Hytive← Back to hytive.app

Product method

How Hytive calculates training estimates

Hytive's current model is deterministic: the same inputs produce the same output. Published research informs its structure, but it does not validate Hytive as a medical product or make its estimates injury predictions.

What the model returns

Hytive combines supported workouts and recovery inputs into three views: recent load compared with a longer-term baseline, a 0 to 100 readiness estimate, and estimated residual load across eight body systems. Suggested next sessions are ranked from those same outputs and include a plain-language reason.

Inputs and calculation

  • Session load uses duration, an intensity value, and a sport demand profile.
  • Catalogued sports distribute that load across legs, push, pull, grip, core, aerobic, anaerobic, and impact channels.
  • Each channel decays over time using a documented model half-life.
  • Load balance compares a recent weighted average with a longer-term weighted average and stays hidden until at least 14 days of history exist.
  • Readiness combines HRV, sleep, and resting heart rate against the athlete's rolling baselines.

What is personalised

Load and fatigue are normalised to the athlete's own training history. HRV and resting heart rate are compared with personal baselines. The sport demand profiles and recovery half-lives are population-level starting points rather than individual measurements.

Important limits

  • Sport demand vectors and channel half-lives are research-informed expert estimates.
  • An uncatalogued activity receives a balanced full-body fallback rather than a sport-specific profile.
  • Missing or stale recovery inputs can limit or withhold readiness.
  • Load-balance bands describe training relative to the user's norm. They are not validated injury-risk bands.
  • Hytive does not diagnose, prevent, or treat injury or illness and does not provide medical advice.

References

  1. Clarkson PM, Hubal MJ. Exercise-induced muscle damage in humans. American Journal of Physical Medicine & Rehabilitation. 2002.
  2. Cheung K, Hume PA, Maxwell L. Delayed onset muscle soreness: treatment strategies and performance factors. Sports Medicine. 2003.
  3. Stanley J, Peake JM, Buchheit M. Cardiac parasympathetic reactivation following exercise: implications for training prescription. Sports Medicine. 2013.
  4. Burke LM, et al. Carbohydrates for training and competition. Journal of Sports Sciences. 2011.
  5. Magnusson SP, Langberg H, Kjaer M. The pathogenesis of tendinopathy: balancing the response to loading. Nature Reviews Rheumatology. 2010.
  6. Gabbett TJ. The training-injury prevention paradox: should athletes be training smarter and harder? British Journal of Sports Medicine. 2016.
  7. Hulin BT, Gabbett TJ, et al. The acute:chronic workload ratio predicts injury: high chronic workload may decrease injury risk in elite rugby league players. British Journal of Sports Medicine. 2016.
  8. Plews DJ, Laursen PB, Stanley J, Kilding AE, Buchheit M. Training adaptation and heart rate variability in elite endurance athletes: opening the door to effective monitoring. Sports Medicine. 2013.
  9. Buchheit M. Monitoring training status with HR measures: do all roads lead to Rome? Frontiers in Physiology. 2014.
  10. Williams S, et al. A better way to determine the acute:chronic workload ratio? British Journal of Sports Medicine. 2017.
  11. Impellizzeri FM, et al. Acute:chronic workload ratio: conceptual and methodological pitfalls. International Journal of Sports Physiology and Performance. 2020.
  12. Windt J, Gabbett TJ. Is it all for naught? What does mathematical coupling mean for acute:chronic workload ratios? British Journal of Sports Medicine. 2019.
  13. Foster C. Monitoring training in athletes with reference to overtraining syndrome. Medicine & Science in Sports & Exercise. 1998.

Privacy

The deterministic model runs on the iPhone. The exact data flows and controls are described in the Privacy Policy.