Development of a machine learning-based prediction model for hypothyroidism-associated delirium in elderly hypothyroid patients in the intensive care unit

Binbin Guan, Lijing Lin, Zhou Chen, Li Ma, Libin Liu · 2026

Read Development of a machine learning-based prediction model for hypothyroidism-associated delirium in elderly hypothyroid patients in the intensive care unit by Binbin Guan, Lijing Lin, Zhou Chen, Li Ma, Libin Liu (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/pmc-13463991.txt.

Description

Guan and colleagues built a machine-learning warning system in 2026 for delirium in intensive care. The target was elderly patients with underactive thyroids, a group at special risk for this sudden confusion. Two large American critical-care databases supplied the data. One trained and tested the model, and the other checked it independently. Candidate variables were sifted down to 13. Nine learning approaches were compared.

A gradient boosting model performed best. That method builds many small decision trees that correct each other's errors. It scored about 81 percent on the discrimination scale in internal testing. On the outside database it scored about 79. The strongest warning signs included consciousness and organ-failure scores. Sedative use, days in intensive care, blood oxygen, calcium, and average blood pressure mattered too. The team wrapped the model in a simple interface. It aims to flag at-risk patients earlier than bedside checks needing patients awake and talking.

Catalog record

CREATORBinbin Guan, Lijing Lin, Zhou Chen, Li Ma, Libin Liu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE50 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13463991

Browse the full library · About the Tower of Babel