Prediksi Risiko Kematian Pada Pasien Covid-19 Menggunakan Xgboost Dan Random Forest

Yusuf, Muhammad Maulana (2022) Prediksi Risiko Kematian Pada Pasien Covid-19 Menggunakan Xgboost Dan Random Forest. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 05211840000076-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Pandemi COVID-19 telah menjadi tantangan kesehatan global yang signifikan sejak akhir 2019, dengan tingkat morbiditas dan mortalitas yang tinggi di berbagai negara. Identifikasi dini pasien dengan risiko kematian tinggi sangat penting untuk mengoptimalkan alokasi sumber daya medis dan meningkatkan peluang kelangsungan hidup pasien. Penelitian ini bertujuan untuk mengembangkan model prediksi risiko kematian pada pasien COVID-19 dengan menggunakan algoritma machine learning, yaitu XGBoost dan Random Forest. Dataset yang digunakan dalam penelitian ini mencakup data klinis dan demografis pasien COVID-19. Proses penelitian meliputi pembersihan data, penanganan data yang hilang, rekayasa fitur, dan pelatihan model. Hasil evaluasi menunjukkan bahwa kedua algoritma mampu memberikan performa yang baik dalam memprediksi risiko kematian. XGBoost menunjukkan performa yang sedikit lebih unggul dibandingkan dengan Random Forest dalam beberapa metrik evaluasi. Model yang dibangun diharapkan dapat membantu tenaga medis dalam pengambilan keputusan klinis yang lebih tepat dan cepat.
==============================================================================================================================
The COVID-19 pandemic has been a significant global health challenge since late 2019, with high morbidity and mortality rates in various countries. Early identification of patients at high risk of mortality is crucial for optimizing medical resource allocation and improving patient survival chances. This study aims to develop a mortality risk prediction model for COVID-19 patients using machine learning algorithms, specifically XGBoost and Random Forest. The dataset used in this study includes clinical and demographic data of COVID-19 patients. The research process includes data cleaning, handling missing data, feature engineering, and model training. Evaluation results show that both algorithms are capable of providing good performance in predicting mortality risk. XGBoost showed slightly superior performance compared to Random Forest in several evaluation metrics. The developed model is expected to assist medical professionals in making more precise and timely clinical decisions.

Item Type:	Thesis (Other)
Additional Information:	RSSI 519.542 Yus p-1 2022
Uncontrolled Keywords:	Prediksi Risiko Kematian. COVID-19. XGBoost. Random Forest.
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD30.213 Management information systems. Dashboards. Enterprise resource planning.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	Mr. Marsudiyana -
Date Deposited:	03 Jun 2026 08:31
Last Modified:	03 Jun 2026 08:31
URI:	http://repository.its.ac.id/id/eprint/133534

Actions (login required)

View Item