Indexé dans
- Base de données des revues académiques
- Ouvrir la porte J
- Genamics JournalSeek
- JournalTOCs
- RechercheBible
- Répertoire des périodiques d'Ulrich
- Bibliothèque des revues électroniques
- RechercheRef
- Université Hamdard
- EBSCO AZ
- OCLC - WorldCat
- érudit
- Catalogue en ligne SWB
- Bibliothèque virtuelle de biologie (vifabio)
- Publions
- MIAR
- Fondation genevoise pour la formation et la recherche médicales
- Pub européen
- Google Scholar
Liens utiles
Partager cette page
Dépliant de journal
Revues en libre accès
- Agriculture et aquaculture
- Alimentation et nutrition
- Biochimie
- Bioinformatique et biologie des systèmes
- Business & Management
- Chimie
- Génétique et biologie moléculaire
- Immunologie & Microbiologie
- Ingénierie
- La science des matériaux
- Neurosciences & Psychologie
- Science générale
- Sciences cliniques
- Sciences environnementales
- Sciences médicales
- Sciences pharmaceutiques
- Sciences vétérinaires
- Soins infirmiers et soins de santé
Abstrait
Application of Machine Learning Techniques in Predicting of Breast Cancer Metastases Using Decision Tree Algorithm, in Sokoto Northwestern Nigeria
Abdulrahaman A. Musa, Usman Malami Aliyu
According to international agency for research on cancer, female breast cancer was the leading type of cancer worldwide in terms of the number of new cases (approximately 2.1 million) diagnosed in 2018.
Predicting outcome of a disease is a challenging task. Data mining techniques tends to simplify the prediction segment. Automated tools have made it possible to collect large volumes of medical data, which are made available to the medical research groups. This study aimed to apply machine learning algorithms using decision three classifier and descriptive statistics to evaluate the performance of the model in predicting the probability of cancer metastasis in patients that present late.
Materials and method: The breast cancer disease dataset has been taken from the department of Radiotherapy and Oncology of Usmanu Danfodiyo University Teaching Hospital, Sokoto state, Nigerian. Dataset has 259 instances and 10 attributes. The experimental results of this study used, decision three classifier in IMB SPSS (version 23) software environment. In the experiment, two classes were used and therefore a 2 × 2 confusion matrix was applied. Class 0=Not Metastasized, Class 1=Metastasized. We applied supervised machine learning approach in which dataset were divided into two classes that is training and testing using 10 fold cross validation.
Results: Shows that 259 instance of breast cancer, 218(84.2%) cases were not metastasized while 41(15.8%) cases were metastasized to the other region of the body. The overall accuracy of the model was found to be 87%, with the sensitivity of 88%, specificity 75% and the precision of 98%
Conclusion: Based on these findings, the machine learning algorism using decision three classifiers predicted that 87% of the tumor presented at stage IV, indicating that the tumour can spread to the other region of the body.