Construction and Evaluation of a Ketosis Prediction Model Based on Milk MIR Spectra and Feature Wavenumber Selection in Dairy Cows.
7 affiliations
- 1Frontiers Science Center for Animal Breeding and Sustainable Production, Huazhong Agricultural University, Ministry of Education, Wuhan 430070, China.
- 2Henan Provincial International Joint Laboratory for Dairy Health Farming, Henan Dairy Herd Improvement Center, Zhengzhou 450046, China.
- 3Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China.
- 4College of Animal Science and Technology, China Agricultural University, Beijing 100193, China.
- 5Dairy Association of China, Beijing 100193, China.
- 6Henan Seed Industry Development Center, Zhengzhou 450046, China.
- 7National Animal Husbandry Service, Beijing 100125, China.
Abstract
Ketosis is a common metabolic disorder in dairy cows and occurs mainly during early lactation. Blood β-hydroxybutyrate (BHB) is widely used for diagnosis, but large-scale testing is limited by sampling requirements and cost. We therefore studied lactating Holstein cows from 12 large-scale dairy farms in central China. Milk samples, milk composition traits, and milk mid-infrared (MIR) spectra were collected through the Dairy Herd Improvement (DHI) testing system from April 2019 to December 2022, and ketosis diagnoses were obtained from farm health records; samples were labeled as healthy or ketotic based on the temporal relationship between diagnosis and sampling. A total of 2206 samples were used to build the calibration and validation datasets, in which five feature wavenumber selection methods and five machine learning algorithms were compared. Ketotic cows had a higher milk fat percentage and fat-to-protein ratio and a lower protein and lactose percentage (p < 0.01). The best combination was PLS-DA based on 104 CARS-selected wavenumbers, which achieved a sensitivity of 0.83, a specificity of 0.79, a balanced accuracy of 0.81 and an area under the receiver operating characteristic curve (AUC) of 0.88 in validation. MIR spectroscopy combined with machine learning can therefore support large-scale ketosis phenotyping within the DHI system.
Related
- An integrated fuzzy multi-criteria decision making and mixed-integer linear programming optimization framework for project risk assessment and response strategy selection: A case study of a liquefied petroleum gas pipeline construction project
- Breath Acetone Sensor for Subclinical Ketosis Detection in Dairy Cows
- Wavenumber-Aware Deep Learning for Robust Analysis of Raman Spectra
- Systematic evaluation of LLM-based zero-shot model construction in chemistry and materials science: predictive performance and response reliability
- Green MW/US-Assisted Construction of Pyrano[2,3-b]pyridines and Pyrazolo[3,4-d]pyrimidinones: Pathway Control and Antibacterial Evaluation.
BibTeX
@article{ren2026construction,
title = {{Construction and Evaluation of a Ketosis Prediction Model Based on Milk MIR Spectra and Feature Wavenumber Selection in Dairy Cows.}},
author = {Xiaoli Ren and Zhuo Yang and Aote Han and Yikai Fan and Yi Zhang and Shaohu Chen and Zhen Zhang and Lei Yan and Zheng Cao and Wenjiao Liu and Xiaofeng Huang and Dongwei Wang and Guixiang Zhang and Qingxia Yan and Shujun Zhang},
journal = {Animals : an open access journal from MDPI},
year = {2026},
month = oct,
doi = {10.3390/ani16203196},
url = {https://europepmc.org/article/MED/42939127},
note = {CC BY},
}
RIS
TY - JOUR
TI - Construction and Evaluation of a Ketosis Prediction Model Based on Milk MIR Spectra and Feature Wavenumber Selection in Dairy Cows.
AU - Xiaoli Ren
AU - Zhuo Yang
AU - Aote Han
AU - Yikai Fan
AU - Yi Zhang
AU - Shaohu Chen
AU - Zhen Zhang
AU - Lei Yan
AU - Zheng Cao
AU - Wenjiao Liu
AU - Xiaofeng Huang
AU - Dongwei Wang
AU - Guixiang Zhang
AU - Qingxia Yan
AU - Shujun Zhang
PY - 2026
DA - 2026/10/12
JO - Animals : an open access journal from MDPI
DO - 10.3390/ani16203196
UR - https://europepmc.org/article/MED/42939127
AB - Ketosis is a common metabolic disorder in dairy cows and occurs mainly during early lactation. Blood β-hydroxybutyrate (BHB) is widely used for diagnosis, but large-scale testing is limited by sampling requirements and cost. We therefore studied lactating Holstein cows from 12 large-scale dairy farms in central China. Milk samples, milk composition traits, and milk mid-infrared (MIR) spectra were collected through the Dairy Herd Improvement (DHI) testing system from April 2019 to December 2022, and ketosis diagnoses were obtained from farm health records; samples were labeled as healthy or ketotic based on the temporal relationship between diagnosis and sampling. A total of 2206 samples were used to build the calibration and validation datasets, in which five feature wavenumber selection methods and five machine learning algorithms were compared. Ketotic cows had a higher milk fat percentage and fat-to-protein ratio and a lower protein and lactose percentage (p < 0.01). The best combination was PLS-DA based on 104 CARS-selected wavenumbers, which achieved a sensitivity of 0.83, a specificity of 0.79, a balanced accuracy of 0.81 and an area under the receiver operating characteristic curve (AUC) of 0.88 in validation. MIR spectroscopy combined with machine learning can therefore support large-scale ketosis phenotyping within the DHI system.
SN - 2076-2615
ER -