How MicroPulse Detects Neuromuscular Fatigue: Locating the Fatigue, Not Just Flagging It

A countermovement jump — the standard hop where a player dips and explodes upward on a force plate — is one of the best objective fatigue tools in sport. But on its own it has a blind spot: it measures net output. A lower jump tells you the player produced less, not whether the cause is a tired nervous system, damaged muscle tissue, or a whole-body dip in sleep and stress. Physiologists have made this point for decades (Gandevia, 2001): the same drop in force can come from very different places. That matters because the fix is different for each. Central (neural) fatigue clears with rest and sleep in hours; peripheral (tissue) fatigue from eccentric muscle damage can linger for days and needs load protection, not just a nap. So the useful question isn't "is his jump down?" — it's "his jump is down, because of what?" MicroPulse is built to answer the second question from data it already collects.

MicroPulse splits neuromuscular fatigue into three labelled types and reads each from a different signal it already has: NEURAL — the explosive, nervous-system-driven qualities. A drop in the jump's peak power, rate of force development (how fast force is built) or concentric impulse points to reduced central drive. Early-phase RFD in particular is neural-dominated and falls before jump height does (D'Emanuele, 2021). TISSUE — the muscular/peripheral qualities. When the jump's timing changes — a longer eccentric (lowering) phase, a longer contraction time — while height barely moves, the player is quietly changing his jump strategy to protect sore tissue. These time-and-eccentric metrics stay abnormal longest after muscle damage (Gathercole, 2015). SYSTEMIC — the whole-body picture. Poor sleep, low energy, high stress and multi-day readiness declines from the daily check-in point to global fatigue that rest, not tissue work, resolves. The daily wellness check-in, the CMJ and the load data each light up a different axis; read together they locate the fatigue rather than just flag it.

A jump plate is precise, but not every wobble is real. The fatigue-sensitive timing metrics are also the noisiest — rate of force development can vary ~16% between two of the same player's tests, versus ~5% for jump height (Gathercole, 2015). Surfaced raw against a small personal baseline, that noise would fire a false "declining" flag on a normal day — the classic over-sensitive-yellow trap. So every CMJ metric must clear its own measurement noise before it can flag: the change has to exceed the larger of the metric's known variability and the player's own observed variability, by a margin. A noisy metric like RFD needs a much bigger move to mean anything than a quiet one like jump height. And every comparison is against the player's own baseline, not a league average — because fatigue thresholds are individual, not shared (Neyroud, 2016). MicroPulse also compares the mean of the session's jumps, not the single best, which catches fatigue and supercompensation more reliably than a max effort (Edwards, 2018; Claudino, 2017).

Two refinements make the read earlier and sharper. First, early-phase rate of force development — how fast force rises in the first 100–200 milliseconds — drops before jump height and is dominated by neural drive, making it an early-warning flag for central fatigue (D'Emanuele, 2021). It is measured as a windowed, force-normalised slope (never an instantaneous peak, which is too noisy). Second, the flight-time-to-contraction-time ratio (FT:CT) — how much air the player gets per unit of push time — is more fatigue-sensitive in team-sport athletes than the popular RSI-modified, which was found insensitive in basketball and rugby (Edwards, 2018). MicroPulse now treats FT:CT as the primary explosive-quality metric and keeps RSI-modified as a secondary read rather than leaning on it. None of these bypass the noise gate above — they inherit it.

A low jump two days after a match can be completely normal — the question is whether it is low on the expected curve, or below it. MicroPulse models the expected post-match jump dip per player, driven by how much high-speed running (>5.5 m/s) he did in that match — not total distance. The evidence is specific: for every 100 m of high-speed running, CMJ peak power drops about 0.5% and muscle-damage markers rise ~30% at 24 hours; total distance predicts neither (Hader, 2019). The expected dip is deepest in the first 0–48 hours and can still be present at 72 hours — jumps recover more slowly than sprinting (Nédélec, 2012; Silva, 2018). So the system builds an expected band as a percentage of the player's own baseline at each hour after the match, and compares his actual jump to it. Inside the band → recovering on schedule. Below it → "recovering slower than expected," which feeds the tissue/peripheral read and shows the coach the numbers: "48 h post-match: jump at 88% of baseline — expected ~92–100% for this match's high-speed running → recovering slower than expected."

