FREE SHIPPING over $40
OVER 9000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Home / Equine Research Bank / Sci Rep / An iterative approach to identify key predictive features of...
Scientific reports2025; 15(1); 24590; doi: 10.1038/s41598-025-10725-4

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 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.
© 2025. The Author(s).
Get Full Text
Publication Date: 2025-07-09 PubMed ID: 40628935PubMed Central: PMC12238550DOI: 10.1038/s41598-025-10725-4Google Scholar: Lookup
The Equine Research Bank provides access to a large database of publicly available scientific literature. Inclusion in the Research Bank does not imply endorsement of study methods or findings by Mad Barn.
LinkedInCopy
  • Journal Article

Summary

This research summary has been generated with artificial intelligence and may contain errors and omissions. Refer to the original study to confirm details provided. Submit correction.

This research uses artificial intelligence to predict fear reactivity and fearfulness in horses based on various morphological, kinematic, behavioral and management measurements. The researchers found six key features that predict fear reactivity and nine for fearfulness, emphasizing the complexity of fear-related traits and the benefits of AI in understanding animal behavior.

Methodology

  • The data was collected from 101 Lipizzan horses, a breed known for its grace and performance in dressage. Each horse was evaluated based on 221 different morphological, kinematic, behavioral and management measurements. Morphology refers to the physical attributes (e.g., body and head size), kinematics is about the movement and behavior of the horse, and management reflects how the horse is taken care of.
  • An artificial intelligence (AI) tool was used to analyze the accumulated data and identify features that predict fear reactivity and fearfulness. The reactivity refers to the immediate reaction of the horse to fear-inducing stimuli, whereas fearfulness refers to a stable personality trait.

Findings

  • Through the AI-driven analysis, the researchers confirmed previous findings about the potential predictive capability of body and head size for fear-related traits.
  • The AI tool identified six key predictive features for fear reactivity and nine for fearfulness. The features that were relevant for ten or more horses were highlighted using a decision tree analysis.
  • The researchers also found a 96% behavioral overlap between reactivity and fearfulness, demonstrating a strong correlation between the two. This means that a horse with a high fear reactivity is very likely to be a fearful horse in general.
  • However, the key predictive features of fear reactivity and fearfulness were noticeably different. The highest correlation coefficient between the features did not exceed 0.57, which suggests that the presence of one trait does not necessarily imply the presence of the other.

Implications

  • This research emphasizes the complexity of fear-related traits in horses and the role of specific phenotypes in predicting the reactivity and personality of adult horses.
  • The results show that using AI tools can provide more accurate and objective descriptions of horse behavior, which can be particularly useful for making informed decisions about management, training, and breeding.

Cite This Article

APA
Gobbo E, Topal O, Novalija I, Mladenić D, Zupan Šemrov M. (2025). An iterative approach to identify key predictive features of fear reactivity and fearfulness in horses (Equus caballus). Sci Rep, 15(1), 24590. https://doi.org/10.1038/s41598-025-10725-4

Publication

Scientific reports
ISSN: 2045-2322
NlmUniqueID: 101563288
Country: England
Language: English
Volume: 15
Issue: 1
Pages: 24590
PII: 24590

Researcher Affiliations

Gobbo, Elena
  • Department of Animal Science, Biotechnical Faculty, University of Ljubljana, Groblje 3, Domžale, Slovenia. elena.gobbo@bf.uni-lj.si.
Topal, Oleksandra
  • Department for Artificial Intelligence, Jožef Stefan Institute, Jamova cesta 39, Ljubljana, Slovenia.
Novalija, Inna
  • Department for Artificial Intelligence, Jožef Stefan Institute, Jamova cesta 39, Ljubljana, Slovenia.
Mladenić, Dunja
  • Department for Artificial Intelligence, Jožef Stefan Institute, Jamova cesta 39, Ljubljana, Slovenia.
Zupan Šemrov, Manja
  • Department of Animal Science, Biotechnical Faculty, University of Ljubljana, Groblje 3, Domžale, Slovenia.

MeSH Terms

  • Animals
  • Fear / physiology
  • Horses / physiology
  • Behavior, Animal / physiology
  • Female
  • Male
  • Artificial Intelligence
  • Personality

Grant Funding

  • J7-3154 / The Slovenian Research and Innovation Agency
  • J7-3154 / The Slovenian Research and Innovation Agency
  • J7-3154 / The Slovenian Research and Innovation Agency
  • J7-3154 / The Slovenian Research and Innovation Agency
  • J7-3154 / The Slovenian Research and Innovation Agency

Conflict of Interest Statement

Declarations. Competing interests: The authors declare no competing interests.

