Comparing Inertial Measurement Units to Markerless Video Analysis for Movement Symmetry in Quarter Horses.
artificial intelligence
horse
inertial measurement unit
lameness
markerless tracking
movement symmetry
Journal
Sensors (Basel, Switzerland)
ISSN: 1424-8220
Titre abrégé: Sensors (Basel)
Pays: Switzerland
ID NLM: 101204366
Informations de publication
Date de publication:
12 Oct 2023
12 Oct 2023
Historique:
received:
19
09
2023
revised:
07
10
2023
accepted:
10
10
2023
medline:
30
10
2023
pubmed:
28
10
2023
entrez:
28
10
2023
Statut:
epublish
Résumé
With an increasing number of systems for quantifying lameness-related movement asymmetry, between-system comparisons under non-laboratory conditions are important for multi-centre or referral-level studies. This study compares an artificial intelligence video app to a validated inertial measurement unit (IMU) gait analysis system in a specific group of horses. Twenty-two reining Quarter horses were equipped with nine body-mounted IMUs while being videoed with a smartphone app. Both systems quantified head and pelvic movement symmetry during in-hand trot (hard/soft ground) and on the lunge (left/right rein, soft ground). Proportional limits of agreement (pLoA) were established. Widths of pLoA were larger for head movement (29% to 50% in-hand; 22% to 38% on lunge) than for pelvic movement (13% to 24% in-hand; 14% to 24% on lunge). The between-system pLoAs exceed current "lameness thresholds" aimed at identifying the affected limb(s) in lame horses. They also exceed published limits of agreement for stride-matched data but are similar to repeatability values and "lameness thresholds" from "non-lame" horses. This is encouraging for multi-centre studies and referral-level veterinary practice. The narrower pLoA values for pelvic movement asymmetry are particularly encouraging, given the difficulty of grading hind limb lameness "by eye".
Sections du résumé
BACKGROUND
BACKGROUND
With an increasing number of systems for quantifying lameness-related movement asymmetry, between-system comparisons under non-laboratory conditions are important for multi-centre or referral-level studies. This study compares an artificial intelligence video app to a validated inertial measurement unit (IMU) gait analysis system in a specific group of horses.
METHODS
METHODS
Twenty-two reining Quarter horses were equipped with nine body-mounted IMUs while being videoed with a smartphone app. Both systems quantified head and pelvic movement symmetry during in-hand trot (hard/soft ground) and on the lunge (left/right rein, soft ground). Proportional limits of agreement (pLoA) were established.
RESULTS
RESULTS
Widths of pLoA were larger for head movement (29% to 50% in-hand; 22% to 38% on lunge) than for pelvic movement (13% to 24% in-hand; 14% to 24% on lunge).
CONCLUSION
CONCLUSIONS
The between-system pLoAs exceed current "lameness thresholds" aimed at identifying the affected limb(s) in lame horses. They also exceed published limits of agreement for stride-matched data but are similar to repeatability values and "lameness thresholds" from "non-lame" horses. This is encouraging for multi-centre studies and referral-level veterinary practice. The narrower pLoA values for pelvic movement asymmetry are particularly encouraging, given the difficulty of grading hind limb lameness "by eye".
Identifiants
pubmed: 37896509
pii: s23208414
doi: 10.3390/s23208414
pmc: PMC10610735
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : University of Calgary
ID : investigative medicine project Kiki Landsbergen
Références
Lancet. 1986 Feb 8;1(8476):307-10
pubmed: 2868172
Res Vet Sci. 2021 Jul;137:281-286
pubmed: 34058399
Sensors (Basel). 2018 Mar 13;18(3):
pubmed: 29534022
Animals (Basel). 2023 Jan 24;13(3):
pubmed: 36766279
PLoS One. 2017 Apr 25;12(4):e0176253
pubmed: 28441406
Equine Vet J. 1987 May;19(3):185-8
pubmed: 3608952
Equine Vet J Suppl. 2010 Nov;(38):417-24
pubmed: 21059039
Equine Vet J. 2001 Sep;33(5):446-51
pubmed: 11558738
Sensors (Basel). 2022 Jan 18;22(3):
pubmed: 35161452
Animals (Basel). 2022 Dec 11;12(24):
pubmed: 36552418
J Biomech. 2021 Jan 4;114:110146
pubmed: 33290946
Am J Vet Res. 2011 Sep;72(9):1156-63
pubmed: 21879972
Vet J. 2013 Dec;198 Suppl 1:e39-45
pubmed: 24140227
Equine Vet J. 2019 Nov;51(6):831-839
pubmed: 30648286
J Am Vet Med Assoc. 2020 Mar 1;256(5):590-599
pubmed: 32068513
Equine Vet J. 1996 Jan;28(1):71-6
pubmed: 8565958
Equine Vet J. 2022 Nov;54(6):1076-1085
pubmed: 34913524
Animals (Basel). 2021 Jun 03;11(6):
pubmed: 34204921
Equine Vet J. 2016 Jan;48(1):83-9
pubmed: 25297461
Equine Vet J. 2021 Sep;53(5):1075-1081
pubmed: 33113248
Stat Methods Med Res. 1999 Jun;8(2):135-60
pubmed: 10501650
Sensors (Basel). 2018 Feb 24;18(2):
pubmed: 29495299
J Biomech. 2012 May 11;45(8):1522-8
pubmed: 22483227
Equine Vet J. 2012 Nov;44(6):652-6
pubmed: 22563674
Am J Vet Res. 2004 May;65(5):665-70
pubmed: 15141889
Equine Vet J. 2018 Jan;50(1):117-124
pubmed: 28548349
J Exp Biol. 2005 Jul;208(Pt 13):2503-14
pubmed: 15961737
Nat Methods. 2022 Apr;19(4):496-504
pubmed: 35414125
Equine Vet J. 2018 Jul;50(4):513-518
pubmed: 29284186