A tabular prior-data fitted network-based prediction model integrating ferritin and total iron-binding capacity for 30-day all-cause mortality in critically ill cancer patients

Lin-Lin Liu, Lei Han, Zuo-Lin Xiang · 2026

Read A tabular prior-data fitted network-based prediction model integrating ferritin and total iron-binding capacity for 30-day all-cause mortality in critically ill cancer patients by Lin-Lin Liu, Lei Han, Zuo-Lin Xiang (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/PMC13425414.txt.

Description

Liu and colleagues built a 2026 prediction model for thirty-day death risk in critically ill cancer patients, adding two iron-related blood measures, ferritin and total iron-binding capacity. They trained the model on 1,137 intensive care patients from one large United States database and checked it on a second database. Their method uses a neural network pre-trained to learn from small tables of data.

About twenty-six percent of the training patients died within thirty days. High ferritin and low iron-binding capacity each predicted death on their own, while plain serum iron did not. The model beat eight rival machine learning methods, with strong accuracy at home and solid accuracy abroad. Blood cell counts, a waste product called lactate, and ferritin drove its predictions most. The authors offer it as an explainable risk tool for intensive care teams.

Catalog record

CREATORLin-Lin Liu, Lei Han, Zuo-Lin Xiang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE42 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13425414

Browse the full library · About the Tower of Babel