Integrated machine learning for cause-of-death classification and postmortem interval prediction: Liver and kidney metabolomics from seawater-immersed rat cadavers

Jianghuan Lu, Yuzhao Xu, Siqi Chen, Zhiao Duan, Yixin Ma, Xiaoshi Qin, Yunchao Zhou, Shan Ha · 2026

Read Integrated machine learning for cause-of-death classification and postmortem interval prediction: Liver and kidney metabolomics from seawater-immersed rat cadavers by Jianghuan Lu, Yuzhao Xu, Siqi Chen, Zhiao Duan, Yixin Ma, Xiaoshi Qin, Yunchao Zhou, Shan Ha (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-0353958.txt.

Description

Lu and colleagues, in a 2026 forensic study, ask whether chemistry in the liver and kidneys can tell how a body died in seawater and how long it has been dead. Telling real drowning from a body placed in water after death is a classic hard problem. Sixty rats were assigned to seawater drowning or to being placed in seawater after death, and tissues were sampled across three days.

Thousands of small molecules in each tissue were measured, and machine learning models were trained on the patterns. Time since death dominated the chemistry, yet the models still separated the two causes of death with very high accuracy in both organs. Separate models guessed time since death within a few hours when tested on known time points, and less well on unseen ones. The authors present the approach as a promising forensic aid under controlled conditions, not yet a courtroom tool.

Catalog record

CREATORJianghuan Lu, Yuzhao Xu, Siqi Chen, Zhiao Duan, Yixin Ma, Xiaoshi Qin, Yunchao Zhou, Shan Ha
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE56476
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0353958

Browse the full library · About the Tower of Babel