Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

pyAKI -- An Open Source Solution to Automated KDIGO classification

Christian Porschen, Jan Ernsting, Paul Brauckmann, Raphael Weiss, Till Würdemann, Hendrik Booke, Wida Amini, Ludwig Maidowski, Benjamin Risse, Tim Hahn, Thilo von Groote

TL;DR

This paper addresses the lack of open-source, standardized tools to apply KDIGO criteria to time-series data for AKI diagnosis. It introduces pyAKI, a Python-based pipeline with a flexible data model and multiple creatinine baseline methods to enable reproducible KDIGO annotation across datasets. Validation against expert labels using a MIMIC-IV demo subset shows strong agreement with clinicians and, in several aspects, competitive accuracy relative to human labeling. The work provides an openly accessible benchmark and tool for large-scale AKI annotation, facilitating reproducible research and AI-assisted decision support in critical care.

Abstract

Acute Kidney Injury (AKI) is a frequent complication in critically ill patients, affecting up to 50% of patients in the intensive care units. The lack of standardized and open-source tools for applying the Kidney Disease Improving Global Outcomes (KDIGO) criteria to time series data has a negative impact on workload and study quality. This project introduces pyAKI, an open-source pipeline addressing this gap by providing a comprehensive solution for consistent KDIGO criteria implementation. The pyAKI pipeline was developed and validated using a subset of the Medical Information Mart for Intensive Care (MIMIC)-IV database, a commonly used database in critical care research. We defined a standardized data model in order to ensure reproducibility. Validation against expert annotations demonstrated pyAKI's robust performance in implementing KDIGO criteria. Comparative analysis revealed its ability to surpass the quality of human labels. This work introduces pyAKI as an open-source solution for implementing the KDIGO criteria for AKI diagnosis using time series data with high accuracy and performance.

pyAKI -- An Open Source Solution to Automated KDIGO classification

TL;DR

This paper addresses the lack of open-source, standardized tools to apply KDIGO criteria to time-series data for AKI diagnosis. It introduces pyAKI, a Python-based pipeline with a flexible data model and multiple creatinine baseline methods to enable reproducible KDIGO annotation across datasets. Validation against expert labels using a MIMIC-IV demo subset shows strong agreement with clinicians and, in several aspects, competitive accuracy relative to human labeling. The work provides an openly accessible benchmark and tool for large-scale AKI annotation, facilitating reproducible research and AI-assisted decision support in critical care.

Abstract

Acute Kidney Injury (AKI) is a frequent complication in critically ill patients, affecting up to 50% of patients in the intensive care units. The lack of standardized and open-source tools for applying the Kidney Disease Improving Global Outcomes (KDIGO) criteria to time series data has a negative impact on workload and study quality. This project introduces pyAKI, an open-source pipeline addressing this gap by providing a comprehensive solution for consistent KDIGO criteria implementation. The pyAKI pipeline was developed and validated using a subset of the Medical Information Mart for Intensive Care (MIMIC)-IV database, a commonly used database in critical care research. We defined a standardized data model in order to ensure reproducibility. Validation against expert annotations demonstrated pyAKI's robust performance in implementing KDIGO criteria. Comparative analysis revealed its ability to surpass the quality of human labels. This work introduces pyAKI as an open-source solution for implementing the KDIGO criteria for AKI diagnosis using time series data with high accuracy and performance.
Paper Structure (16 sections, 2 equations, 3 figures, 2 tables)

This paper contains 16 sections, 2 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. aki Definition
  4. Creatinine Baseline Definition
  5. aki Data Model
  6. Software Development
  7. Validation Data Set
  8. Pipeline Validation
  9. Results
  10. Patient Cohort
  11. Accuracy
  12. aki Characteristics
  13. Misclassification
  14. Discussion
  15. Acknowledgements
  16. ...and 1 more sections

Figures (3)

  • Figure 1: pyAKI Data Model. PK = Primary Key, dt = Datetime, bool = Boolean Value, int = Integer Value, float = Floating Point Value
  • Figure 2: Workflow of validating the pyAKI pipeline.
  • Figure 3: Overall accuracy of human vs. pyAKI generated labels by classification method.