Dichotomous Radial Basis Tanimoto Network to Predict Delivery Mode in Maternal Care Domain

• Published in: International journal of information communication technologies and human development Vol. 13; no. 4; pp. 92 - 104
• Main Authors: Thangavel, Balasubramanian, Kannan, Kavitha
• Format: Journal Article
• Language: English
• Published: Hershey IGI Global 01.10.2021
• Subjects: Accuracy; Births; Cesarean section; Childbirth & labor; Information communication; Machine learning; Medical research; Neural networks; Performance prediction; Pregnancy; Regression analysis; Similarity measures; Utilization; Vagina
• ISSN: 1935-5661; 1935-567X
• DOI: 10.4018/IJICTHD.2021100104

Pregnancy delivery mode prediction is an important one for doctors to provide timely treatment. Some research works have been developed for pregnancy delivery mode prediction using machine learning techniques. But the accuracy of prediction was not improved with less time. In order to perform accurate delivery prediction, dichotomous radial basis Tanimoto network prediction (DRBTNP) method is proposed to enhance the process of pregnancy delivery mode prediction with higher accuracy. The proposed DRBTNP method comprises different types of layers for performing delivery mode prediction with less time and space utilization. Experimental evaluation is performed with different factors such as prediction accuracy, prediction time, and space utilization with respect to patient data. The observed result shows that the presented DRBTNP method increases the prediction accuracy up to 9% with the reduction of prediction time and space utilization up to 20% and 19% over the state-of-the-art methods.