Analisis Risiko Klaim Peserta BPJS Kesehatan berdasarkan Riwayat Diagnosis Penyakit dengan Model Coxph dan Pendekatan Bayesian Survival

Aryguna, Made Rucita (2026) Analisis Risiko Klaim Peserta BPJS Kesehatan berdasarkan Riwayat Diagnosis Penyakit dengan Model Coxph dan Pendekatan Bayesian Survival. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5006221100-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Analisis survival merupakan pendekatan yang dapat digunakan untuk memodelkan waktu hingga terjadinya klaim Fasilitas Kesehatan Rujukan Tingkat Lanjutan (FKRTL) berulang pada peserta BPJS Kesehatan. Penelitian ini bertujuan mengestimasi pola waktu survival, menganalisis pengaruh karakteristik peserta terhadap risiko klaim FKRTL berulang, serta menguji perbedaan waktu survival berdasarkan jenis hipertensi menurut klasifikasi ICD-10. Data yang digunakan merupakan data sekunder BPJS Kesehatan tahun 2024 sebanyak 3.592 peserta hipertensi dengan periode observasi selama 363 hari. Analisis dilakukan menggunakan metode Kaplan Meier, uji Log Rank, Cox Proportional Hazards, Stratified Cox Proportional Hazards, dan Bayesian Cox Proportional Hazards dengan algoritma Markov Chain Monte Carlo–No-U-Turn Sampler (MCMC-NUTS). Hasil penelitian menunjukkan bahwa median waktu survival keseluruhan adalah 105 hari, dengan 3.411 peserta (95%) mengalami klaim FKRTL berulang dan 181 peserta (5%) tersensor. Uji Log Rank menunjukkan bahwa jenis hipertensi, usia, status kepesertaan, wilayah domisili, dan jenis pelayanan berpengaruh signifikan terhadap waktu survival, sedangkan jenis kelamin dan jenis fasilitas kesehatan tidak signifikan. Model Stratified Cox PH memenuhi asumsi proportional hazards dengan wilayah domisili sebagai prediktor signifikan (HR = 0,7412), sementara pendekatan Bayesian Cox PH mampu mengestimasi seluruh kovariat secara simultan dengan estimasi yang lebih stabil sehingga dipilih sebagai model terbaik. Hasil penelitian ini diharapkan dapat mendukung pengembangan manajemen risiko serta perencanaan cadangan klaim BPJS Kesehatan.
=====================================================================================================================================
Survival analysis is an approach that can be used to model the time until the occurrence of recurrent Advanced Level Referral Health Facility (FKRTL) claims among BPJS Kesehatan participants. This study aims to estimate survival time patterns, analyze the influence of participant characteristics on the risk of recurrent FKRTL claims, and examine differences in survival time based on hypertension types classified by ICD-10. Secondary data from BPJS Kesehatan for 2024, comprising 3,592 hypertensive participants observed over a 363 day period, were utilized. The analysis employed the Kaplan-Meier method, Log-Rank test, Cox Proportional Hazards, Stratified Cox Proportional Hazards, and Bayesian Cox Proportional Hazards models using the Markov Chain Monte Carlo–No-U-Turn Sampler (MCMC-NUTS) algorithm. The results indicate an overall median survival time of 105 days, with 3,411 participants (95%) experiencing recurrent FKRTL claims and 181 participants (5%) being censored. The Log Rank test revealed that hypertension type, age, membership status, region of residence, and type of service significantly influenced survival time, whereas gender and type of health facility did not. The Stratified Cox PH model satisfied the proportional hazards assumption with the region of residence as a significant predictor (HR = 0.7412), while the Bayesian Cox PH approach capable of simultaneously estimating all covariates with greater stability was selected as the best model. These findings are expected to support risk management development and claim reserve planning for BPJS Kesehatan.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Analisis Survival, Bayesian Survival, Cox Proportional Hazards, Hipertensi, Risiko Klaim BPJS Kesehatan, Bayesian Survival, Cox Proportional Hazards, Hypertension, Risk of BPJS Health Claims, Survival Analysis
Subjects:	H Social Sciences > HG Finance > HG8054.5 Risk (Insurance) 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 Q Science > QA Mathematics > QA279.5 Bayesian statistical decision theory.
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis
Depositing User:	Made Rucita Aryguna
Date Deposited:	17 Jul 2026 04:27
Last Modified:	17 Jul 2026 04:29
URI:	http://repository.its.ac.id/id/eprint/135298

Actions (login required)

View Item