Model Bayesian Cox Proportional Hazards dan klasifikasi Naive Bayes untuk analisis faktor risiko dan prediksi status mortalitas pasien kanker payudara

Nurhayasih, Neneng (2026) Model Bayesian Cox Proportional Hazards dan klasifikasi Naive Bayes untuk analisis faktor risiko dan prediksi status mortalitas pasien kanker payudara. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text
1_cover.pdf

Download (330kB) | Preview
[img]
Preview
Text
2_abstrak.pdf

Download (92kB) | Preview
[img]
Preview
Text
3_skbebasplagiarism.pdf

Download (237kB) | Preview
[img]
Preview
Text
4_daftarisi.pdf

Download (104kB) | Preview
[img]
Preview
Text
5_bab1.pdf

Download (2MB) | Preview
[img] Text
6_bab2.pdf
Restricted to Registered users only

Download (396kB) | Request a copy
[img] Text
7_bab3.pdf
Restricted to Registered users only

Download (4MB) | Request a copy
[img] Text
8_bab4.pdf
Restricted to Registered users only

Download (6MB) | Request a copy
[img] Text
9_bab5.pdf
Restricted to Registered users only

Download (135kB) | Request a copy
[img] Text
10_daftarpustaka.pdf
Restricted to Registered users only

Download (80kB) | Request a copy
[img] Text
11_lampiran.pdf
Restricted to Repository staff only

Download (231kB) | Request a copy

Abstract

INDONESIA: Analisis survival menggunakan model Cox Proportional Hazards (CPH) tidak memerlukan asumsi distribusi tertentu pada baseline hazard. Penelitian ini menggunakan pendekatan Bayesian pada model CPH untuk mengidentifikasi faktor yang berpengaruh terhadap waktu survival pasien kanker payudara serta memanfaatkan variabel signifikan dalam klasifikasi status mortalitas menggunakan Naive Bayes. Estimasi parameter dilakukan menggunakan algoritma Metropolis Hastings melalui pendekatan Markov Chain Monte Carlo (MCMC). Data yang digunakan merupakan data sekunder pasien kanker payudara dari Kaggle dengan variabel usia, stadium tumor, histologi, status HER2, dan jenis operasi. Hasil penelitian menunjukkan bahwa stadium tumor, histologi, dan jenis operasi memiliki kategori yang berpengaruh signifikan terhadap waktu survival, sedangkan usia dan status HER2 tidak menunjukkan pengaruh signifikan. Klasifikasi Naive Bayes dilakukan dalam dua skenario, yaitu menggunakan variabel signifikan berdasarkan model Bayesian Cox Proportional Hazards dan seluruh variabel prediktor. Hasil perbandingan menunjukkan bahwa skenario menggunakan variabel signifikan memberikan kinerja klasifikasi yang lebih baik dibandingkan skenario menggunakan seluruh variabel prediktor. ENGLISH: Survival analysis using the Cox Proportional Hazards (CPH) model does not require a specific distributional assumption for the baseline hazard. This study applies a Bayesian approach to the CPH model to identify factors affecting the survival time of breast cancer patients and utilizes the significant variables for mortality status classification using Naive Bayes. Parameter estimation is performed using the Metropolis-Hastings algorithm within the Markov Chain Monte Carlo (MCMC) approach. The study uses secondary breast cancer patient data obtained from Kaggle, with age, tumor stage, histology, HER2 status, and type of surgery as predictor variables. The results show that tumor stage, histology, and type of surgery have categories that significantly affect survival time, while age and HER2 status do not show significant effects. The Naive Bayes classification is conducted using two scenarios: significant variables identified by the Bayesian Cox Proportional Hazards model and all predictor variables. The comparison results show that the scenario using significant variables provides better classification performance than the scenario using all predictor variables.

Item Type: Thesis (Sarjana)
Uncontrolled Keywords: Analisis survival; Bayesian Cox Proportional Hazards; Metropolis Hastings; Naive Bayes, kanker payudara
Subjects: Mathematics
Applied mathematics
Applied mathematics > Statistical Mathematics
Divisions: Fakultas Sains dan Teknologi > Program Studi Matematika
Depositing User: Neneng Nurhayasih
Date Deposited: 25 Aug 2026 15:52
Last Modified: 25 Aug 2026 15:52
URI: https://digilib.uinsgd.ac.id/id/eprint/139435

Actions (login required)

View Item View Item