References

This article includes 55 references
  1. Stankowich T, Blumstein DT. Fear in animals: a meta-analysis and review of risk assessment.. 2627–2634 (2005).
    pmc: PMC1559976pubmed: 16321785doi: 10.1098/rspb.2005.3251google scholar: lookup
  2. Forkman B, Boissy A, Meunier-Salaün MC, Canali E, Jones RB. A critical review of fear tests used on cattle, pigs, sheep, poultry and horses.. 340–374 (2007).
    pubmed: 18046784doi: 10.1016/j.physbeh.2007.03.016google scholar: lookup
  3. Sackman JE, Houpt KA. Equine personality: Association with breed, use, and husbandry factors.. 47–55 (2019).
    pubmed: 30929783doi: 10.1016/j.jevs.2018.10.018google scholar: lookup
  4. Rankins EM, Wickens CL. A systematic review of equine personality.. 105076 (2020).
    doi: 10.1016/j.applanim.2020.105076google scholar: lookup
  5. Acton AS, Gaw CE, Chounthirath T. Nonfatal horse-related injuries treated in emergency departments in the united states, 1990–2017.. 1062–1068 (2020).
    pubmed: 31402233doi: 10.1016/j.ajem.2019.158366google scholar: lookup
  6. Genik LM, McMurtry CM. Prevalence and impact of bumps, bruises, and other painful incidents among children while handling and riding horses.. 100229 (2019).
    doi: 10.1016/j.jort.2019.100229google scholar: lookup
  7. Camargo F. Horse-related injuries: causes, preventability, and where educational efforts should be focused.. 1432168 (2018).
    doi: 10.1080/23311932.2018.1432168google scholar: lookup
  8. von König U. Assessing and influencing personality for improvement of animal welfare: A review of equine studies.. 1–27 (2013).
    doi: 10.1079/pavsnnr20138006google scholar: lookup
  9. MacKay JRD, Haskell MJ. Consistent individual behavioral variation: the difference between temperament, personality and behavioral syndromes.. 455–478 (2015).
    pmc: PMC4598688pubmed: 26479368doi: 10.3390/ani5030366google scholar: lookup
  10. Dai F. Validation of a fear test in sport horses using infrared thermography.. 128–136 (2015).
    doi: 10.1016/j.jveb.2014.12.001google scholar: lookup
  11. Lansade L, Bouissou MF, Erhard HW. Fearfulness in horses: A temperament trait stable across time and situations.. 182–200 (2008).
    doi: 10.1016/j.applanim.2008.06.011google scholar: lookup
  12. Finkemeier MA, Langbein J, Puppe B. Personality research in mammalian farm animals: concepts, measures, and relationship to welfare.. 131–146 (2018).
    pmc: PMC6031753pubmed: 30003083doi: 10.3389/fvets.2018.00131google scholar: lookup
  13. Lansade L, Philippon P, Hervé L, Vidament M. Development of personality tests to use in the field, stable over time and across situations, and linked to horses’ show jumping performance.. 43–51 (2016).
    doi: 10.1016/j.applanim.2016.01.005google scholar: lookup
  14. Christensen JW, Keeling LJ, Lindstrom NB. Responses of horses to novel visual, olfactory and auditory stimuli.. 53–65 (2005).
    doi: 10.1016/j.applanim.2005.06.017google scholar: lookup
  15. von König U, Euent S, Graf P, König S, Gauly M. Equine behavior and heart rate in temperament tests with or without rider or handler.. 454–463 (2011).
    pubmed: 21616087doi: 10.1016/j.physbeh.2011.05.010google scholar: lookup
  16. Topal O, Novalija I, Mladenić D, Gobbo E, Zupan Šemrov M. Machine learning in animal personality: modelling fearfulness of Lipizzan horses.. (in review) (2025).
  17. McGreevy PD. Dog behavior co-varies with height, bodyweight and skull shape.. e80529 (2013).
    pmc: PMC3864788pubmed: 24358107doi: 10.1371/journal.pone.0080529google scholar: lookup
  18. Kern EMA, Robinson D, Gass E, Godwin J, Langerhans RB. Correlated evolution of personality, morphology and performance.. 79–86 (2016).
    pmc: PMC5791543pubmed: 29398712doi: 10.1016/j.anbehav.2016.04.007google scholar: lookup
