Category: Data Analytics

Athlete running on treadmill monitored by researchers analyzing performance data on computer screens
Data Analytics, performance, research, Scientific publication, Sports Science

From Splits to Heat Strain: A Ten-Year Triathlon Study Built End-to-End with AI

Regular readers will know I have spent the last couple of months playing with AI agents to scrape and visualise publicly available sport data — first football muscle injuries, then a live dashboard for the Giro d’Italia. Those were fun, low-stakes experiments to learn what the tools could do. This post is the point where the experiment turned into something more serious: a full research study, now posted as a preprint, built almost entirely with the same family of AI tools.

I planned, conducted and executed this study — and developed the accompanying digital twin — using Claude Sonnet 5 and Claude Opus, together with Claude Cowork, Claude Code and Claude Design. Cowork orchestrated the data gathering and organisation across ten years of race results and weather records, Code built the statistical models and the digital twin engine, and Design shaped how the outputs are presented. I stayed firmly in the loop throughout as the domain expert: setting the research questions, checking the physiology and the methodology at every step, validating the data, and deciding what the numbers actually meant. I also modified some of the coding as things progressed to develop various analytics steps.

Why triathlon, why heat

Triathlon is an Olympic sport, and elite Olympic-distance racing is shaped by the interplay of swim-bike-run pacing, transition efficiency, the quality of the field, and — increasingly — the heat athletes race in. Major championships are more and more often held in hot conditions, which matters enormously for how athletes and support staff plan training, pacing, cooling and acclimatization. Despite there being a decade of publicly available race results and weather records out there, nobody had linked the two together at scale. That gap was the starting point.

The study had four aims: characterise the performance signature of a podium finish; reconstruct the thermal environment of championship venues over ten years; identify which athletes seem resilient to heat; and, building on all of that, prototype a digital twin that could support race planning.

Ten years of racing, in numbers

The dataset ended up covering 7,415 athlete-race records across 339 events and 3,060 unique athletes, with wet-bulb globe temperature (WBGT) at those races ranging from a mild 7.1°C to a much more challenging 28.0°C.

A few things stood out. Bike and run splits each contribute roughly equal unique variance to total race time, but the run leg is the real discriminator between the podium and the rest — it was the single most important feature in the podium-prediction models, at 45.5% importance for men and 48.9% for women. Somewhat counter-intuitively, the slope linking heat to performance did not reach statistical significance for either sex (men p=0.065, women p=0.104), which is a useful reminder not to over-interpret heat effects from headline temperature alone. DNF rates, on the other hand, told a clearer story, ranging from 12.7–16.3% for men and 11.7–18.8% for women across World Triathlon’s Green and Blue flag heat-risk categories.

Building the digital twin

The last aim — and the part I am most excited about — was turning ten years of descriptive analysis into something forward-looking. The digital twin prototype couples a performance model with a thermo-physiological heat-strain model, so it can be used to explore pacing, cooling and acclimatization decisions ahead of a race rather than just explaining results after the fact. On a temporal hold-out (training on earlier years, testing on later ones — the fairest test for something meant to inform future decisions), it achieved a mean absolute error of 0.490 z-units for men and 0.468 for women (r=0.383 and 0.295 respectively). Those are honest, prototype-grade numbers, not a finished predictive tool, and I say so explicitly in the paper.

The usual health warning

This is a preprint. It has not been peer reviewed, and I want to be upfront about that rather than let the AI-workflow angle overshadow it. The underlying data are scraped from publicly available sources, so they carry all the usual caveats about completeness and accuracy that come with that. What I can say is that the statistical approach, the modelling choices and the interpretation were all reviewed and directed by me at every stage — the AI tools accelerated the mechanics of gathering, structuring, analysing and building, but the scientific judgement was, and had to be, human. Critical thinking stays firmly the job of the person in the loop, whatever is doing the typing.

Why this matters to me

I hope this prototype is the beginning of something bigger rather than a one-off curiosity. There is an enormous amount of publicly available data across sport that nobody has the time to properly interrogate and organise — results archives, weather records, GPS feeds, injury registries. What changed for me this year is that a single person, using these AI tools well, can now plan, run and analyse a study of this scale in weeks rather than requiring a full research team and many months. I want to keep using that capability to ask more questions like this one across sports science and sports medicine, and to be transparent about the process as I develop more tools and research questions.

If you want to dig into the full methods, results and figures, the preprint is here: From Splits to Heat Strain: A Ten-Year Analysis of Performance Determinants and a Digital Twin Prototype for Olympic-Distance Triathlon Developed Using a Generative AI Workflow (DOI: 10.21203/rs.3.rs-10216961/v1). As always, comments and critique are very welcome — that is rather the point of putting it out as a preprint while it goes through formal peer review.

Analytics, Data, Data Analytics, High Intensity training, Sports Science

What’s New in the Lactate Threshold App: Anaerobic Speed Reserve, Flexible Training Zones, Maximum Speed and More

The Lactate Threshold app started as a simple tool to turn a step test into a clean set of threshold values. Over the past few development cycles it has grown into something closer to a complete profiling and prescription workspace. This post walks through the most significant additions — anaerobic speed reserve, maximum speed determination, switchable 3- and 5-zone models — and the smaller refinements that came with them.

Anaerobic Speed Reserve (ASR)

The headline feature is the ability to determine an athlete’s anaerobic speed reserve — the velocity range that sits between the speed at maximal oxygen uptake (vVO2max, or maximal aerobic speed) and maximal sprinting speed (MSS). Everything an athlete does above their aerobic ceiling happens inside this band, which is exactly why it matters for events decided by surges, kicks and repeated high-intensity efforts.

The concept owes much to the work of Dr Gareth Sandford and colleagues, who showed that ASR and maximal sprint speed are “untapped tools” for differentiating the world’s best middle-distance runners and for understanding the complexity of athlete profiles that traditional aerobic categories miss. Two athletes with an identical vVO2max can have very different reserves above it — and therefore very different tolerances to supramaximal work — information that is invisible if you only look at threshold and VO2max.

Dr. Martin Buchheit’s research extends this directly into programming. Prescribing high-intensity work as a percentage of maximal aerobic speed alone ignores the differing mechanical ceilings between individuals, so the same session can impose very different relative stress on two athletes. Anchoring supramaximal efforts to a percentage of the ASR instead normalises that stress, and the evidence shows it reduces the inter-individual variability of physiological adaptation. The app now makes that calculation a single step rather than a spreadsheet exercise.

Maximum Speed Determination

Because ASR depends on having a reliable upper anchor, the app now supports maximum sprint speed (MSS) determination as a first-class input. Enter the result of a short maximal sprint and the app uses it as the top of the reserve, pairing it with the aerobic anchor derived from the step test. This closes the loop: from a single profiling session you get the threshold values, the aerobic speed, the sprint ceiling, and the reserve that connects them.

Flexible Training Zones: 3 or 5

Training-zone prescription is now configurable. You can choose between a 3-zone model — the classic below-LT1, between-thresholds, above-LT2 structure favoured in polarised approaches — and a more granular 5-zone model for coaches who want finer resolution across the intensity spectrum. Zones are generated directly from the athlete’s own threshold and speed anchors rather than from generic percentages, so the prescription reflects the individual profile the test produced.

Switching between the two models takes a tap, which makes it easy to align the output with whichever periodisation philosophy a given athlete or training block calls for.

Other Improvements

Alongside the marquee features, this round of work brought a number of refinements: cleaner presentation of the threshold detection results, a more consistent workflow from data entry through to zone output, and better handling of the speed-based inputs that the ASR and MSS features rely on. The aim throughout has been to keep the app fast to use rink-side or track-side while quietly adding depth for those who want it.

Development is ongoing, and I’ll keep posting updates here as new capabilities land. If you’re using the app and have feedback or feature requests, I’d be glad to hear them. If you use it for any purposes make sure you reference it:

Cardinale, M. (2026). Lactate Threshold and HIT designer [Web application]. Retrieved from https://lactatethresholdhitdesigner.netlify.app.

⚠️ UPDATE 1st June 2026 ⚠️: I have now added the option for Cycling Tests.

A note for team-sport coaches: if you are specifically after a tool to plan HIIT sessions with change-of-direction (COD) prescriptions, I’d recommend Dr Martin Buchheit’s dedicated COD shuttle prescription app, available here. It is purpose-built for that use case and complements the profiling work the Lactate Threshold app is designed for. A screenshot is below.

Key References

  • Sandford GN, Allen SV, Kilding AE, Ross A, Laursen PB. Maximal Sprint Speed and the Anaerobic Speed Reserve Domain: The Untapped Tools that Differentiate the World’s Best Male 800 m Runners. Sports Medicine, 2019.
  • Sandford GN, Laursen PB, Buchheit M. Anaerobic Speed/Power Reserve and Sport Performance: Scientific Basis, Current Applications and Future Directions. Sports Medicine, 2021.
  • Buchheit M, Laursen PB. High-Intensity Interval Training, Solutions to the Programming Puzzle. Part II: Anaerobic Energy, Neuromuscular Load and Practical Applications. Sports Medicine, 2013.
Data Analytics, Sports Science, youth sports

Protecting Young Athletes: reflections from my talk at the 1st CYSM Conference in London

Last Friday I had the pleasure of speaking in London at the Centre for Youth Sports Medicine (CYSM) Annual Conference 2026, on a topic close to my heart: how we protect young athletes while helping them develop. My talk was titled “Protecting young athletes: performance progressions, realistic expectations and injury prevention,” and what follows is a short summary of what I covered, the science behind it, and a new project I shared at the end

Young athletes are not mini-adults

The starting point of the talk is a simple but frequently ignored idea: a young athlete is not a scaled-down version of a senior one. Youth development sits on an individually unique and constantly changing base of physical growth, biological maturation and behavioural development. Because of this, success at an early age does not guarantee success at senior level, and selection systems in most sports quietly favour early maturers — children who happen to be bigger and stronger sooner, not necessarily those with the most long-term potential.

This matters because the way we coach, test and select needs to account for where a child actually is in their development, not simply how many years have passed since their birth.

Age is not just a number

A large part of the talk dealt with the difference between three kinds of age:

  • Chronological age — years since birth.
  • Training age — how many years a young person has spent in structured training.
  • Biological age — where the individual actually sits on the maturation curve, based on physiological markers.

Two children of the same chronological age can be years apart biologically. Around the growth spurt — the period of Peak Height Velocity (PHV) — this gap becomes especially important for training and injury risk. I walked through the methods we use to assess maturity status and timing, from skeletal age estimation (Tanner–Whitehouse, Greulich–Pyle, Fels) to anthropometric approaches based on height, leg length and body mass. I also flagged an important caution from our own work: prediction methods developed on one population can systematically over- or under-predict in another, so the difference between skeletal and chronological age should be used to put test results into context rather than as an absolute truth (for some recent work on this, read this paper from Dr Lorenzo Lolli here).

Talent, the relative age effect, and the road from youth to senior

I then turned to talent identification and the relative age effect — the well-documented bias in which athletes born early in the selection year are over-represented in youth squads and ranking lists. Across athletics and team sports such as Italian football, the data show how strongly birth-quarter skews youth selection. Yet relatively younger or later-maturing athletes often progress better when they transition to senior level — the so-called “underdog hypothesis.”

This connects to one of the central findings I shared, drawn from analyses of tens of thousands of athletes’ careers: early success is not a prerequisite for success as an adult. In jumping events in track and field, only around 8% of males and 16% of females ranked in the world top 50 at age 16 went on to reach the top 50 as seniors. In sprints, on average only about 17% of men and 21% of women were in the top 50 both as under-18s and as seniors. Different pathways can lead to similar outcomes, and many talented juniors never make the transition — for reasons ranging from maturation and selection bias to injury, burnout, loss of funding, or simply moving to another sport.

