Implementasi Pengukuran Kemiripan Penyakit untuk Atlas of Human Infectious Diseases dengan Menggunakan Metode Pengukuran BIOSSES

Fortuna, Dian Nizzah (2024) Implementasi Pengukuran Kemiripan Penyakit untuk Atlas of Human Infectious Diseases dengan Menggunakan Metode Pengukuran BIOSSES. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5026201002-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy

Abstract

Dalam 30 tahun terakhir, telah muncul lebih dari 30 penyakit infeksi emerging (PIE) di dunia dan ini menuntut banyak pihak di tingkat internasional untuk mencegah dan menangani PIE secara lebih baik. Salah satu sumber pengetahuan mengenai PIE yang menyerang manusia adalah buku Atlas of Human Infectious Diseases (AHID). Informasi yang terdapat di dalam AHID telah distrukturisasi dan diringkas dalam bentuk kamus berbasis web oleh penelitian sebelumnya namun tidak ada visualisasi yang merepresentasikan kemiripan antar penyakit. Analisis kemiripan penyakit bersifat penting dalam memahami petogenesis penyakit kompleks, pencegahan dini, diagnosis penyakit utama, bahkan pengembangan obat baru. Penelitian sebelumnya telah melakukan analisis kemiripan teks biomedis menggunakan metode BIOSSES dan menghasilkan Pearson Correlation Coefficient (PCC) sebesar 0.836. Sesuai dengan data AHID yang berisikan teks biomedis, maka dalam penelitian ini digunakan metode BIOSSES untuk mengukur kemiripan penyakit berdasarkan atribut epidemiology, clinical findings, agent, trnasmission, incubation period, dan diagnostic tests. Model ini menghasilkan skor kemiripan teks dengan nilai PCC sebesar 0.3630 dan Median Absolute Deviation (MAD) sebesar 0.1158. Hasil pengukuran skor kemiripan disajikan dalam bentuk human disease network dan tersedia pada aplikasi web bersama dengan AHID Dictionary.
==================================================================================================================================
In the last 30 years, more than 30 emerging infectious diseases (EIDs) have emerged in the world and this requires many parties at the international level to prevent and treat EIDs better. One source of knowledge about EIDs that attacks humans is the book Atlas of Human Infectious Diseases (AHID). The information contained in AHID has been structured and summarized by previous research in the form of a web-based dictionary but there is no visualization that represents similarities between diseases. Disease similarity analysis is important in understanding the pathogenesis of complex diseases, early prevention, diagnosis of major diseases, and even the development of new drugs. Previous research has carried out similarity analysis of biomedical texts using the BIOSSES method and produced a Pearson Correlation Coefficient (PCC) of 0.836. In accordance with AHID data which contains biomedical text, in this study the BIOSSES method was used to measure disease similarity based on the attributes of epidemiology, clinical findings, agent, transmission, incubation period and diagnostic tests. This model produces a text similarity score with a PCC value of 0.3630 and a Median Absolute Deviation (MAD) of 0.1158. The results of the similarity score measurement are presented in the form of a human disease network and are available on the web application together with the AHID Dictionary.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	AHID, BIOSSES, Kemiripan Semantik, Teks Biomedis
Subjects:	Q Science Q Science > Q Science (General) Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	Dian Nizzah Fortuna
Date Deposited:	30 Jul 2024 07:48
Last Modified:	30 Jul 2024 07:48
URI:	http://repository.its.ac.id/id/eprint/110466

Actions (login required)

View Item