Validation of a deep learning model for cattle lameness detection: Comparison of human scorer performance and automated gait analysis

Lameness is a common health and welfare issue in dairy cattle, with significant economic consequences due to reduced productivity. Traditional visual locomotion scoring relies on human expertise and is prone to subjectivity and variability. This study presents an AI-based system for automated lamene...

Full description

Saved in:
Bibliographic Details
Main Authors: Sandra Reitmaier, Serhan Narli
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525004836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849694447158165504
author Sandra Reitmaier
Serhan Narli
author_facet Sandra Reitmaier
Serhan Narli
author_sort Sandra Reitmaier
collection DOAJ
description Lameness is a common health and welfare issue in dairy cattle, with significant economic consequences due to reduced productivity. Traditional visual locomotion scoring relies on human expertise and is prone to subjectivity and variability. This study presents an AI-based system for automated lameness detection, integrating deep learning for keypoint extraction with kinematic feature-based classification. A total of 424 high-resolution locomotion videos from 260 Holstein Friesian cows were collected across four German farms and scored using the 5-point Locomotion Scoring System (LCS) by 12 experienced human evaluators. The system was trained using two strategies: a direct multi-class Random Forest model and a hierarchical model combining binary and multi-class stages. The hierarchical model achieved 94 % accuracy, while the multi-class model reached 87.5%. Both models showed high sensitivity and specificity, and their average prediction closely matched the consensus of human scorers. Despite this, mild lameness remained difficult to classify for both humans and AI, particularly between LCS-2 and LCS-3. The findings support the potential of AI systems to deliver consistent, scalable, and objective lameness detection, with future applications in real time farm settings to improve welfare outcomes and decision making.
format Article
id doaj-art-fe214dd6fb5f4533b481a85de4cd8a02
institution DOAJ
issn 2772-3755
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-fe214dd6fb5f4533b481a85de4cd8a022025-08-20T03:20:04ZengElsevierSmart Agricultural Technology2772-37552025-12-011210125210.1016/j.atech.2025.101252Validation of a deep learning model for cattle lameness detection: Comparison of human scorer performance and automated gait analysisSandra Reitmaier0Serhan Narli1Julius Wolff Institute, Berlin Institute of Health, Charité - Universitätsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, GermanyCorresponding author at: Charité - Universitätsmedizin Berlin, Julius Wolff Institut für Biomechanik und Muskuloskeletale Regeneration, Berlin, Germany.; Julius Wolff Institute, Berlin Institute of Health, Charité - Universitätsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, GermanyLameness is a common health and welfare issue in dairy cattle, with significant economic consequences due to reduced productivity. Traditional visual locomotion scoring relies on human expertise and is prone to subjectivity and variability. This study presents an AI-based system for automated lameness detection, integrating deep learning for keypoint extraction with kinematic feature-based classification. A total of 424 high-resolution locomotion videos from 260 Holstein Friesian cows were collected across four German farms and scored using the 5-point Locomotion Scoring System (LCS) by 12 experienced human evaluators. The system was trained using two strategies: a direct multi-class Random Forest model and a hierarchical model combining binary and multi-class stages. The hierarchical model achieved 94 % accuracy, while the multi-class model reached 87.5%. Both models showed high sensitivity and specificity, and their average prediction closely matched the consensus of human scorers. Despite this, mild lameness remained difficult to classify for both humans and AI, particularly between LCS-2 and LCS-3. The findings support the potential of AI systems to deliver consistent, scalable, and objective lameness detection, with future applications in real time farm settings to improve welfare outcomes and decision making.http://www.sciencedirect.com/science/article/pii/S2772375525004836Machine learningLameness detectionDairy cowsLocomotion scoringPose EstimationComputer Vision
spellingShingle Sandra Reitmaier
Serhan Narli
Validation of a deep learning model for cattle lameness detection: Comparison of human scorer performance and automated gait analysis
Smart Agricultural Technology
Machine learning
Lameness detection
Dairy cows
Locomotion scoring
Pose Estimation
Computer Vision
title Validation of a deep learning model for cattle lameness detection: Comparison of human scorer performance and automated gait analysis
title_full Validation of a deep learning model for cattle lameness detection: Comparison of human scorer performance and automated gait analysis
title_fullStr Validation of a deep learning model for cattle lameness detection: Comparison of human scorer performance and automated gait analysis
title_full_unstemmed Validation of a deep learning model for cattle lameness detection: Comparison of human scorer performance and automated gait analysis
title_short Validation of a deep learning model for cattle lameness detection: Comparison of human scorer performance and automated gait analysis
title_sort validation of a deep learning model for cattle lameness detection comparison of human scorer performance and automated gait analysis
topic Machine learning
Lameness detection
Dairy cows
Locomotion scoring
Pose Estimation
Computer Vision
url http://www.sciencedirect.com/science/article/pii/S2772375525004836
work_keys_str_mv AT sandrareitmaier validationofadeeplearningmodelforcattlelamenessdetectioncomparisonofhumanscorerperformanceandautomatedgaitanalysis
AT serhannarli validationofadeeplearningmodelforcattlelamenessdetectioncomparisonofhumanscorerperformanceandautomatedgaitanalysis