SURVIVAL ANALYSIS OF CORONARY HEART DISEASE PATIENTS USING THE KAPLAN-MEIER METHOD AND COX PROPORTIONAL HAZARDS REGRESSION (BRESLOW METHOD)

Abstract

This study aims to analyze the survival of CHD patients during hospitalization using survival analysis methods. The Kaplan–Meier method was applied to estimate survival probabilities, and group differences were tested using the log-rank test. Furthermore, the Cox proportional hazards model with the Breslow approach was used to assess the effect of clinical factors on survival, with assumptions verified using Schoenfeld residuals. By integrating nonparametric and semiparametric survival methods, this study provides a more comprehensive assessment of CHD patient survival compared with previous studies that relied on a single analytical approach. Data were collected retrospectively from 150 inpatients at Haji General Hospital, Medan, between 2021 and 2022, with 45 cases identified as censored. The Kaplan–Meier analysis revealed a progressive decline in survival probability during hospitalization, with the survival rate decreasing from 69.3% on the first day to 5.3% by day 40. The log-rank test results indicated that only hypertension had a statistically significant effect on patient survival (p 0.05). The Cox regression analysis confirmed these findings, showing that CHD patients with hypertension had more than three times higher risk of death (HR = 3.13; 95% CI: 2.06–4.78) compared to those without hypertension. These findings highlight hypertension as the most dominant risk factor reducing survival among CHD patients during hospitalization. This supports prioritizing early detection and intensive monitoring for hypertensive CHD patients to improve in-hospital clinical outcomes. However, this study has limitations due to its single-center retrospective design and the use of only four variables, leaving out other clinical factors that may influence survival outcomes.