The majority of proximal sesamoid and condylar fractures occurred in horses identified as high risk by inertial measurement unit sensors.

IMU-based algorithms identify high-risk horses for condylar and sesamoid fractures with strong predictive value.

This study evaluated accelerometer-based inertial measurement unit (IMU) sensors worn by racing Thoroughbreds to develop fracture-specific algorithms for predicting forelimb condylar and proximal sesamoid fractures. Data from 42,623 races involving 15,755 horses were analyzed, including 54 races from 23 horses with subsequent condylar fractures and 90 races from 31 horses with subsequent sesamoid fractures. Risk stratification algorithms classified horses into green (low risk), amber (asymmetry detected), and red (high risk, scores 3-5) categories. Results demonstrated that 89% of all fractures occurred in the red-risk group. For horses with ≥3 starts and mean risk scores >3.0 over consecutive races, positive predictive value reached 0.74 with an odds ratio of 133 (95% CI, 23.5-753). Over 98.8% of horses with scores <5 remained fracture-free. These fracture-specific algorithms show promise in identifying high-risk horses for clinical intervention and monitoring, potentially reducing catastrophic forelimb fractures in racing populations.

This summary was distilled by AI and may occasionally misinterpret data. Confirm critical details with the primary literature before clinical application.