<![CDATA[The development of information technology in healthcare opens new opportunities to improve continuous patient monitoring. A major challenge is alert fatigue, where medical personnel are overwhelmed by excessive notifications, reducing concentration, work efficiency, and potentially compromising patient safety. This study presents a proof-of-concept application of the Decision Tree algorithm to analyze alert triggering factors in patient monitoring systems. The dataset is a synthetic health monitoring dataset from Kaggle, containing 10,000 entries with vital parameters including blood pressure, heart rate, oxygen saturation, and glucose levels, designed with deterministic logical relationships between threshold indicators and alert outcomes. The imbalanced dataset (73.67% alert triggered, 26.33% no alert) was intentionally not processed using imbalanced learning techniques to demonstrate Decision Tree's capability in processing structured health data and producing interpretable classifications. The research methodology included data preprocessing, exploratory data analysis, data splitting (90% training, 10% testing), GridSearchCV optimization, and performance evaluation. Results showed perfect metrics (100% accuracy, precision, recall, F1-score), reflecting the deterministic nature of the synthetic dataset rather than real-world clinical complexity. Feature importance analysis identified blood pressure as the most dominant variable, followed by heart rate and glucose levels. This study demonstrates Decision Tree's interpretability and feature importance analysis capabilities in health data contexts, establishing a methodological framework that requires validation on real clinical Electronic Health Record (EHR) data for practical application in reducing alert fatigue and supporting informed clinical decisions.]]>
Copyrights © 2025
