PREDIKSI JENIS PERAWATAN PADA PASIEN DI RUMAH SAKIT MENGGUNAKAN METODE ENSEMBLE LEARNING BERDASARKAN HASIL TES LABORATORIUM PASIEN

Adrian Dwi Adinata, . (2023) PREDIKSI JENIS PERAWATAN PADA PASIEN DI RUMAH SAKIT MENGGUNAKAN METODE ENSEMBLE LEARNING BERDASARKAN HASIL TES LABORATORIUM PASIEN. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (135kB)
[img] Text
AWAL.pdf
Download (1MB)
[img] Text
BAB 1.pdf
Download (176kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (617kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (311kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (4MB)
[img] Text
BAB 5.pdf
Download (161kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (119kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (103kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (5MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (5MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (536kB)

Abstract

Types of treatment at the hospital can be divided into inpatient and outpatient care. As part of a hospital automation system, a classification model is needed to predict the type of patient care to simplify and speed up decision making. The dataset used is taken from Kaggle which refers to Electronic Health Record Predicting collected from private hospitals in Indonesia. The dataset contains the results of the patient's blood laboratory tests. This study aims to build a machine learning model to predict whether patients should be classified under inpatient or outpatient treatment types. The method used in this study is Ensemble Learning, which combines logistic regression algorithms, k-nearest neighbors, support vector machines, decision trees, and naïve bayes. The modeling that will be applied uses Ensemble Vote and Ensemble Stacking to get the prediction model with the best accuracy. The classification model obtained will be evaluated using accuracy, precision, recall, and F1-Score values. The best accuracy results are obtained when using the Ensemble Stacking algorithm with an accuracy of 0.786. It can be concluded that applying the Ensemble Stacking Algorithm is proven to increase the accuracy for predicting the type of patient care in a hospital based on laboratory tests of the patient's blood compared to other algorithms used.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1910511038] [Pembimbing: Didit Widiyanto] [Penguji 1: Bayu Hananto] [Penguji 2: Rio Wirawan]
Uncontrolled Keywords: Hospitals, Predictions, Types of Treatment, Ensemble Learning
Subjects: L Education > L Education (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Adrian Dwi Adinata
Date Deposited: 02 Aug 2023 06:51
Last Modified: 02 Aug 2023 06:51
URI: http://repository.upnvj.ac.id/id/eprint/26127

Actions (login required)

View Item View Item