This paper introduces pyAKI, an open-source tool designed to standardize the implementation of Kidney Disease Improving Global Outcomes (KDIGO) criteria to time series data for acute kidney injury diagnosis. It was developed and validated using a subset of the Medical Information Mart for Intensive Care (MIMIC)-IV database. The study demonstrated that the tool could surpass the quality of human labels and could be a vital resource for clinical decision support systems.

 

Publication date: 24 Jan 2024
Project Page: https://arxiv.org/abs/2401.12930
Paper: https://arxiv.org/pdf/2401.12930

Post Views: 219