2018/08/24 by Charles C. Onu, Onu, Charles C.
Computer Science · Health Professions · Medicine · Neuroscience · #Applications (stat.AP) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Infant Health and Development #Neonatal and fetal brain pathology #Neuroscience of respiration and sleep #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1808.08299
openalex publication_date 2018/08/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Perinatal Asphyxia is one of the top three causes of infant mortality in\ndeveloping countries, resulting to the death of about 1.2 million newborns\nevery year. At its early stages, the presence of asphyxia cannot be\nconclusively determined visually or via physical examination, but by medical\ndiagnosis. In resource-poor settings, where skilled attendance at birth is a\nluxury, most cases only get detected when the damaging consequences begin to\nmanifest or worse still, after death of the affected infant. In this project,\nwe explored the approach of machine learning in developing a low-cost\ndiagnostic solution. We designed a support vector machine-based pattern\nrecognition system that models patterns in the cries of known asphyxiating\ninfants (and normal infants) and then uses the developed model for\nclassification of `new' infants as having asphyxia or not. Our prototype has\nbeen tested in a laboratory setting to give prediction accuracy of up to\n88.85%. If higher accuracies can be obtained, this research may be a key\ncontributor to the 4th Millennium Development Goal (MDG) of reducing mortality\nin under-five children.\n