Artificial Intelligence (AI) Based Techniques for Reducing Neonatal Mortality in Nigeria: A Descriptive Review

Abstract

Neonatal diseases are the disturbances of normal condition of the body, organs and abnormal function of newborns. They range from minor ailments like jaundice, to serious issues such as congenital heart defects encompassing a wide range of health conditions that affect newborns within the first 28 days of life. Thus, the first four weeks of life are critical and vulnerable period that require identification, accurate diagnosis, and management. The major causes of death of diseased newborns have been found to be late detection and misdiagnosis due to confusions in diagnosing diseases with similar symptoms. Hence, artificial intelligence (AI) techniques, especially those based on deep learning algorithms have emerged as important tool in handling very difficult tasks. In spite of its prospect, the potentials of AI are yet to be maximized in newborns’ health management. This paper explored the prospects of deep learning method in neonatal diseases classification. The study proposed a Long Short-Term Memory-Artificial Neural Network (LSTM-ANN) model, the model would be trained on a large dataset comprising of age, symptoms, laboratory test results, x-ray image results and diseases diagnosed.These would be obtained from the medical records of previously diagnosed and treated newborn. The technology will enhance accurate and timely diagnosis of neonatal diseases.