Efektivitas Penggunaan Skor Acute Physiology And Chronic Health Evaluation II (APACHE II) Dalam Memprediksi Mortalitas Pasien Di ICU RSD dr. Soebandi Jember

Abstract

Background: Mortality among patients admitted to the Intensive Care Unit (ICU) remains a major challenge in critical care due to the severity and complexity of patients' conditions. Accurate prognostic tools are needed to identify patients at high risk of death and support clinical decision-making. The Acute Physiology and Chronic Health Evaluation II (APACHE II) score is one of the most widely used scoring systems for assessing disease severity and predicting mortality in critically ill patients. However, its effectiveness in predicting mortality among ICU patients at RSD dr. Soebandi Jember has not been previously evaluated. Objective: To evaluate the effectiveness of the Acute Physiology and Chronic Health Evaluation II (APACHE II) score in predicting mortality among ICU patients at RSD dr. Soebandi Jember. Methods: This analytical observational study employed a retrospective design using secondary data obtained from ICU patients' medical records. A total of 111 patients who met the inclusion and exclusion criteria were included. Receiver Operating Characteristic (ROC) analysis was performed to evaluate the predictive performance of the APACHE II score. The Area Under the Curve (AUC) was used to assess predictive accuracy, while the optimal cut-off value was determined using the Youden Index. Results: The APACHE II score demonstrated excellent predictive performance with an AUC of 0.939 (95% CI: 0.893–0.985; p<0.001). The optimal cut-off value was ≥11.5, with a Youden Index of 0.721, resulting in a sensitivity of 92.1% and a specificity of 80.0%. In addition, patients with an APACHE II score ≥11.5 had 46.66 times higher odds of mortality than those with an APACHE II score <11.5. Conclusion: The APACHE II score demonstrated excellent performance in predicting mortality among ICU patients at RSD dr. Soebandi Jember. Therefore, APACHE II may serve as a reliable tool for mortality prediction, early risk stratification, and clinical decision-making in critically ill patients.