Acute kidney injury severity in ICU patients: Developing and evaluating a data-driven analysis of clinical covariates using machine learning

Mohammad Fathi, Nader Markazi Moghaddam, Mahdis Fathi, Mohammadreza Hajiesmaeili, Navid Nooraei, Nasser Malekpour Alamdari, Sanaz Zargar Balaye Jame, Hamed Markazi Moghadam · 2026

Read Acute kidney injury severity in ICU patients: Developing and evaluating a data-driven analysis of clinical covariates using machine learning by Mohammad Fathi, Nader Markazi Moghaddam, Mahdis Fathi, Mohammadreza Hajiesmaeili, Navid Nooraei, Nasser Malekpour Alamdari, Sanaz Zargar Balaye Jame, Hamed Markazi Moghadam (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0352314.txt.

Description

Mohammad Fathi and seven colleagues train a machine-learning model to grade how badly intensive care patients' kidneys are failing, in this 2026 PLOS ONE study. Standard staging uses two measures and misses much of the clinical picture. Working with records of more than two thousand patients from a large critical-care database, the team fed dozens of routine variables into a gradient-boosted model and asked which ones carried the signal.

The model sorted patients into the correct severity stage about four times in five, performing best at the extremes — no injury and the most severe injury. Pre-existing kidney disease, sepsis, a liver pigment, and several blood-pressure drugs topped the predictor list. Such models could flag deteriorating kidneys hours before the standard thresholds trip.

Catalog record

CREATORMohammad Fathi, Nader Markazi Moghaddam, Mahdis Fathi, Mohammadreza Hajiesmaeili, Navid Nooraei, Nasser Malekpour Alamdari, Sanaz Zargar Balaye Jame, Hamed Markazi Moghadam
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE34285
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0352314

Browse the full library · About the Tower of Babel