Jamaluddin, M. (2021) Klasifikasi Diagnosa Pasien Berdasarkan Rekam Medis Elektronik Menggunakan Text Mining Dan Support Vector Machine. Masters thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 07111850067004-Master_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
07111850067004-Master_Thesis.pdf Restricted to Repository staff only Download (2MB) | Request a copy |
|
Text
07111850067004-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (5MB) | Request a copy |
Abstract
Rekam Medis Elektronik (RME) adalah elemen penting dari teknologi informasi di bidang kesehatan. RME adalah catatan elektronik yang berisi informasi terkait kesehatan pasien yang dapat dibuat dan dikelola oleh dokter dan staf yang berwenang di organisasi pelayanan kesehatan. RME adalah kerangka kerja untuk menentukan diagnosis dan pengobatan kepada pasien. RME memiliki format teks bebas dan tidak terstruktur yang membuat lebih sulit untuk menggali informasi tersembunyi sebagai sistem pendukung keputusan.
Dalam thesis ini, dilakukan penelitian untuk klasifikasi dari RME berbahasa Indonesia sebagai Clinical Decision Support System (CDSS) dalam mengklasifikasikan diagnosis pasien menggunakan Term Frequency-Inverse Document Frequency (Tf-Idf) untuk ekstraksi fitur dan Support Vector Machine (SVM) untuk metode klasifikasi. Diagnosa yang diklasifikasikan dalam thesis ini adalah tuberkulosis, kanker, diabetes mellitus, hipertensi, dan gagal ginjal yang memiliki angka prevalensi tinggi di Indonesia.
Model dibangun dengan mempertimbangkan fungsi kernel SVM serta penggunaan stopword removal atau tanpa stopword removal. Akurasi tertinggi didapatkan pada kernel RBF menggunakan stopword removal dan model n-gram (1-3) dengan nilai akurasi 91,71%. Hasil penelitian menunjukkan bahwa metode Tf-Idf dan SVM dapat digunakan secara efektif untuk memprediksi diagnosis.
============================================================
=========================================
Electronic Medical Record (EMR) is an important element of information technology in health sector. EMR is an electronic record containing health-related information on an patient that can be created and managed by authorized physician and staff in a health service organization. EMR is a framework for determining diagnosis and treatment. EMR has free text and unstructured format which makes it more difficult to extract the hidden information as a decision support system.
This study performs classification from Indonesian EMR for clinical decision support system (CDSS) in classifying patient diagnosis using Term Frequency-Inverse Document Frequency (Tf-Idf) for feature extraction and Support Vector Machine (SVM) for classifier method. The focus diagnoses classified in this paper are tuberculosis, cancer, diabetes mellitus, hypertension, and kidney failure which have high prevalence rates in Indonesia.
The model is built by considering the kernel function and the use of stopword removal or without stopword removal. The highest accuracy is obtained in the RBF kernel with stopword removal and n-gram (1-3) by an accuracy value of 91.71%. The result showed that Tf-Idf and SVM method could be used effectively to predict diagnosis.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Rekam Medis Elektronik, Text mining , Support Vector Machine, Electronic Medical Record |
| Subjects: | Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis |
| Depositing User: | M. Jamaluddin M. Jamaluddin |
| Date Deposited: | 13 Aug 2021 10:43 |
| Last Modified: | 13 Aug 2021 10:43 |
| URI: | http://repository.its.ac.id/id/eprint/86313 |
Actions (login required)
 |
View Item |