Model Survival dengan Frailty Univariate pada Perbaikan Pasien Gagal Ginjal Kronis (Studi Kasus: Pasien yang Menjalani Hemodialisis di Rumah Sakit Nur Hidayah Bantul)

Al Fatih, Nur Abdillah (2024) Model Survival dengan Frailty Univariate pada Perbaikan Pasien Gagal Ginjal Kronis (Studi Kasus: Pasien yang Menjalani Hemodialisis di Rumah Sakit Nur Hidayah Bantul). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003201136-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (1MB) | Request a copy

Abstract

Regresi Cox bertujuan mengetahui pengaruh variabel independen terhadap waktu survival suatu subjek penelitian sampai terjadinya peristiwa tertentu. Model frailty merupakan perluasan dari model Cox proportional hazard. Pendekatan frailty merupakan pemodelan statistik yang bertujuan untuk memperhitungkan heterogenitas yang disebabkan oleh kovariat yang tidak terukur. Penyakit ginjal kronis, yang mempengaruhi lebih dari 10% populasi global dengan 843,6 juta kasus pada tahun 2017, menjadi fokus penelitian. Hu-Care di RS Nurul Hidayah mengkategorikan kondisi psikospiritual pasien. Penelitian sebelumnya menggunakan regresi Cox proportional hazard untuk menilai pengaruh Hu-Care pada waktu kekambuhan pasien rawat inap yang mengalami gagal ginjal kronis tetapi tidak menangkap variasi tertentu. Oleh karena itu, penelitian ini mempertimbangkan extended Cox dengan frailty univariate untuk mengeksplorasi heterogenitas dari kovariat tak terukur. Frailty univariate dipilih karena model hanya mempertimbangkan satu variabel respon, yaitu waktu hingga pasien hemodialisis kembali rawat inap. Penelitian ini membandingkan model survival dengan frailty univariate dan model regresi Cox tanpa frailty. Model terbaik adalah model stratified Cox tanpa interaksi dengan dua variabel stratifikasi (riwayat hipertensi dan anemia) dengan AIC 120,64 dan hazard ratio untuk jenis kelamin sebesar 0,4313 pada taraf signifikansi 10%. Penambahan frailty univariate tidak mempengaruhi model stratified Cox, tetapi pada model regresi Cox dengan frailty univariate berdistribusi Gaussian variabel time-dependent, AIC menurun dari 184,29 menjadi 176,61.
============================================================
=================
Cox regression aims to determine the influence of independent variables on the survival time of a research subject until the occurrence of a certain event. The frailty model is an extension of the Cox hazard proportional model. The frailty approach is a statistical modeling that aims to account for heterogeneity caused by immeasurable covariance. Chronic kidney disease, which affects more than 10% of the global population with 843.6 million cases in 2017, is the focus of research. Hu-Care at Nurul Hidayah Hospital categorizes the patient's psychospiritual condition. Previous studies used Cox proportional hazard regression to assess the effect of Hu-Care on the time of recurrence of inpatients with chronic kidney failure but did not capture any specific variations. Therefore, this study considers extended Cox with frailty univariate to explore the heterogeneity of immeasurable covariate. Frailty univariate was chosen because the model only considered one response variable, namely the time until the hemodialysis patient returned to hospitalization. This study compares the survival model with frailty univariate and the Cox regression model without frailty. The best model was the stratified Cox model without interaction with two stratified variables (history of hypertension and anemia) with an AIC of 120.64 and a hazard ratio for sex of 0.4313 at a significance level of 10%. The addition of frailty univariate did not affect the stratified Cox model, but in the Cox regression model with the time-dependent variable Gaussian distributed frailty univariate, the AIC decreased from 184.29 to 176.61.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Choronic Kidney Disiase, Hu-Care, Cox Regression, Univariate Frailty,Gagal Ginjal Kronis, Hu-Care, Regresi Cox, Frailty Univariate
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) R Medicine > RC Internal medicine > RC901.7.H45 Hemodialysis.
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Nur Abdillah Al Fatih
Date Deposited:	09 Aug 2024 06:43
Last Modified:	09 Aug 2024 06:43
URI:	http://repository.its.ac.id/id/eprint/115085

Actions (login required)

View Item