A mapping study of ensemble classification methods in lung cancer decision support systems
- PDF / 2,186,573 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 30 Downloads / 150 Views
REVIEW ARTICLE
A mapping study of ensemble classification methods in lung cancer decision support systems Mohamed Hosni 1 & Ginés García-Mateos 2 José Luis Fernández-Alemán 2
&
Juan M. Carrillo-de-Gea 2
&
Ali Idri 1
&
Received: 5 January 2020 / Accepted: 25 June 2020 # International Federation for Medical and Biological Engineering 2020
Abstract Achieving a high level of classification accuracy in medical datasets is a capital need for researchers to provide effective decision systems to assist doctors in work. In many domains of artificial intelligence, ensemble classification methods are able to improve the performance of single classifiers. This paper reports the state of the art of ensemble classification methods in lung cancer detection. We have performed a systematic mapping study to identify the most interesting papers concerning this topic. A total of 65 papers published between 2000 and 2018 were selected after an automatic search in four digital libraries and a careful selection process. As a result, it was observed that diagnosis was the task most commonly studied; homogeneous ensembles and decision trees were the most frequently adopted for constructing ensembles; and the majority voting rule was the predominant combination rule. Few studies considered the parameter tuning of the techniques used. These findings open several perspectives for researchers to enhance lung cancer research by addressing the identified gaps, such as investigating different classification methods, proposing other heterogeneous ensemble methods, and using new combination rules. Keywords Lung cancer . Ensemble methods . Classification . Decision support systems . Machine learning
1 Introduction Lung cancer is the most commonly diagnosed type of cancer and the leading cause of cancer death worldwide. In fact, according to recent statistics published by the World Health Organization (WHO), it was responsible for 1.76 million deaths in 2018, and 2.09 million people were diagnosed with this disease [81]. Lung cancer is a term used to refer to the abnormal growth of cells inside the lung. There are two different categories of lung cancer [14, 34]: small cell lung cancer, which is a highly malignant tumor, and non-small cell lung cancer, which, in turn, can be divided into three categories: adenocarcinoma, squamous cell carcinoma, and large cell carcinoma. Several factors can increase the risk of developing lung cancer: smoking, exposure to radon, alcohol, and physical inactivity are the greatest risk factors for * Ginés García-Mateos [email protected] 1
Software Project Management Research Team, ENSIAS, Mohammed V University in Rabat, Rabat, Morocco
2
Department of Informatics and Systems, Faculty of Computer Science, University of Murcia, Murcia, Spain
this disease [14, 34, 81]. Early detection of lung cancer can contribute significantly to reduce disease mortality, since at an early stage, cancer can respond effectively to treatment, and therefore, many lives can be saved [75, 81]. Early detection is, however, still far fro
Data Loading...
