PREDIKSI DURASI RAWAT INAP PASIEN ICU MENGGUNAKAN DEEP LEARNING

ANGGRAINI, FENNY and Firdaus, Firdaus and Tutuko, Bambang (2024) PREDIKSI DURASI RAWAT INAP PASIEN ICU MENGGUNAKAN DEEP LEARNING. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_56201_09011182025019.pdf] Text
RAMA_56201_09011182025019.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (3MB) | Request a copy
[thumbnail of RAMA_56201_09011182025019_TURNITIN.pdf] Text
RAMA_56201_09011182025019_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[thumbnail of RAMA_56201_09011182025019_0221017801_0012016003_01_front_ref.pdf] Text
RAMA_56201_09011182025019_0221017801_0012016003_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (793kB)
[thumbnail of RAMA_56201_09011182025019_0221017801_0012016003_02.pdf] Text
RAMA_56201_09011182025019_0221017801_0012016003_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (473kB) | Request a copy
[thumbnail of RAMA_56201_09011182025019_0221017801_0012016003_03.pdf] Text
RAMA_56201_09011182025019_0221017801_0012016003_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (415kB) | Request a copy
[thumbnail of RAMA_56201_09011182025019_0221017801_0012016003_04.pdf] Text
RAMA_56201_09011182025019_0221017801_0012016003_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_56201_09011182025019_0221017801_0012016003_05.pdf] Text
RAMA_56201_09011182025019_0221017801_0012016003_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (181kB) | Request a copy
[thumbnail of RAMA_56201_09011182025019_0221017801_0012016003_06_ref.pdf] Text
RAMA_56201_09011182025019_0221017801_0012016003_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (193kB) | Request a copy
[thumbnail of RAMA_56201_09011182025019_0221017801_0012016003_07_lamp.pdf] Text
RAMA_56201_09011182025019_0221017801_0012016003_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (878kB) | Request a copy

Abstract

Memprediksi durasi lama rawat inap pada pasien merupakan aspek krusial bagi rumah sakit untuk meningkatkan kualitas pelayanan medis dan manajemen rumah sakit. Prediksi ini membantu pasien dalam menyiapkan kebutuhan yang diperlukan serta memungkinkan rumah sakit untuk mempersiapkan pelayanan medis yang tepat. Dalam penelitian ini, dilakukan prediksi durasi rawat inap pasien ICU menggunakan pendekatan deep learning dengan tujuan untuk menemukan metode terbaik dalam memprediksi durasi rawat inap. Prediksi ini menggunakan database MIMIC-IV dengan metode imputasi interpolasi linear dan XU-Netl. Prediksi dilakukan dengan membandingkan beberapa metode deep learning yaitu Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Stacked Long Short-Term Memory, Bidirectional Long Short Term Memory (Bi-LSTM), dan one-dimensional (1D) multi-scale convolutional neural network (1D-MSNet). Hasil penelitian menunjukkan bahwa arsitektur GRU merupakan metode terbaik dengan nilai akurasi dan AUC sebesar 66% pada data dengan imputasi interpolasi linear. Secara keseluruhan, arsitektur GRU memberikan performa terbaik dalam memprediksi durasi rawat inap pasien ICU menggunakan data yang diimputasi dengan interpolasi linear.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Durasi rawat inap, prediksi, imputasi, deep learning
Subjects: Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions: 09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Fenny Anggraini
Date Deposited: 22 Jul 2024 07:08
Last Modified: 22 Jul 2024 07:08
URI: http://repository.unsri.ac.id/id/eprint/152681

Actions (login required)

View Item View Item