An iterative approach to identify key predictive features of fear reactivity and fearfulness in horses (Equus caballus)

Abstract This study extends previous findings by applying artificial intelligence (AI) methods to a larger dataset to identify key features that predict fear reactivity (i.e., immediate reaction to fear inducing stimuli) and fearfulness (i.e., a stable personality trait) in 101 Lipizzan horses. The...

Full description

Saved in:
Bibliographic Details
Main Authors: Elena Gobbo, Oleksandra Topal, Inna Novalija, Dunja Mladenić, Manja Zupan Šemrov
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10725-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387917844152320
author Elena Gobbo
Oleksandra Topal
Inna Novalija
Dunja Mladenić
Manja Zupan Šemrov
author_facet Elena Gobbo
Oleksandra Topal
Inna Novalija
Dunja Mladenić
Manja Zupan Šemrov
author_sort Elena Gobbo
collection DOAJ
description Abstract This study extends previous findings by applying artificial intelligence (AI) methods to a larger dataset to identify key features that predict fear reactivity (i.e., immediate reaction to fear inducing stimuli) and fearfulness (i.e., a stable personality trait) in 101 Lipizzan horses. The analysis included 221 morphological, kinematic, behavioral and management measurements per horse. Previous findings were confirmed, as body and head size were identified as promising predictors of aspects of fear-related trait. Using an iterative AI approach, six key features for fear reactivity and nine for fearfulness were identified, with decision tree analysis highlighting significant features that were relevant for equal or more than 10 horses. A 96% behavioral overlap between reactivity and fearfulness was observed, indicating a strong correlation. However, key predictive features differed between the two traits, with correlation coefficients not exceeding 0.57. This study highlights the complexity of fear-related traits and emphasizes that specific phenotypes more accurately predict reactivity and personality in adult horses when AI methods are used. These methods may provide objective, data-driven insights into horses’ behavior, which could support more informed and individualized decisions in management, training and breeding.
format Article
id doaj-art-8aea30f99f9a4e78ba37b7e933b49fc5
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-8aea30f99f9a4e78ba37b7e933b49fc52025-08-20T03:42:27ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-10725-4An iterative approach to identify key predictive features of fear reactivity and fearfulness in horses (Equus caballus)Elena Gobbo0Oleksandra Topal1Inna Novalija2Dunja Mladenić3Manja Zupan Šemrov4Department of Animal Science, Biotechnical Faculty, University of LjubljanaDepartment for Artificial Intelligence, Jožef Stefan InstituteDepartment for Artificial Intelligence, Jožef Stefan InstituteDepartment for Artificial Intelligence, Jožef Stefan InstituteDepartment of Animal Science, Biotechnical Faculty, University of LjubljanaAbstract This study extends previous findings by applying artificial intelligence (AI) methods to a larger dataset to identify key features that predict fear reactivity (i.e., immediate reaction to fear inducing stimuli) and fearfulness (i.e., a stable personality trait) in 101 Lipizzan horses. The analysis included 221 morphological, kinematic, behavioral and management measurements per horse. Previous findings were confirmed, as body and head size were identified as promising predictors of aspects of fear-related trait. Using an iterative AI approach, six key features for fear reactivity and nine for fearfulness were identified, with decision tree analysis highlighting significant features that were relevant for equal or more than 10 horses. A 96% behavioral overlap between reactivity and fearfulness was observed, indicating a strong correlation. However, key predictive features differed between the two traits, with correlation coefficients not exceeding 0.57. This study highlights the complexity of fear-related traits and emphasizes that specific phenotypes more accurately predict reactivity and personality in adult horses when AI methods are used. These methods may provide objective, data-driven insights into horses’ behavior, which could support more informed and individualized decisions in management, training and breeding.https://doi.org/10.1038/s41598-025-10725-4Animal personalityFear-related behaviorsMorphologyArtificial intelligence
spellingShingle Elena Gobbo
Oleksandra Topal
Inna Novalija
Dunja Mladenić
Manja Zupan Šemrov
An iterative approach to identify key predictive features of fear reactivity and fearfulness in horses (Equus caballus)
Scientific Reports
Animal personality
Fear-related behaviors
Morphology
Artificial intelligence
title An iterative approach to identify key predictive features of fear reactivity and fearfulness in horses (Equus caballus)
title_full An iterative approach to identify key predictive features of fear reactivity and fearfulness in horses (Equus caballus)
title_fullStr An iterative approach to identify key predictive features of fear reactivity and fearfulness in horses (Equus caballus)
title_full_unstemmed An iterative approach to identify key predictive features of fear reactivity and fearfulness in horses (Equus caballus)
title_short An iterative approach to identify key predictive features of fear reactivity and fearfulness in horses (Equus caballus)
title_sort iterative approach to identify key predictive features of fear reactivity and fearfulness in horses equus caballus
topic Animal personality
Fear-related behaviors
Morphology
Artificial intelligence
url https://doi.org/10.1038/s41598-025-10725-4
work_keys_str_mv AT elenagobbo aniterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus
AT oleksandratopal aniterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus
AT innanovalija aniterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus
AT dunjamladenic aniterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus
AT manjazupansemrov aniterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus
AT elenagobbo iterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus
AT oleksandratopal iterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus
AT innanovalija iterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus
AT dunjamladenic iterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus
AT manjazupansemrov iterativeapproachtoidentifykeypredictivefeaturesoffearreactivityandfearfulnessinhorsesequuscaballus