Hybridized neural network and decision tree based classifier for prognostic decision making in breast cancers

• Published in: Soft computing (Berlin, Germany) Vol. 24; no. 11; pp. 7947 - 7953
• Main Authors: Suresh, A., Udendhran, R., Balamurgan, M.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2020; Springer Nature B.V
• Subjects: Algorithms; Archives & records; Artificial Intelligence; Autonomous cars; Breast cancer; Calcification; Communication; Computational Intelligence; Control; Data mining; Decision making; Decision trees; Disease; Electronic health records; Engineering; Face recognition; Focus; Health care; Industrial robots; Information technology; Mammography; Mathematical Logic and Foundations; Mechatronics; Medical personnel; Mortality; Neural networks; Professionals; Radial basis function; Robotics; Support vector machines; Breast cancer; Soft computing; Decision trees; Radial basis function neural network
• ISSN: 1432-7643; 1433-7479
• DOI: 10.1007/s00500-019-04066-4

Artificial intelligence techniques and algorithms are applied at various fields such as face recognition, self-driving cars, industrial robots and health care. These real-world conundrums are solved employing artificial intelligence since it focuses on narrow tasks, and AI-driven tasks are very reliable and efficient because of its automated problem-solving techniques. Breast cancer is considered as the most common type of cancer among women. The well-known technique for detection of breast cancer is mammography which can diagnosis anomalies and determine cancerous cells. However, in the present breast cancer screenings, the retrospective studies reveal that approximately 20–40% of breast cancer cases are missed by radiologists. The main objective of the proposed algorithm is to exactly forecast the misclassified malignant cancers employing radial basis function network and decision tree. In order to obtain the effective classification algorithm, this work is compared with three widely employed algorithms, namely K -nearest neighbors, support vector machine and Naive Bayes algorithm, and the proposed algorithm achieves a high accuracy.