Blog post by Marco Altini
We have released a new feature in HRV4Training, lactate threshold estimation. In this post, we go over the background, cover what we mean as lactate threshold, how you can use this feature to plan and track your trainings and progress and also provide additional details about the underlying algorithms that we developed to estimate lactate threshold and its accuracy, as well as some of the current limitations.
Lactate threshold estimation in HRV4Training and actual 10 km race time.
What's the lactate threshold anyway?
You'll see in this section we will be using interchangeably the terms lactate and anaerobic threshold - for the purpose of this blog post, they are the same parameter. Borrowing from Svedahl et al. : the anaerobic threshold is defined as the highest sustained intensity of exercise for which measurement of oxygen uptake can account for the entire energy requirement. ... There are many reasons for trying to quantify this intensity of exercise, including assessment of cardiovascular or pulmonary health, evaluation of training programs, and categorization of the intensity of exercise as mild, moderate, or intense. As Buchheit et al. put it , although there is still an important debate on its theoretical basis, the anaerobic threshold is interesting because it has been advanced to be a better marker of endurance performance than VO2max.
What does this mean in practical terms?
In practical terms, the lactate or anaerobic threshold, 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 making sense of the app estimation.
How can you use it?
Intuitively, knowing your lactate threshold can help you defining 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 start to play a more important role), as well as determining training pace for intervals and tempo runs. Some useful insights in this context are provided by Greg McMillan in this article, that I'd recommend checking out.
How do we compute it?
To compute your lactate threshold, we turned around the problem and worked on machine learning models to estimate running performance, in particular 10 km racing time, using the following set of parameters:
What data do I need?
You need to be a runner with at least 15 workouts, including heart rate data, in the past 45 days.
To improve this feature, we re-designed completely the underlying data storage for workouts synched from Strava or TrainingPeaks. In particular, while you will still see aggregates in the History page, the app will discriminate between workouts (and racing events) split into multiple parts (for example warmup, workout or race, cooldown), so that more accurate estimates can be provided.
What's in the app?
The app will show you the estimated range based on your past 45 days of data, see for example above the range and average value displayed for my recent data. You will also see the recent trend, in case your threshold is lowering, hence you are getting faster, or the other way around. The feature will be available for both iOS and Android, and also visible in HRV4Training Coach in case you coach runners.
Accuracy and known limitations
Our work is currently under review and hopefully we will be able to share more in the next few weeks, as we finalize it for publication. For the development of our models we used real life data from more than 2000 HRV4Training users that used the app for several months, and linked the app to either Strava or TrainingPeaks. Using this unique dataset of morning physiological measurements, workouts, and higher level features extracted as longitudinal data related to training patterns for several months was available, we could build models able to predict lactate threshold with a 14 seconds/km average error, which is about 40% better than when using only anthropometrics data and training history (more details will follow as soon as the paper is published).
Relation between predicted and estimated lactate threshold and Bland-Altman plot for more than 2000 users that were part of this analysis. These are cross-validated results, meaning that no data used for model building was used for model validation.
We do have several checks in place to make sure outliers don't get in the way, however under certain circumstances the estimate might be underestimated. In particular, underestimation can result if you train mostly on trails and do very little speed work. A few hard sessions per month should be sufficient to provide accurate estimates even for trail runners.
We talked elsewhere (see this article for example) about how we strongly believe in the ability to further improve our understanding of complex relations between physiology and performance through large-scale research carried out in real-life.
Our journey started by developing a validated and practical tool like HRV4Training, and releasing it in the hands of thousands of individuals, so that research can be carried out at a scale that is not possible in regular laboratory studies.
By relying on this approach, we were able to feed our findings back to the community. We have been developing new features (for example VO2max estimation for cyclists or the current lactate threshold estimation) that hopefully will help you better track and plan your trainings, and eventually lead to improved performance.
Thank you everyone for joining us and making the data-driven development of this new feature possible.
 Svedahl, K. and MacIntosh, B.R., 2003. Anaerobic threshold: the concept and methods of measurement. Canadian journal of applied physiology, 28(2), pp.299-323.
 Buchheit, M., Solano, R. and Millet, G.P., 2007. Heart-rate deflection point and the second heart-rate variability threshold during running exercise in trained boys. Pediatric Exercise Science, 19(2), pp.192-204.
Register to the mailing list
and try the HRV4Training app!
1. Intro to HRV
2. HRV 101
3. How to use HRV, the basics
4. HRV guided training
5. The big picture
6. HRV and training load
7. HRV, strength & power
1. Context & Time of the Day
3. Paced breathing
4. Orthostatic Test
5. Slides HRV overview
6. rMSSD vs SDNN
7. Normal values and historical data
1a. Acute Changes in HRV
1b. Acute Changes in HRV (population level)
1c. Acute Changes in HRV & measurement consistency
1d. Acute Changes in HRV in endurance and power sports
2a. Interpreting HRV Trends
2b. HRV Baseline Trends & CV
3. Tags & Correlations
4. Ectopic beats & motion artifacts
5. HRV4Training Insights
6. HRV4Training & Sports Science
7. HRV & fitness / training load
8. HRV & performance
9. VO2max models
10. Repeated HRV measurements
11. VO2max and performance
12. HR, HRV and performance
13. Training intensity & performance
14. Publication: VO2max & running performance
15. Estimating running performance
Camera & Sensors
1. ECG vs Polar & Mio Alpha
2a. Camera vs Polar
2b. Camera vs Polar iOS10
2c. iPhone 7+ vs Polar
2d. Comparison of PPG sensors
3. Camera measurement guidelines
4. Validation paper
5. Android camera vs Chest strap
6. Zoom HRV vs Polar
7. Apple Watch and HRV
8. Scosche Rhythm24
9. Apple Watch
1. Features and Recovery Points
2. Daily advice
3. HRV4Training insights
4. Sleep tracking
5. Training load analysis
6a. Integration with Strava
6b. Integration with TrainingPeaks
6c. Integration with SportTracks
6d. Integration with Genetrainer
6e. Integration with Apple Health
6f. Integration with Todays Plan
7. HRV4T Coach advanced view
8. Acute HRV changes by sport
9. Remote tags in HRV4T Coach
10. VO2max Estimation
11. Acute stressors analysis
12. Training Polarization
13. Custom desirable range / SWC
14. Lactate Threshold Estimation
15. Functional Threshold Power(FTP) Estimation for cyclists
16. Aerobic Endurance analysis
1. HRV normal values
2. HRV by sport
3. HRV normalization by HR