Cardiovascular Fitness and Stride Acceleration in Race-Pace Workouts for the Prediction of Performance in Thoroughbreds.

In-training racehorse physiological data can be leveraged to further explore race-day performance prediction. To date, no large retrospective, observational study has analysed whether in-training speed and heart rate recovery can predict racehorse success. Speed (categorised as 'slow' to 'fast' according to the time taken to cover the last 600 m from a virtual finish line) and heart rate recovery (from gallop to 1 min after exercise) of flat racehorses (n = 485) of varying age, sex and type according to distance (e.g., sprinter, miler and stayer) were obtained using a fitness tracker from a single racing yard in Australia. Race-pace training sessions on turf comprised 'fast gallop' (n = 3418 sessions) or 'jumpout' (n = 1419). A posteriori racing information (n = 3810 races) for all 485 racehorses was extracted and combined with training data. Race performance was categorised as win/not-win or podium or not, each analysed by logistic regression. Colts ( p < 0.001), stayers ( p < 0.001) and being relatively fast over the last 600 m of a benchmark test in training ( p < 0.008) were all predictive of race performance. Heart rate recovery after exercise ( p = 0.21) and speed recorded at 600 m of a 1 km benchmark test in training ( p = 0.94) were not predictive. In-training physiological data analytics used along with subjective experience may help trainers identify promising horses and improve decision-making.