Neural Network-Aided Milk Somatic Cell Count Increase Prediction

Subclinical mastitis (SM) is the most economically damaging yet often visually undetectable disease of dairy cows. Early detection and treatment can reduce the loss caused by the disease; thus, the continuous improvement of SM diagnostic methods is necessary. Although milk’s somatic cell count (SCC)...

Full description

Saved in:
Bibliographic Details
Main Authors: Sára Ágnes Nagy, István Csabai, Tamás Varga, Bettina Póth-Szebenyi, György Gábor, Norbert Solymosi
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Veterinary Sciences
Subjects:
Online Access:https://www.mdpi.com/2306-7381/12/5/420
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126226784518144
author Sára Ágnes Nagy
István Csabai
Tamás Varga
Bettina Póth-Szebenyi
György Gábor
Norbert Solymosi
author_facet Sára Ágnes Nagy
István Csabai
Tamás Varga
Bettina Póth-Szebenyi
György Gábor
Norbert Solymosi
author_sort Sára Ágnes Nagy
collection DOAJ
description Subclinical mastitis (SM) is the most economically damaging yet often visually undetectable disease of dairy cows. Early detection and treatment can reduce the loss caused by the disease; thus, the continuous improvement of SM diagnostic methods is necessary. Although milk’s somatic cell count (SCC) is commonly measured for diagnostic purposes, its direct determination is not widely used in everyday practice. The primary objective of our work was to investigate whether the predictive value of SM diagnostics can be improved by training artificial neural networks (ANNs) on data generated using typical conventional milking systems. The best ANN classifier had a sensitivity of 0.54 and a specificity of 0.77, which is comparable to performances of various California Mastitis Tests (CMT) found in the literature. Combining two diagnostic tests, ANN and CMT, we concluded that the positive predictive value could be up to 50% higher than the value provided by the individual CMT. While implementing CMT is a labor-intensive process on herd-level, in milking machines where milk properties or milk yield data can be measured automatically, similar to our work, SCC-increase predictions for all individuals could be obtained daily basis.
format Article
id doaj-art-5f97a3a2a9f44fa98ab261c0324f922b
institution OA Journals
issn 2306-7381
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Veterinary Sciences
spelling doaj-art-5f97a3a2a9f44fa98ab261c0324f922b2025-08-20T02:33:58ZengMDPI AGVeterinary Sciences2306-73812025-04-0112542010.3390/vetsci12050420Neural Network-Aided Milk Somatic Cell Count Increase PredictionSára Ágnes Nagy0István Csabai1Tamás Varga2Bettina Póth-Szebenyi3György Gábor4Norbert Solymosi5Department of Physics of Complex Systems, Eötvös Loránd University, 1117 Budapest, HungaryDepartment of Physics of Complex Systems, Eötvös Loránd University, 1117 Budapest, HungaryCentre for Bioinformatics, University of Veterinary Medicine, 1078 Budapest, HungaryDoctoral School of Animal Science, Hungarian University of Agriculture and Life Sciences, 7400 Kaposvár, HungaryCentre for Bioinformatics, University of Veterinary Medicine, 1078 Budapest, HungaryDepartment of Physics of Complex Systems, Eötvös Loránd University, 1117 Budapest, HungarySubclinical mastitis (SM) is the most economically damaging yet often visually undetectable disease of dairy cows. Early detection and treatment can reduce the loss caused by the disease; thus, the continuous improvement of SM diagnostic methods is necessary. Although milk’s somatic cell count (SCC) is commonly measured for diagnostic purposes, its direct determination is not widely used in everyday practice. The primary objective of our work was to investigate whether the predictive value of SM diagnostics can be improved by training artificial neural networks (ANNs) on data generated using typical conventional milking systems. The best ANN classifier had a sensitivity of 0.54 and a specificity of 0.77, which is comparable to performances of various California Mastitis Tests (CMT) found in the literature. Combining two diagnostic tests, ANN and CMT, we concluded that the positive predictive value could be up to 50% higher than the value provided by the individual CMT. While implementing CMT is a labor-intensive process on herd-level, in milking machines where milk properties or milk yield data can be measured automatically, similar to our work, SCC-increase predictions for all individuals could be obtained daily basis.https://www.mdpi.com/2306-7381/12/5/420dairy cowsubclinical mastitissomatic cell countelectrical conductivitymachine learningartificial neural network
spellingShingle Sára Ágnes Nagy
István Csabai
Tamás Varga
Bettina Póth-Szebenyi
György Gábor
Norbert Solymosi
Neural Network-Aided Milk Somatic Cell Count Increase Prediction
Veterinary Sciences
dairy cow
subclinical mastitis
somatic cell count
electrical conductivity
machine learning
artificial neural network
title Neural Network-Aided Milk Somatic Cell Count Increase Prediction
title_full Neural Network-Aided Milk Somatic Cell Count Increase Prediction
title_fullStr Neural Network-Aided Milk Somatic Cell Count Increase Prediction
title_full_unstemmed Neural Network-Aided Milk Somatic Cell Count Increase Prediction
title_short Neural Network-Aided Milk Somatic Cell Count Increase Prediction
title_sort neural network aided milk somatic cell count increase prediction
topic dairy cow
subclinical mastitis
somatic cell count
electrical conductivity
machine learning
artificial neural network
url https://www.mdpi.com/2306-7381/12/5/420
work_keys_str_mv AT saraagnesnagy neuralnetworkaidedmilksomaticcellcountincreaseprediction
AT istvancsabai neuralnetworkaidedmilksomaticcellcountincreaseprediction
AT tamasvarga neuralnetworkaidedmilksomaticcellcountincreaseprediction
AT bettinapothszebenyi neuralnetworkaidedmilksomaticcellcountincreaseprediction
AT gyorgygabor neuralnetworkaidedmilksomaticcellcountincreaseprediction
AT norbertsolymosi neuralnetworkaidedmilksomaticcellcountincreaseprediction