Lactate Threshold (Critical pace) and Race Time Estimation

User guide index: https://marcoaltini.substack.com/p/hrv4training-pro-user-guide

Mar 30, 2023

The lactate threshold and race time estimation feature allow runners using the Strava or TrainingPeaks integration and training with a heart rate monitor, to determine their lactate threshold (in this context, we could call it critical pace), and estimated times over the half and full marathon distance. The estimate is then used to provide advice on pacing strategies for racing and workouts. Check out this publication to learn more about our work on predicting running performance and building this model.

In practical terms, the lactate threshold (or critical pace in this context), is approximately the pace you should be able to hold for a distance between 10 and 15 km. This is the criteria used in HRV4Training, which should help you make sense of the estimate.

We estimate your lactate threshold based on your workouts data, training patterns, morning measurements, and anthropometrics data. In particular, the top panel shows your current lactate threshold (past 3 to 6 weeks depending on available data) and the relative change with respect to the previous 2 months. The side panels show the most likely range in which your current lactate threshold is, consider our estimation model error.

Intuitively, knowing your lactate threshold can help you define pacing strategies for racing events between the 5 km and the half marathon (or longer, but in that case, other factors such as training volume or running economy start to play a more important role), as well as determining training pace for intervals and tempo runs. Pro provides pace zones as reported below.

Race time estimation

The race time estimation is an extension of our previously published analysis (see "Estimating running performance combining non-invasive physiological measurements and training patterns in free-living” which was accepted for publication at the 40th International Engineering in Medicine and Biology Conference, full text here, while another blog post explaining the paper can be found here).

Our models to estimate half marathon and full marathon times are based on a similar analysis, and the following parameters:

Resting measurements of cardiac activity (heart rate and heart rate variability).
Physiological data during training (for example the running pace to heart rate ratio, which we described in our VO2max estimation paper).
Training pace and volume.
Training patterns (for example training intensity distribution, or time spent at low or high intensities vs time spent at moderate intensities, as well as time spent at different speeds).
Previous running performance (automatically derived from racing events or hard interval workouts).
Estimated VO2max.
Long runs (number and frequency).

You will see a different degree of confidence in the models, as we try to move away from ‘exact’ estimates, as there is no such a thing and all models include an error, to provide you with a range of most likely values that can help you, given your knowledge of your workouts and physical condition, getting a realistic understanding of what racing times could be possible based on the available data (R2 was above 0.85 for both models). This is what you see below as optimistic and pessimistic values.

In addition, the models differ as the full marathon estimation model highly relies on the presence of long runs among your workouts, an aspect often forgotten by other estimators, and which we believe is key to performance in long-distance events.

Data

Our lactate threshold estimation requires at least one hard effort of about 5 km (3 miles) to work correctly. If you see inconsistent results, the reason might be the lack of hard efforts in the past few weeks. We recommend using Strava for this feature to work best, as we can access more detailed workout information in that case (e.g. laps instead of just workout summaries).

I hope you’ll like the new Lactate threshold and race time estimation page and the improvements we implemented.

Please feel free to comment below in case of any questions or feature requests.

Thank you for your support.

Marco holds a PhD cum laude in applied machine learning, a M.Sc. cum laude in computer science engineering, and a M.Sc. cum laude in human movement sciences and high-performance coaching.

He has published more than 50 papers and patents at the intersection between physiology, health, technology, and human performance.

He is co-founder of HRV4Training, advisor at Oura, guest lecturer at VU Amsterdam, and editor for IEEE Pervasive Computing Magazine. He loves running.

Social: