Journal article
Early diagnosis of thyroid cancer diseases using computational intelligence techniques: A case study of a Saudi Arabian dataset

Research Areas
Currently no objects available

Publication Details
Author list: Sunday O. Olatunji, Sarah Alotaibi, Ebtisam Almutairi, Zainab Alrabae, Yasmeen Almajid, Rahaf Altabee, Mona Altassan, Mohammed Imran Basheer Ahmed, Mehwash Farooqui, and Jamal Alhiyafi
Publisher: Elsevier: 12 months
Publication year: 2021
Journal: Computers in Biology and Medicine
Volume number: 131
Issue number: April 2021
Start page: 1
End page: 9
Number of pages: 9
ISSN: 0010-4825
Web of Science ID: 000634812300001
PubMed ID: 33647831
Scopus ID: 85101587639
eISSN: 1879-0534

In recent times, researchers have noticed that chronic diseases have become more common. In the Kingdom of Saudi Arabia, the number of patients with thyroid cancer (TC) has become a concern, necessitating a proactive system that can help cut down the incidence of this disease, where the system can assist in early interventions to prevent or cure the disease. In this paper, we introduce our work developing machine learning-based tools that can serve as early warning systems by detecting TC at very early stages (pre-symptomatic stage). In addition, we aimed at obtaining the greatest possible accuracy while using fewer features. It must be noted that while there have been past efforts to use machine learning in predicting TC, this is the first attempt using a Saudi Arabian dataset as well as targeting diagnosis in the pre-symptomatic stage (pre-emptive diagnosis). The techniques used in this work include random forest (RF), artificial neural network (ANN), support vector machine (SVM), and naïve Bayes (NB), each of which was selected for their unique capabilities. The highest accuracy rate obtained was 90.91% with the RF technique, while SVM, ANN, and NB achieved 84.09%, 88.64%, and 81.82% accuracy, respectively. These levels were obtained by using only seven features out of an available 15. Considering the pattern of the obtained results, it is clear that the RF technique is better and, hence, recommended for this specific problem.

Currently no objects available

Currently no objects available

Currently no objects available

Last updated on 2021-10-06 at 13:34