  19. Hansen I, Christiansen F, Hansen HS, Braastad B, Bakken M. Variation in behavioural responses of Ewes towards predator related stimuli.. (2001).
    pubmed: 11118663doi: 10.1016/s0168-1591(00)00155-6google scholar: lookup
  20. Shivley C, Grandin T, Deesing M. Behavioral laterality and facial hair whorls in horses.. 62–66 (2016).
    doi: 10.1016/j.jevs.2016.02.238google scholar: lookup
  21. Debeljak N, Košmerlj A, Altimiras J, Zupan Šemrov M. Relationship between anatomical characteristics and personality traits in Lipizzan horses.. 12618 (2022).
    pmc: PMC9308772pubmed: 35871229doi: 10.1038/s41598-022-16627-zgoogle scholar: lookup
  22. Leiner L, Fendt M. Behavioural fear and heart rate responses of horses after exposure to novel objects: effects of habituation.. 104–109 (2011).
    doi: 10.1016/j.applanim.2011.02.004google scholar: lookup
  23. Zsoldos RR, Licka TF. The equine neck and its function during movement and locomotion.. 364–376 (2015).
    pubmed: 26163862doi: 10.1016/j.zool.2015.03.005google scholar: lookup
  24. Mullard J, Berger JM, Ellis AD, Dyson S. Development of an ethogram to describe facial expressions in ridden horses (FEReq).. 7–12 (2017).
    doi: 10.1016/j.jveb.2016.11.005google scholar: lookup
  25. Zimmermann B. Anatomical and functional basis of facial expressions and their relationship with emotions in horses.. 105418 (2024).
    pubmed: 39303445doi: 10.1016/j.rvsc.2024.05.010google scholar: lookup
  26. Finka LR. Geometric morphometrics for the study of facial expressions in non-human animals, using the domestic Cat as an exemplar.. 46330 (2019).
    pmc: PMC6614427pubmed: 31285531doi: 10.1038/s41598-019-46330-5google scholar: lookup
  27. Camerlink I, Coulange E, Farish M, Baxter EM, Turner SP. Facial expression as a potential measure of both intent and emotion.. 17602 (2018).
    pmc: PMC6279763pubmed: 30514964doi: 10.1038/s41598-018-35905-3google scholar: lookup
  28. Reefmann N, Wechsler B, Gygax L. Behavioural and physiological assessment of positive and negative emotion in sheep.. 651–659 (2009).
    doi: 10.1016/j.anbehav.2009.06.015google scholar: lookup
  29. Wathan J, Burrows AM, Waller BM, McComb K. EquiFACS: the equine facial action coding system.. e0131738 (2015).
    pmc: PMC4526551pubmed: 26244573doi: 10.1371/journal.pone.0131738google scholar: lookup
  30. Dalla Costa E. Development of the horse grimace scale (HGS) as a pain assessment tool in horses undergoing routine castration.. e92281 (2014).
    pmc: PMC3960217pubmed: 24647606doi: 10.1371/journal.pone.0092281google scholar: lookup
  31. Dyson S, Berger JM, Ellis AD, Mullard J. Can the presence of musculoskeletal pain be determined from the facial expressions of ridden horses (FEReq)?. 78–89 (2017).
    doi: 10.1016/j.jveb.2017.03.005google scholar: lookup
  32. Andersen PH. Towards machine recognition of facial expressions of pain in horses.. 1643 (2021).
    pmc: PMC8229776pubmed: 34206077doi: 10.3390/ani11061643google scholar: lookup
  33. Ricci-Bonot C, Mills DS. Recognising the facial expression of frustration in the horse during feeding period.. 105966 (2023).
    doi: 10.1016/j.applanim.2023.105966google scholar: lookup
  34. Larose C, Richard-Yris MA, Hausberger M, Rogers LJ. Laterality of horses associated with emotionality in novel situations.. 355–367 (2006).
    pubmed: 16754236doi: 10.1080/13576500600624221google scholar: lookup
  35. Draaisma, R. (Taylor & Francis, 2018).
  36. De Roches BD, Richard-Yris A, Henry MA, Ezzaouïa S, Hausberger M. Laterality and emotions: visual laterality in the domestic horse (Equus caballus) differs with objects’ emotional value.. 487–490 (2008).
    pubmed: 18455205doi: 10.1016/j.physbeh.2008.03.002google scholar: lookup
