Interpretation of Artificial Intelligence Algorithms in the Prediction of Sepsis

Abstract

Despite the rise of Artificial Intelligence (AI) algorithms and their applications in various fields, their utilizations in high-risk fields like healthcare and finance is limited because of the lack of interpretability of their inner workings. Some algorithms are interpretable, but not accurate, whereas some produce accurate results and not decipherable. Research is underway to explore the possibilities to interrogate an AI system, and ask why it makes certain decisions. This paper aims to investigate the decision-making process by AI algorithms in the prediction of sepsis based on patients’ clinical records.We were ranked 59 in the PhysioNet/Computing in Cardiology Challenge 2019 and the utility score obtained on the full test set is 0.131, and our team name was ARUL.