Extended Survival Model Pada Ketahanan Penderita Hipertensi Sampai Mengalami Hypertensive Heart Disease

Alrifa'i, Ahmad (2026) Extended Survival Model Pada Ketahanan Penderita Hipertensi Sampai Mengalami Hypertensive Heart Disease. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003221108-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Hipertensi merupakan salah satu penyakit kronis dengan prevalensi tinggi dan menjadi faktor risiko utama berbagai komplikasi kardiovaskular, salah satunya Hypertensive Heart Disease (HHD). Risiko terjadinya HHD dipengaruhi oleh berbagai faktor klinis dan berkembang secara bertahap dalam rentang waktu tertentu sehingga analisis survival relevan untuk digunakan. Model Cox Proportional Hazards (Cox PH) merupakan metode yang umum diterapkan dalam analisis survival, namun model ini mensyaratkan terpenuhinya asumsi proportional hazards yang dalam praktik sering kali tidak terpenuhi. Penelitian ini bertujuan untuk mendeskripsikan karakteristik pasien hipertensi, memeriksa pemenuhan asumsi proportional hazards, serta menerapkan extended survival model yang mencakup regresi Cox terstratifikasi dan model dengan time-dependent covariates pada data ketahanan penderita hipertensi hingga mengalami HHD. Data yang digunakan merupakan data sekunder rekam medis 328 pasien hipertensi rawat jalan di RSUD Haji Jawa Timur sepanjang tahun 2024, dengan 71 pasien mengalami HHD dan 257 pasien tersensor. Variabel yang dianalisis meliputi usia, jenis kelamin, tekanan darah sistolik, tekanan darah diastolik, diabetes mellitus, dan riwayat keluarga hipertensi. Analisis dilakukan menggunakan estimasi Kaplan-Meier, uji log-rank, regresi Cox PH, pengujian asumsi PH menggunakan residual Schoenfeld, regresi Cox terstratifikasi, serta regresi Cox time-dependent covariates. Hasil pengujian menunjukkan bahwa tekanan darah diastolik tidak memenuhi asumsi proportional hazards sehingga digunakan sebagai variabel stratifikasi. Hasil uji likelihood ratio menunjukkan tidak terdapat interaksi yang signifikan antara variabel stratifikasi dan kovariat dalam model. Selain itu, pendekatan time-dependent covariates menggunakan fungsi logaritmik waktu dan fungsi Heaviside menunjukkan bahwa efek tekanan darah diastolik tidak berubah secara signifikan terhadap waktu pengamatan. Berdasarkan nilai Akaike Information Criterion (AIC), model Cox terstratifikasi menghasilkan nilai AIC terkecil sebesar 674,838 sehingga dipilih sebagai model terbaik. Hasil pemodelan menunjukkan bahwa tekanan darah sistolik ≥140 mmHg merupakan faktor yang berpengaruh signifikan terhadap ketahanan penderita hipertensi hingga mengalami HHD dengan hazard ratio sebesar 1,718.
=========================================================================================================================================
Hypertension is one of the most prevalent chronic diseases and a major risk factor for various cardiovascular complications, including Hypertensive Heart Disease (HHD). The risk of developing HHD is influenced by several clinical factors and progresses gradually over time, making survival analysis an appropriate analytical approach. The Cox Proportional Hazards (Cox PH) model is widely used in survival analysis; however, it requires the proportional hazards assumption to be satisfied, which is often violated in practice. This study aimed to describe the characteristics of hypertensive patients, assess the proportional hazards assumption, and apply an extended survival model, including Stratified Cox Regression and Time-Dependent Covariate Models, to analyze the survival time of hypertensive patients until the occurrence of HHD. The study utilized secondary data obtained from the medical records of 328 outpatient hypertensive patients at RSUD Haji East Java from January 1 to December 31, 2024. Among these patients, 71 experienced HHD events, while 257 observations were right-censored. The variables analyzed included age, sex, systolic blood pressure, diastolic blood pressure, diabetes mellitus, and family history of hypertension. The analysis was conducted using Kaplan–Meier estimation, the log-rank test, Cox Proportional Hazards regression, assessment of the proportional hazards assumption using Schoenfeld residuals, Stratified Cox regression, and Cox regression with time-dependent covariates. The results indicated that diastolic blood pressure violated the proportional hazards assumption and was therefore treated as a stratification variable. The likelihood ratio test showed no significant interaction between the stratification variable and the covariates. Furthermore, the time-dependent covariate approach using logarithmic time and Heaviside functions indicated that the effect of diastolic blood pressure did not change significantly over the observation period. Based on the Akaike Information Criterion (AIC), the Stratified Cox model produced the smallest AIC value of 674.838 and was therefore selected as the best model. The final model showed that systolic blood pressure ≥140 mmHg was a significant factor affecting the survival time of hypertensive patients until the occurrence of HHD, with a hazard ratio of 1.718.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Analisis Survival, Cox Proportional Hazards, Extended Survival Model, Hipertensi, Hypertensive Heart Disease. Survival Analysis, Cox Proportional Hazards, Extended Survival Model, Hypertension, Hypertensive Heart Disease.
Subjects:	Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) R Medicine > R Medicine (General) > R853.S7 Survival analysis (Biometry)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Ahmad Alrifa'i
Date Deposited:	04 Aug 2026 08:47
Last Modified:	04 Aug 2026 08:47
URI:	http://repository.its.ac.id/id/eprint/143574

Actions (login required)

View Item