  37. Süß F, Guth S, Müller-Ehrenberg H, Röcken M, Staszyk C. Gross anatomy of the equine masseter muscle: lamination and intramuscular course of the N. massetericus.. e70000 (2024).
    pubmed: 39462227doi: 10.1111/ahe.70000google scholar: lookup
  38. Pilliner, S., Elmhurst, S. & Davies, Z. (Wiley-Blackwell, 2002).
  39. Clayton HM, Hobbs SJ. A review of Biomechanical gait classification with reference to collected trot, passage and Piaffe in dressage horses.. 763 (2019).
    pmc: PMC6826507pubmed: 31623360doi: 10.3390/ani9100763google scholar: lookup
  40. Grandin T, Shivley C. How farm animals react and perceive stressful situations such as handling, restraint, and transport.. 1233–1251 (2015).
    pmc: PMC4693213pubmed: 26633523doi: 10.3390/ani5040409google scholar: lookup
  41. Baragli P, Vitale V, Banti L, Sighieri C. Effect of aging on behavioural and physiological responses to a stressful stimulus in horses ().. 1513–1533 (2014).
    doi: 10.1163/1568539x-00003197google scholar: lookup
  42. Christensen JW, Zharkikh T, Ladewig J. Do horses generalise between objects during habituation?. 509–520 (2008).
    doi: 10.1016/j.applanim.2008.03.007google scholar: lookup
  43. . TPSDig2: a program for landmark development and analysis (2021).. .
  44. Sheets, H. D. (Canisius College, 2016).
  45. Murphy J, Arkins S. Facial hair whorls (trichoglyphs) and the incidence of motor laterality in the horse.. 7–12 (2008).
    pubmed: 18511219doi: 10.1016/j.beproc.2008.03.006google scholar: lookup
  46. Górecka-Bruzda A, Golonka M, Chruszczewski MH, Jezierski T. A note on behaviour and heart rate in horses differing in facial hair whorl.. 244–248 (2007).
    doi: 10.1016/j.applanim.2006.05.013google scholar: lookup
  47. Leleu C, Gloria E, Renault G. Analysis of trotter gait on the track by accelerometry and image analysis.. 344–348 (2002).
    pubmed: 12405713
  48. Leleu C, Cotrel C, Barrey E. Relationships between biomechanical variables and race performance in French standardbred trotters.. 39–46 (2005).
    pubmed: 15789646doi: 10.1016/j.livprodsci.2004.07.019google scholar: lookup
  49. Argüelles D, Saitua A, de Medina AS, Muñoz JA, Muñoz A. Clinical efficacy of clodronic acid in horses diagnosed with navicular syndrome: A field study using objective and subjective lameness evaluation.. 298–304 (2019).
    pubmed: 31351199doi: 10.1016/j.rvsc.2019.07.018google scholar: lookup
  50. López-Sanromán FJ, Holmbak-Petersen R, Santiago I, Gómez de segura IA. Gait analysis using 3D accelerometry in horses sedated with xylazine.. 212–216 (2012).
    pubmed: 22082509doi: 10.1016/j.tvjl.2011.10.012google scholar: lookup
  51. Graf P, von Borstel K, Gauly M. Practical considerations regarding the implementation of a temperament test into horse performance tests: results of a large-scale test run.. 329–340 (2014).
  52. Lansade L. Personality and predisposition to form habit behaviours during instrumental conditioning in horses (Equus caballus).. e0171010 (2017).
    pmc: PMC5291538pubmed: 28158199doi: 10.1371/journal.pone.0171010google scholar: lookup
  53. Brunberg E, Gille S, Mikko S, Lindgren G, Keeling LJ. Icelandic horses with the silver coat colour show altered behaviour in a fear reaction test.. 72–78 (2013).
    doi: 10.1016/j.applanim.2013.04.005google scholar: lookup
  54. von König U. Impact of riding in coercively obtained Rollkür posture on welfare and fear in performance horses.. 228–236 (2009).
    doi: 10.1016/j.applanim.2008.10.001google scholar: lookup
  55. Leśniak K. Directional asymmetry of facial and limb traits in horses and ponies.. e46–e51 (2013).
    pubmed: 24152382doi: 10.1016/j.tvjl.2013.09.032google scholar: lookup

Citations

This article has been cited 0 times.
Subscribe to our newsletter
Join 99,357 horse owners like you who receive our email updates on horse health and nutrition.