One principle governs all of this: the neuromuscular-fatigue read never moves the player's readiness colour. The traffic-light verdict a coach sees comes from the personal-norm readiness engine; the fatigue type is a distinct, labelled interpretation layer next to it — it explains and contextualises, it does not override. A green player recovering slowly still shows green, with the recovery note as added context, not a downgrade. The read also states its own confidence and its gaps honestly. No recent jump, or no high-speed-running data for the match, means no verdict and lowered confidence — never a silent "no fatigue." Every driver names the metric it is built on and cites the paper behind it, so a coach can see the reasoning and a physio can drill into it. That is the whole design: measure objectively, locate the fatigue, explain it in plain language — and leave the decision with the coach.

D'Emanuele, S., Maffiuletti, N. A., Tarperi, C., Rainoldi, A., Schena, F., & Boccia, G. (2021). Rate of force development as an indicator of neuromuscular fatigue: A scoping review. Frontiers in Human Neuroscience, 15, 701916. https://doi.org/10.3389/fnhum.2021.701916 Carroll, T. J., Taylor, J. L., & Gandevia, S. C. (2017). Recovery of central and peripheral neuromuscular fatigue after exercise. Journal of Applied Physiology, 122(5), 1068–1076. https://doi.org/10.1152/japplphysiol.00775.2016 Gathercole, R., Sporer, B., Stellingwerff, T., & Sleivert, G. (2015). Alternative countermovement-jump analysis to quantify acute neuromuscular fatigue. International Journal of Sports Physiology and Performance, 10(1), 84–92. https://doi.org/10.1123/ijspp.2013-0413 Edwards, T., Spiteri, T., Piggott, B., Bonhotal, J., Haff, G. G., & Joyce, C. (2018). Monitoring and managing fatigue in basketball. Sports, 6(1), 19. https://doi.org/10.3390/sports6010019 Claudino, J. G., Cronin, J., Mezêncio, B., McMaster, D. T., McGuigan, M., Tricoli, V., Amadio, A. C., & Serrão, J. C. (2017). The countermovement jump to monitor neuromuscular status: A meta-analysis. Journal of Science and Medicine in Sport, 20(4), 397–402. https://doi.org/10.1016/j.jsams.2016.08.011 Hader, K., Rumpf, M. C., Hertzog, M., Kilduff, L. P., Girard, O., & Silva, J. R. (2019). Monitoring the athlete match response: Can external load variables predict post-match acute and residual fatigue in soccer? A systematic review with meta-analysis. Sports Medicine – Open, 5, 53. https://doi.org/10.1186/s40798-019-0219-7 Neyroud, D., Kayser, B., & Place, N. (2016). Are there critical fatigue thresholds? Aggregated vs. individual data. Frontiers in Physiology, 7, 376. https://doi.org/10.3389/fphys.2016.00376 Nédélec, M., McCall, A., Carling, C., Legall, F., Berthoin, S., & Dupont, G. (2012). Recovery in soccer, part I: Post-match fatigue and time course of recovery. Sports Medicine, 42(12), 997–1015. Silva, J. R., Rumpf, M. C., Hertzog, M., Castagna, C., Farooq, A., Girard, O., & Hader, K. (2018). Acute and residual soccer match-related fatigue: A systematic review and meta-analysis. Sports Medicine, 48(3), 539–583. Gandevia, S. C. (2001). Spinal and supraspinal factors in human muscle fatigue. Physiological Reviews, 81(4), 1725–1789. Note: References are formatted in APA 7th edition style; details verified against publisher and PubMed records.