Monitoring Players’ Readiness Using Predicted Heart Rate Responses to Football Drills

Lacome M, Simpson B, Broad N, Buchheit M

Purpose: The study aimed to assess the effectiveness of multivariate models in predicting heart rate (HR) responses to specific training drills using various GPS variables. Additionally, it aimed to evaluate the utility of the difference between predicted and actual HR responses as an index of fitness or readiness to perform.

Method: Data were collected during the 2016-2017 season, with soccer activity monitored using 5-Hz GPS and internal load measured using HR. GPS and HR data were analyzed during typical small-sided games and a 4-minute standardized submaximal run (12 km/h). Multiple stepwise regression analysis identified combinations of GPS variables correlated with HR responses at the individual level (HRACT, 149±46 GPS/HR pairs per player). These combinations were then used to predict HR during individual drills (HRPRED). The difference between predicted and actual HR (HRΔ, %) was computed to assess fitness or readiness to perform. The validity of HRΔ was examined by comparing changes in HRΔ with changes in HR responses to a submaximal run (HRRUN, fitness criterion) and across different phases of the season.

Results: HRPRED showed a very large correlation with HRACT (r=0.78±0.04). Within-player changes in HRΔ were largely correlated with changes in HRRUN (r=0.66, 0.50-0.82). HRΔ likely decreased from July to August (3.1±2.0 vs. 0.8±2.2%) and further decreased in September (-1.5±2.1%).

Conclusion: HRΔ is a valid variable for monitoring elite soccer players’ fitness, allowing daily fitness monitoring during regular practice and reducing the need for formal testing.

View this research