Assessing the reproducibility of Fourier-transform mid-infrared–derived biomarker clusters across lactations and their direct prediction from milk spectra
S. Franceschini, S. Czaplicki, N. Nickmilder, J. Leblois, C. Grelet, N. Gengler, H. Soyeurt · 2026
Read Assessing the reproducibility of Fourier-transform mid-infrared–derived biomarker clusters across lactations and their direct prediction from milk spectra by S. Franceschini, S. Czaplicki, N. Nickmilder, J. Leblois, C. Grelet, N. Gengler, H. Soyeurt (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/PMC13542450.txt.
Description
In 2026, S Franceschini and colleagues published a study checking whether health patterns detected in milk spectra hold up across a cow's life. Milk recording already uses infrared spectroscopy to estimate fine milk composition cheaply. Earlier work on first-lactation Holstein cows grouped cows into clusters by predicted milk biomarkers; here the unsupervised method was repeated five times across three lactations and extended to older, multiparous cows.
Patterns matched between younger and older cows only for one purpose: detecting metabolic trouble. Other cluster patterns proved less stable across lactations. To make the approach usable on farms, the team also built a model that predicts cluster membership directly from a milk spectrum, reaching 92 percent accuracy, close to the earlier study. Reliable metabolic screening from routine milk samples could help farmers catch energy problems in their herds earlier.
Catalog record
| CREATOR | S. Franceschini, S. Czaplicki, N. Nickmilder, J. Leblois, C. Grelet, N. Gengler, H. Soyeurt |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 23309 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |