[Research] Intensity as the Primary Driver of Autonomic Change (In Team Sports Too!)
A new study brings HRV analysis to Basketball players, showing similar patterns to what we have seen in endurance athletes.
Last week I was in contact with Jorge Abruñedo, author of the study “An Explainable Machine Learning Approach to Explain the Effects of Training and Match Load on Ultra-Short-Term Heart Rate Variability in Semi-Professional Basketball Players“ (full text here), in which, as the title says, they monitored semi-professional basketball players over a full season, combining daily HRV4Training measurements with training load and contextual variables, and then used an explainable machine learning approach (Gradient Boosting + SHAP) to understand which load components had the largest impact on day-to-day HRV, and how these responses differed between athletes.
I’ve talked about HRV in team sports a few times, and recently co-authored an article on HRV in football, highlighting how the same principles apply, but also how we don’t have much data due to the complexities of working in team settings. Hence, it was nice to see a new study being able to track HRV for a long time in a (small) group of semi-professional Basketball players.
What the Basketball Study Shows
Five players were tracked for around seven months using daily RMSSD measurements collected with HRV4Training. Training load was captured through simple and reliable metrics: session RPE, duration, and match minutes. Days were categorized as training, match, or rest, allowing the authors to compare how different stress exposures impacted next-morning physiology.
Matches, which naturally include higher intensity, resulted in lower morning HRV. In contrast, normal training days (regardless of duration) did not meaningfully reduce next-morning HRV, as we can see from the paper’s data:
What I liked the most is that the authors did not limit the findings to group-level analysis, as the one above, but then looked at the relationship between various potential predictors of HRV changes and HRV, for each athlete individually.
They did so using an explainable machine learning model, which highlighted how RPE (or perceived effort, which I have discussed here) was the most important predictor of HRV changes, followed by the number of days since the last match. Hence, intensity was the most important parameter:
What Drives Autonomic Changes and Why?
When we look at how athletes respond to training from a physiological perspective, one pattern emerges over and over: intensity drives the largest changes in autonomic state. Duration matters, volume matters, but neither produces the magnitude of disruption that high-intensity work does. Jorge’s study of semi-professional basketball players using HRV4Training offers a clear confirmation of this principle.
Even with a small sample, the findings align almost perfectly with what we already understand from exercise physiology and studies in endurance athletes. Morning HRV (measured first thing after waking) was strongly suppressed the day after matches, while regular training sessions produced little to no measurable change. Similarly, perceived effort was the strongest correlate with HRV changes.
These results are entirely consistent with what we see across the literature. High-intensity exercise produces large autonomic shifts, marked by increased sympathetic activity, reduced parasympathetic tone, and measurable hormonal changes. Catecholamines rise, cortisol increases, and the body is pushed further away from homeostasis. HRV simply reflects this disturbance.
On the other hand, low-intensity exercise often has a positive effect on the nervous system. As discussed in my analysis of low-intensity training, which you can find here, even substantial increases in duration rarely create the kind of autonomic perturbation caused by a single intense session, while low-intensity exercise can reduce cortisol and increase HRV. Seiler’s work also shows that doubling session duration has far less impact than performing one high-intensity workout. Intensity drives the response, which is why in HRV-guided training, it’s intensity that I’d recommend scaling down, more than exercise time.
Wrap-up
Effective training requires knowing when to push and when to hold back. HRV-guided frameworks provide a structured way to make these decisions by aligning daily training stimulus with the athlete’s current physiological state. I’ve discussed the evolution of this approach, as well as practical guidance on applying it, in my writing on HRV-guided training. Timing matters.
This recent study on Basketball players adds yet another data point to a growing body of evidence: intensity is what challenges the system most, HRV captures this reliably, and morning measurements captured with HRV4Training offer a simple, cost-effective, and actionable way to keep training aligned with recovery.
Thanks again, Jorge and co-authors, for using our app for your studies, and looking forward to reading your future work!
Personal Coaching for Runners
If you are interested in working with me, please learn more here, and fill in the athlete intake form, here.
How to Show Your Support
No paywalls here. All my content is and will remain free.
As a HRV4Training user, the best way to help is to sign up for HRV4Training Pro.
Thank you for supporting my work.
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 is a certified ultrarunning coach.
Marco 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:
Substack
Strava
Instagram
