TY - GEN
T1 - Mobile-Bayesian diagnostic system for childhood infectious diseases
AU - Iheme, Precious
AU - Omoregbe, Nicholas
AU - Misra, Sanjay
AU - Adeloye, Davies
AU - Adewumi, Adewole
PY - 2017/1/1
Y1 - 2017/1/1
N2 - About 5.9 million children under the age of 5 died in 2015, Preterm birth, delivery complications and infections source a great number of neonatal deaths. the Sustainable Development goals (SDGs) 3.2 is to end preventable deaths of newborns and children under 5 years of age, with a target to reduce neonatal mortality to at least 12 per 1,000 live births and under-5 mortality to at least as low as 25 per 1,000 live births in all countries. However quality and accessible healthcare service is essential to achieve this goal whereas most undeveloped and developing countries still have poor access to quality healthcare. with the emergences on mobile computing and telemedicine, this work provide diagnostics alternative for childhood infectious diseases using Naïve Bayesian classier which has been proven to be efficient in handling uncertainty as regards learning of incomplete data. In this research, sample data was collected from hospitals to model a pediatric system using Naïve Bayes classifier, which produce a 70% accuracy level suitable for a decision support system. The model was also integrated into a SMS platform to enable ease of usage.
AB - About 5.9 million children under the age of 5 died in 2015, Preterm birth, delivery complications and infections source a great number of neonatal deaths. the Sustainable Development goals (SDGs) 3.2 is to end preventable deaths of newborns and children under 5 years of age, with a target to reduce neonatal mortality to at least 12 per 1,000 live births and under-5 mortality to at least as low as 25 per 1,000 live births in all countries. However quality and accessible healthcare service is essential to achieve this goal whereas most undeveloped and developing countries still have poor access to quality healthcare. with the emergences on mobile computing and telemedicine, this work provide diagnostics alternative for childhood infectious diseases using Naïve Bayesian classier which has been proven to be efficient in handling uncertainty as regards learning of incomplete data. In this research, sample data was collected from hospitals to model a pediatric system using Naïve Bayes classifier, which produce a 70% accuracy level suitable for a decision support system. The model was also integrated into a SMS platform to enable ease of usage.
KW - Childhood diseases
KW - Diagnostic system
KW - Machine learning
KW - Mobile computing
KW - Naïve Bayesian
KW - SMS-based system
UR - http://www.scopus.com/inward/record.url?scp=85026757173&partnerID=8YFLogxK
U2 - 10.3233/978-1-61499-773-3-109
DO - 10.3233/978-1-61499-773-3-109
M3 - Conference contribution
AN - SCOPUS:85026757173
T3 - Frontiers in Artificial Intelligence and Applications
SP - 109
EP - 118
BT - Proceedings of the 8th International Conference on Applications of Digital Information and Web Technologies, ICADIWT 2017
A2 - Rodriguez Jorge, Ricardo
A2 - Almazo Perez, Diego Moises
A2 - Pichappan, Pit
A2 - Pichappan, Pit
A2 - Pichappan, Pit
A2 - Mizera-Pietraszko, Jolanta
PB - IOS Press
T2 - 8th International Conference on Applications of Digital Information and Web Technologies, ICADIWT 2017
Y2 - 29 March 2017 through 31 March 2017
ER -