Klasifikasi Stadium Kanker Tiroid Dengan Menggunakan Machine Learning (Studi Kasus: Pasien Kanker Tiroid Di Rumah Sakit Onkologi Surabaya)

Aprilia, Nanda Gita (2021) Klasifikasi Stadium Kanker Tiroid Dengan Menggunakan Machine Learning (Studi Kasus: Pasien Kanker Tiroid Di Rumah Sakit Onkologi Surabaya). Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
06211740000019-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (1MB) | Request a copy
[img] Text
06211740000019-Undergraduate_Thesis.pdf
Restricted to Repository staff only

Download (1MB) | Request a copy

Abstract

Kanker hingga saat ini masih menjadi masalah kesehatan dunia, termasuk di Indonesia. The International Agency for Research on Cancer (IARC) mengestimasi secara global, 1 dari 8 laki-laki dan 1 dari 11 perempuan meninggal karena kanker. Berdasarkan data Globocan tahun 2020, kanker tiroid merupakan kanker peringkat 5 tertinggi yang diderita oleh perempuan di seluruh dunia. Kanker tiroid menempati urutan ke-9 dari 10 kanker terbanyak di Indonesia, serta angkanya mengalami peningkatan tiap tahunnya. Pengklasifikasian stadium kanker tiroid penting dilakukan karena memengaruhi perawatan yang akan diberikan untuk kelangsungan hidup pasien. Tujuan dari penelitian ini adalah melakukan klasifikasi stadium kanker tiroid menggunakan metode Naïve Bayes dan k-Nearest Neighbor (k-NN). Data yang digunakan adalah data rekam medis pasien kanker tiroid di Rumah Sakit Onkologi Surabaya pada bulan Januari 2008 hingga Februari 2019 yang terdiri dari 141 pasien. Hasil klasifikasi dengan metode Naïve Bayes menghasilkan nilai AUC sebesar 0,7185 untuk data training dan 0,7326 untuk data testing, sedangkan metode k-NN dengan k = 7 menghasilkan nilai AUC sebesar 0,7405 untuk data training dan 0,8102 untuk data testing. Metode terbaik dipilih berdasarkan nilai AUC terbesar, sehingga metode k-NN dengan k = 7 dipilih sebagai metode terbaik untuk mengklasifikasikan stadium kanker tiroid pasien di Rumah Sakit Onkologi Surabaya. ===================================================================================================== Cancer is still a world health problem, including in Indonesia. The International Agency for Research on Cancer (IARC) estimates that globally, 1 in 8 men and 1 in 11 women die from cancer. Based on Globocan data in 2020, thyroid cancer is the fifth highest cancer suffered by women worldwide. Thyroid cancer ranks 9 out of 10 most cancers in Indonesia and the number is increasing every year. Thyroid cancer stage classification is important because it affects the treatment that will be given for the survival of the patient. The purpose of this study was to classify thyroid cancer stage using the Naïve Bayes and k-Nearest Neighbor (k-NN) methods. The data used was the medical record data of thyroid cancer patients at the Surabaya Oncology Hospital from January 2008 to February 2019, which consisted of 141 patients. The results of the classification using the Naïve Bayes method produced an AUC value of 0.7061 for training data and 0.7122 for testing data, while the k-NN method with k = 3 produced an AUC value of 0.7418 for training data and 0.7332 for testing data. The best method was chosen based on the largest AUC value, so the k-NN method with k = 3 was chosen as the best method for classifying the stage of thyroid cancer patients at the Surabaya Oncology Hospital.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Kanker Tiroid, Klasifikasi, k-Nearest Neighbor, Naïve Bayes, Classification, k-Nearest Neighbor, Naïve Bayes, Thyroid Cancer.
Subjects: H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects )
Q Science > Q Science (General) > Q325.5 Machine learning.
Q Science > QR Microbiology > QR 201.T84 Tumors. Cancer
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Nanda Gita Aprilia
Date Deposited: 27 Aug 2021 03:04
Last Modified: 27 Aug 2021 03:04
URI: https://repository.its.ac.id/id/eprint/90209

Actions (login required)

View Item View Item