Analisis Survival Competing Risk pada Model Subdistribution Fine-Gray dengan Metode Maximum Partial Likelihood Estimation (Studi Kasus: Pasien COVID-19 di Rumah Sakit Islam Sultan Agung, Semarang)

Ainurrochmah, Alifta (2021) Analisis Survival Competing Risk pada Model Subdistribution Fine-Gray dengan Metode Maximum Partial Likelihood Estimation (Studi Kasus: Pasien COVID-19 di Rumah Sakit Islam Sultan Agung, Semarang). Masters thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06211950015003-Master_Thesis.pdf] Text
06211950015003-Master_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (3MB) | Request a copy

Abstract

Pada analisis survival, terdapat situasi dimana suatu individu dapat mengalami lebih dari satu jenis event dan terjadinya event tersebut menghambat terjadinya jenis event yang lain. Keadaan tersebut disebut competing risk atau kejadian bersaing. Metode Cumulative Incidence Function (CIF) diusulkan sebagai solusi untuk menyelesaikan kejadian competing risk. Model regresi Cox juga dimodifikasi untuk memungkinkan adanya competing risk. Model tersebut dinamakan model subdistribution Fine-Gray dengan menggunakan Maximum Partial Likelihood Estimation (MPLE). Corona Virus Disease-19 (COVID-19) adalah penyakit dengan gejala infeksi saluran pernafasan yang disebabkan oleh virus corona yang ditemukan pada tahun 2019. Adanya komorbiditas pada pasien terinfeksi COVID-19 dapat disebut competing risk. Penelitian ini bertujuan menaksir parameter dan statistik uji model subdistribution Fine-Gray pada kasus competing risk kematian pasien terinfeksi COVID-19 yang memiliki komorbiditas di Rumah Sakit Islam Sultan Agung, Semarang. Berdasarkan hasil analisis, hasil model Subdistribution Fine-Gray dengan taraf signifikansi 5% disimpulkan bahwa terdapat penurunan risiko kematian pasien terinfeksi COVID-19 dengan status event of interest sebesar 0,95 setiap pasien mengalami penambahan 1 satuan variabel saturasi oksigen. Pada pasien terinfeksi COVID-19 dengan status CR-1, terdapat penurunan risiko kematian pasien sebesar 0,91 setiap pasien mengalami penambahan 1 satuan variabel saturasi oksigen. Variabel yang mempengaruhi kematian pasien terinfeksi COVID-19 dengan status CR-2 adalah usia. Berdasarkan subdistribution hazard ratio dapat diketahui bahwa terdapat peningkatan risiko kematian pasien sebesar 1,09 setiap pasien mengalami penambahan 1 satuan variabel usia. Kemudian variabel yang mempengaruhi kematian pasien terinfeksi COVID-19 dengan status CR-3 adalah suhu tubuh dan frekuensi nafas. Berdasarkan subdistribution hazard ratio dapat diketahui bahwa terdapat peningkatan risiko kematian pasien sebesar 1,74 setiap pasien mengalami penambahan 1 satuan variabel suhu tubuh dan terdapat peningkatan risiko kematian pasien sebesar 1,03 setiap pasien mengalami penambahan 1 satuan pada variabel frekuensi nafas.
======================================================================================================
In survival analysis, there is a situation where an individual can experience more than one type of event and the occurrence of these events prevents the occurrence of other types of events. This situation is called competing risk. The Cumulative Incidence Function (CIF) method is proposed as a solution to solve competing risk events. The Cox regression model is also modified to allow for competing risk. This model is called the Fine-Gray hazard subdistribution model using the Maximum Partial Likelihood Estimation (MPLE). Corona Virus Disease-19 (COVID-19) is a disease with symptoms of a respiratory system infection caused by a corona virus that was discovered in 2019. The comorbidities deaths caused by being infected with COVID-19 can be called a competing risk. This research was conducted to estimate the parameters and statistics test of the Fine-Gray subdistribution model in cases of competing risk of death in COVID-19 patients who has comorbidities at Sultan Agung Islamic Hospital, Semarang. Based on the results of the analysis, the Fine-Gray Subdistribution model used significance level of 5% can be concluded that there is a decrease in the risk of death of COVID-19 patients who has event of interest status by 0,95 for each patient experiencing the addition of 1 unit of oxygen saturation variable. In COVID-19 patients who has CR-1 status, there is a decreased risk of patient death by 0,91 for each patient experiencing an additional 1 unit of oxygen saturation variable. The variable that affects the mortality of COVID-19 patients who has CR-2 status is age. Based on the subdistribution hazard ratio, it can be seen that there is an increase in the risk of patient death by 1,09 each patient experiencing an additional 1 unit of age variable. Then the variables that affect the mortality of COVID-19 patients who has CR-3 status are body temperature and respiratory frequency. Based on the subdistribution hazard ratio, it can be seen that there is an increase in the risk of patient death by 1,74 each patient experiencing an addition of 1 unit of body temperature variable and there is an increase in the risk of death of the patient by 1,03 each patient experiencing an addition of 1 unit in the respiratory frequency variable.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Analisis Survival, Competing Risk, Model Subdistribution Fine-Gray, Corona Virus Disease-19 Survival Analysis, Competing Risk, Subdistribution Fine-Gray Models, Corona Virus Disease-19
Subjects: Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression
R Medicine > R Medicine (General) > R853.S7 Survival analysis (Biometry)
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49101-(S2) Master Thesis
Depositing User: Alifta Ainurrochmah
Date Deposited: 09 Sep 2021 07:52
Last Modified: 09 Sep 2021 07:52
URI: http://repository.its.ac.id/id/eprint/91895

Actions (login required)

View Item View Item