Maternal circulating lipid metabolic heterogeneity in preeclampsia: machine learning identifies clinically distinct subtypes

Jianfeng Gan, Li Cao, Jiejie Shao, Weirong Gu, Rong Hu, Yu Xiong, Yinan Wang, Huanqiang Zhao, Qiongjie Zhou, Xiaotian Li · 2026

Read Maternal circulating lipid metabolic heterogeneity in preeclampsia: machine learning identifies clinically distinct subtypes by Jianfeng Gan, Li Cao, Jiejie Shao, Weirong Gu, Rong Hu, Yu Xiong, Yinan Wang, Huanqiang Zhao, Qiongjie Zhou, Xiaotian Li (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/PMC13563807.txt.

Description

Jianfeng Gan and nine colleagues let a clustering algorithm sort preeclampsia, the dangerous blood-pressure disorder of pregnancy, into types based on blood fats. The condition varies bafflingly between women, and the placenta's handling of lipids may drive some of that variety. Their 2026 study reviewed 1,124 affected women treated between 2018 and 2022. Four standard third-trimester lipid measures fed an unsupervised k-means method, which settled on four subtypes: low metabolic, high HDL, high triglyceride, and high metabolic.

Surprises followed. The high triglyceride group, despite the heaviest mothers, recorded the lowest preterm birth rate at 3.1 percent and the least low birth weight. The high metabolic group carried the worst blood pressure and protein leakage. The authors argue that fat-based sorting exposes real biological variety inside one diagnosis, and that treatment trials should stop averaging across it.

Catalog record

CREATORJianfeng Gan, Li Cao, Jiejie Shao, Weirong Gu, Rong Hu, Yu Xiong, Yinan Wang, Huanqiang Zhao, Qiongjie Zhou, Xiaotian Li
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE40451
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13563807

Browse the full library · About the Tower of Babel