Injuries and load in young athletes

The final scientific section focused on injury. Young athletes face a distinct set of growth-related conditions — Osgood-Schlatter disease at the knee, Sever’s disease at the heel, gymnast’s wrist, Little League shoulder and elbow, apophysitis around the hip, and more. Our own prospective work in a full-time athletics academy was, to our knowledge, the first to examine growth rates and skeletal maturation as injury risk factors in a large adolescent cohort engaged in full time athletics. We found that rapid growth in stature and leg length, a younger skeletal age and a faster maturity tempo were all associated with an increased risk of bone and growth-plate injuries.

This raises hard questions about how we manage load. Most studies still quantify training simply as “time,” without accounting for what athletes actually do in that time — two athletes can train for the same number of hours doing completely different work. Better load monitoring, including the thoughtful use of wearables and AI, is one of the areas where I think we can genuinely improve.

The book chapter: The Young Athlete

Much of this material is drawn together in a chapter I co-authored with Gennaro Boccia, Paolo Riccardo Brustio, James Baker and Eirik Halvorsen Wik — Chapter 9, “The Young Athlete,” in the Sports Physician Handbook (Fourth Edition of the FIMS Team Physician Manual), edited by Pitsiladis, Yung, Hutchinson and Pigozzi (Academic Press, 2026, pp. 199–235, the link the book is here).

The chapter brings together the themes of the talk into a single reference for clinicians and practitioners: defining the elite young athlete, understanding growth and maturation and why they matter, the relative age effect and the junior-to-senior transition, performance progression and realistic expectations, and the prevention and management of youth injuries and illness — including data from recent Youth Olympic Games.

A thank you to the CYSM, ISEH and the audience

I want to thank the Center for Youth Sports Medicine and the Institute of Sport, Exercise and Health for hosting me and for the care they put into convening this event. The ISEH has been a genuine centre of excellence for sport and exercise medicine since its creation as a legacy of the 2012 London Olympic Games, and its commitment to the health of young athletes is exactly the kind of leadership this field needs. I was equally grateful for the audience — the questions, the engagement and the obvious dedication of so many practitioners to getting this right. Youth sport sits at the intersection of health, development and performance, and it is genuinely encouraging to see so much interest in protecting the young people at the centre of it.

Bringing athletics data to life: a new (experimental) project

One recurring frustration in this area is that the data needed to put a young athlete’s results into context — how the best in the world actually developed over time — is hard to access and harder to compare against. So I have been building something to help coaches interested in Athletics.

I am sharing here an early look at the Athletics Performance Tracker, an AI-assisted project that brings athletics results databases to life and makes them accessible to everyone. The aim is to let coaches, athletes, parents and researchers explore how performance develops with age and compare a young athlete’s results against those of top-ranked athletes.

It currently covers around 30 World Athletics events with thousands of athletes and tens of thousands of performances, and includes:

  • Development curves showing how the world’s best progress from age 12 to 40, with mean values and confidence intervals across the top 10, 20, 50 or 100 athletes.
  • Year-on-year analysis of absolute and percentage improvements for individual athletes or whole cohorts.
  • World top lists for every event, with comparisons to the previous year.

You can explore it here: athletics-tracker.fly.dev.

An important caveat: this is very much an experimental project and still under active development. It is intended for research and exploration, it is not affiliated with World Athletics, and features and data will continue to change. I would welcome feedback as it evolves.

In summary

Early success is not a requirement for success as an adult. Assessing maturity status is key to interpreting training and test results. Training should be progressive, varied and developmentally appropriate, and we need to understand injury patterns — and load — far better than we currently do, with more work needed on young female athletes in particular. Above all, health and longevity in sport should always come before performance at a young age. If we get that balance right, we give more young athletes the chance to fulfil their potential — and to stay healthy doing it.