other organs, age at diagnosis, N stage, T stage, curative radiation treatment, and Ki-67(%). Even after excluding patients who developed other cancers after breast cancer, the XGB model remained the best-performing, with an AUC of 0.8518 and a specificity of 0.9766. Additionally, the top predictors from SHAP were similar to the results for the overall sample. Conclusions: Our models provided excellent predictions of breast cancer mortality using real-world data from South Korea. Explainable artificial intelligence, such as SHAP, validated the clinical applicability and interpretability of these models.
31 August 2025 in Osong Public Health and Research Perspectives
Objectives: Severe trauma remains a leading cause of death in the Republic of Korea. In response, regional trauma centers were established in 2012. This study evaluated the impact of direct prehospital transport to trauma centers on in-hospital mortality among patients with severe trauma using the national trauma registry.Methods: This nationwide observational study utilized data from the Korean community-based trauma registry between 2016 and 2020. Patients with an injury severity score >15 who were directly transported from the prehospital setting were included. Variables analyzed encompassed demographics, injury mechanism, transport time, hospital level, and outcomes. The primary outcome was in-hospital mortality. Both logistic regression and decision tree models were employed.Results: A total of 24,567 patients were included. Overall mortality decreased by 5.2% during the study period. Patients transported to level 1 or 2 trauma centers had a lower mortality rate (23.6%) compared to those transported to level 3 or 4 hospitals (28.0%). The proportion of direct transports to high-level centers increased from 46.7% to 64.1% between 2016 and 2020. Despite longer transport times, patients transported to high-level institutions exhibited improved survival, particularly when transport exceeded 30 minutes, suggesting that hospital selection may be more critical than minimizing transport time.Conclusion: Direct transport to high-level trauma centers improves survival among patients with severe trauma, even when transport times are prolonged. These findings support the importance of a well-organized trauma system that emphasizes hospital capability in prehospital triage decisions.
Age-related macular degeneration (AMD) is a leading cause of irreversible visual impairment among older adults. Despite the accumulation of evidence linkin