Explainable AI Enabled Infant Mortality Prediction Based on Neonatal Sepsis  

作　　者：Priti Shaw Kaustubh Pachpor Suresh Sankaranarayanan 

机构地区：[1]Barclays Bank,Bund Garden Road,Pune,411001,India [2]University of Illinois,60607,Illinois,USA [3]SRM Institute of Science and Technology,Chennai,603203,India

出　　处：《Computer Systems Science & Engineering》2023年第1期311-325,共15页计算机系统科学与工程（英文）

摘　　要：Neonatal sepsis is the third most common cause of neonatal mortality and a serious public health problem,especially in developing countries.There have been researches on human sepsis,vaccine response,and immunity.Also,machine learning methodologies were used for predicting infant mortality based on certain features like age,birth weight,gestational weeks,and Appearance,Pulse,Grimace,Activity and Respiration(APGAR)score.Sepsis,which is considered the most determining condition towards infant mortality,has never been considered for mortality prediction.So,we have deployed a deep neural model which is the state of art and performed a comparative analysis of machine learning models to predict the mortality among infants based on the most important features including sepsis.Also,for assessing the prediction reliability of deep neural model which is a black box,Explainable AI models like Dalex and Lime have been deployed.This would help any non-technical personnel like doctors and practitioners to understand and accordingly make decisions.

关 键 词：APGAR SEPSIS explainable AI machine learning 

分 类 号：R722.1[医药卫生—儿科] TP18[医药卫生—临床医学]