Predicting life expectancy of lung cancer patients after thoracic surgery using SMOTE and machine learning approaches

. Lung cancer is a life-threatening condition characterized by the uncontrolled growth and spread of abnormal cells in the lungs. Thoracic surgery is a commonly employed diagnostic and treatment procedure for lung cancer. The objective of this study is to utilize machine learning techniques to predi...

Full description

Bibliographic Details
Main Authors: SELLY ANASTASSIA AMELLIA KHARIS, ARMAN HAQQI ANNA ZILI
Format: Article
Language:English
Published: Universitas Syiah Kuala, Faculty of Mathematics and Natural Science 2023-10-01
Series:Jurnal Natural
Subjects:
Online Access:https://jurnal.usk.ac.id/natural/article/view/29144
_version_ 1797226059293261824
author SELLY ANASTASSIA AMELLIA KHARIS
ARMAN HAQQI ANNA ZILI
author_facet SELLY ANASTASSIA AMELLIA KHARIS
ARMAN HAQQI ANNA ZILI
author_sort SELLY ANASTASSIA AMELLIA KHARIS
collection DOAJ
description . Lung cancer is a life-threatening condition characterized by the uncontrolled growth and spread of abnormal cells in the lungs. Thoracic surgery is a commonly employed diagnostic and treatment procedure for lung cancer. The objective of this study is to utilize machine learning techniques to predict the life expectancy of lung cancer patients one year after thoraric surgery. The study utilizes the Thoraric  Surgery Data Set, consisting of 454 data, with 385 data representing surviving patients and 69 data representing patients who passed away. Due to an imbalance in the data, the Synthetic Minority Oversampling Technique (SMOTE) process is applied to balance the dataset. Multiple machine learning algorithms, including Random Forest (RF), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM), are employed for prediction. Validation is performed using 5-fold cross validation, repeated three times. The results indicate that the KNN model achieves the highest mean accuracy of 84.80% before the SMOTE process, although all models exhibit a low mean F1-score. Following the SMOTE process, the RF model attains  the highest mean accuracy of 79.52%, while the KNN model demonstrates  the highest mean F1-score of 26.54%. This research contributes valuable insights to clinicians in making informed decisions and improving patient outcomes.
first_indexed 2024-03-11T14:18:46Z
format Article
id doaj.art-f7485bec64fb4a8aaa7edc39eda7e997
institution Directory Open Access Journal
issn 1411-8513
2541-4062
language English
last_indexed 2024-04-24T14:18:53Z
publishDate 2023-10-01
publisher Universitas Syiah Kuala, Faculty of Mathematics and Natural Science
record_format Article
series Jurnal Natural
spelling doaj.art-f7485bec64fb4a8aaa7edc39eda7e9972024-04-03T08:07:37ZengUniversitas Syiah Kuala, Faculty of Mathematics and Natural ScienceJurnal Natural1411-85132541-40622023-10-0123315216110.24815/jn.v23i3.2914416836Predicting life expectancy of lung cancer patients after thoracic surgery using SMOTE and machine learning approachesSELLY ANASTASSIA AMELLIA KHARIS0ARMAN HAQQI ANNA ZILI1Faculty of Science and Technology Universitas TerbukaFaculty of Mathematics and Science Universitas Indonesia. Lung cancer is a life-threatening condition characterized by the uncontrolled growth and spread of abnormal cells in the lungs. Thoracic surgery is a commonly employed diagnostic and treatment procedure for lung cancer. The objective of this study is to utilize machine learning techniques to predict the life expectancy of lung cancer patients one year after thoraric surgery. The study utilizes the Thoraric  Surgery Data Set, consisting of 454 data, with 385 data representing surviving patients and 69 data representing patients who passed away. Due to an imbalance in the data, the Synthetic Minority Oversampling Technique (SMOTE) process is applied to balance the dataset. Multiple machine learning algorithms, including Random Forest (RF), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM), are employed for prediction. Validation is performed using 5-fold cross validation, repeated three times. The results indicate that the KNN model achieves the highest mean accuracy of 84.80% before the SMOTE process, although all models exhibit a low mean F1-score. Following the SMOTE process, the RF model attains  the highest mean accuracy of 79.52%, while the KNN model demonstrates  the highest mean F1-score of 26.54%. This research contributes valuable insights to clinicians in making informed decisions and improving patient outcomes.https://jurnal.usk.ac.id/natural/article/view/29144machine learning, lung cancer, smote, thoracic surgery
spellingShingle SELLY ANASTASSIA AMELLIA KHARIS
ARMAN HAQQI ANNA ZILI
Predicting life expectancy of lung cancer patients after thoracic surgery using SMOTE and machine learning approaches
Jurnal Natural
machine learning, lung cancer, smote, thoracic surgery
title Predicting life expectancy of lung cancer patients after thoracic surgery using SMOTE and machine learning approaches
title_full Predicting life expectancy of lung cancer patients after thoracic surgery using SMOTE and machine learning approaches
title_fullStr Predicting life expectancy of lung cancer patients after thoracic surgery using SMOTE and machine learning approaches
title_full_unstemmed Predicting life expectancy of lung cancer patients after thoracic surgery using SMOTE and machine learning approaches
title_short Predicting life expectancy of lung cancer patients after thoracic surgery using SMOTE and machine learning approaches
title_sort predicting life expectancy of lung cancer patients after thoracic surgery using smote and machine learning approaches
topic machine learning, lung cancer, smote, thoracic surgery
url https://jurnal.usk.ac.id/natural/article/view/29144
work_keys_str_mv AT sellyanastassiaamelliakharis predictinglifeexpectancyoflungcancerpatientsafterthoracicsurgeryusingsmoteandmachinelearningapproaches
AT armanhaqqiannazili predictinglifeexpectancyoflungcancerpatientsafterthoracicsurgeryusingsmoteandmachinelearningapproaches