Automated acute pain prediction in domestic goats using deep learning-based models on video-recordings

Abstract Facial expressions are essential in animal communication, and facial expression-based pain scales have been developed for different species. Automated pain recognition offers a valid alternative to manual annotation with growing evidence across species. This study applied machine learning (...

Full description

Saved in:
Bibliographic Details
Main Authors: Ludovica Chiavaccini, Anjali Gupta, Nicole Anclade, Guido Chiavaccini, Chiara De Gennaro, Alanna N. Johnson, Diego A. Portela, Marta Romano, Enzo Vettorato, Daniela Luethy
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-78494-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850061763041558528
author Ludovica Chiavaccini
Anjali Gupta
Nicole Anclade
Guido Chiavaccini
Chiara De Gennaro
Alanna N. Johnson
Diego A. Portela
Marta Romano
Enzo Vettorato
Daniela Luethy
author_facet Ludovica Chiavaccini
Anjali Gupta
Nicole Anclade
Guido Chiavaccini
Chiara De Gennaro
Alanna N. Johnson
Diego A. Portela
Marta Romano
Enzo Vettorato
Daniela Luethy
author_sort Ludovica Chiavaccini
collection DOAJ
description Abstract Facial expressions are essential in animal communication, and facial expression-based pain scales have been developed for different species. Automated pain recognition offers a valid alternative to manual annotation with growing evidence across species. This study applied machine learning (ML) methods, using a pre-trained VGG-16 base and a Support Vector Machine classifier to automate pain recognition in caprine patients in hospital settings, evaluating different frame extraction rates and validation techniques. The study included goats of different breed, age, sex, and varying medical conditions presented to the University of Florida’s Large Animal Hospital. Painful status was determined using the UNESP-Botucatu Goat Acute Pain Scale. The final dataset comprised images from 40 goats (20 painful, 20 non-painful), with 2,253 ‘non-painful’ and 3,154 ‘painful’ images at 1 frame per second (FPS) extraction rate and 7,630 ‘non-painful’ and 9,071 ‘painful’ images at 3 FPS. Images were used to train deep learning-based models with different approaches. The model input was raw images, and pain presence was the target attribute (model output). For the single train-test split and 5-fold cross-validation, the models achieved approximately 80% accuracy, while the subject-wise 10-fold cross-validation showed mean accuracies above 60%. These findings suggest ML’s potential in goat pain assessment.
format Article
id doaj-art-8129353cfe2c492f8adea19dfd1bab3a
institution DOAJ
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-8129353cfe2c492f8adea19dfd1bab3a2025-08-20T02:50:07ZengNature PortfolioScientific Reports2045-23222024-11-0114111110.1038/s41598-024-78494-0Automated acute pain prediction in domestic goats using deep learning-based models on video-recordingsLudovica Chiavaccini0Anjali Gupta1Nicole Anclade2Guido ChiavacciniChiara De Gennaro3Alanna N. Johnson4Diego A. Portela5Marta Romano6Enzo Vettorato7Daniela Luethy8Department of Comparative, Diagnostic and Population Medicine, College of Veterinary Medicine, University of FloridaDepartment of Comparative, Diagnostic and Population Medicine, College of Veterinary Medicine, University of FloridaDepartment of Comparative, Diagnostic and Population Medicine, College of Veterinary Medicine, University of FloridaDepartment of Comparative, Diagnostic and Population Medicine, College of Veterinary Medicine, University of FloridaDepartment of Comparative, Diagnostic and Population Medicine, College of Veterinary Medicine, University of FloridaDepartment of Comparative, Diagnostic and Population Medicine, College of Veterinary Medicine, University of FloridaDepartment of Comparative, Diagnostic and Population Medicine, College of Veterinary Medicine, University of FloridaDepartment of Comparative, Diagnostic and Population Medicine, College of Veterinary Medicine, University of FloridaDepartment of Clinical Studies – New Bolton Center, School of Veterinary Medicine, University of PennsylvaniaAbstract Facial expressions are essential in animal communication, and facial expression-based pain scales have been developed for different species. Automated pain recognition offers a valid alternative to manual annotation with growing evidence across species. This study applied machine learning (ML) methods, using a pre-trained VGG-16 base and a Support Vector Machine classifier to automate pain recognition in caprine patients in hospital settings, evaluating different frame extraction rates and validation techniques. The study included goats of different breed, age, sex, and varying medical conditions presented to the University of Florida’s Large Animal Hospital. Painful status was determined using the UNESP-Botucatu Goat Acute Pain Scale. The final dataset comprised images from 40 goats (20 painful, 20 non-painful), with 2,253 ‘non-painful’ and 3,154 ‘painful’ images at 1 frame per second (FPS) extraction rate and 7,630 ‘non-painful’ and 9,071 ‘painful’ images at 3 FPS. Images were used to train deep learning-based models with different approaches. The model input was raw images, and pain presence was the target attribute (model output). For the single train-test split and 5-fold cross-validation, the models achieved approximately 80% accuracy, while the subject-wise 10-fold cross-validation showed mean accuracies above 60%. These findings suggest ML’s potential in goat pain assessment.https://doi.org/10.1038/s41598-024-78494-0Artificial intelligenceAcute painDeep learningFacial expressionGoatsPain measurement
spellingShingle Ludovica Chiavaccini
Anjali Gupta
Nicole Anclade
Guido Chiavaccini
Chiara De Gennaro
Alanna N. Johnson
Diego A. Portela
Marta Romano
Enzo Vettorato
Daniela Luethy
Automated acute pain prediction in domestic goats using deep learning-based models on video-recordings
Scientific Reports
Artificial intelligence
Acute pain
Deep learning
Facial expression
Goats
Pain measurement
title Automated acute pain prediction in domestic goats using deep learning-based models on video-recordings
title_full Automated acute pain prediction in domestic goats using deep learning-based models on video-recordings
title_fullStr Automated acute pain prediction in domestic goats using deep learning-based models on video-recordings
title_full_unstemmed Automated acute pain prediction in domestic goats using deep learning-based models on video-recordings
title_short Automated acute pain prediction in domestic goats using deep learning-based models on video-recordings
title_sort automated acute pain prediction in domestic goats using deep learning based models on video recordings
topic Artificial intelligence
Acute pain
Deep learning
Facial expression
Goats
Pain measurement
url https://doi.org/10.1038/s41598-024-78494-0
work_keys_str_mv AT ludovicachiavaccini automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings
AT anjaligupta automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings
AT nicoleanclade automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings
AT guidochiavaccini automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings
AT chiaradegennaro automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings
AT alannanjohnson automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings
AT diegoaportela automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings
AT martaromano automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings
AT enzovettorato automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings
AT danielaluethy automatedacutepainpredictionindomesticgoatsusingdeeplearningbasedmodelsonvideorecordings