Lighthouse AdvisorySLED AI Adoption Intelligence

Higher Education & ResearchIssue 093 records

College Athletics

Three newly archived sources pair a Division I on-device coaching-AI announcement with measured collegiate multi-sensor fatigue modeling and independent scrutiny of wearable consent and NCAA guidance limits. ASU/Intel projects prep-time savings without published measurement; Xu reports strong within-study fatigue AUC that still needs local U.S. revalidation; Duke argues performance-tech recommendations remain non-binding amid fragmented privacy law. One pattern links monitoring-model evidence to athlete-data controls. Recruiting/compliance outcomes, facilities, Division III, and audited ROI remain gaps.

Evidence records
3
Cross-source patterns
1
Evidence classes
1 vendor claim1 academic research1 independent research
Outcomes
1 emerging1 mixed1 cautionary
Source freshness
1 new this fortnight1 older, newly relevant1 recent
Research completed
2026-09-15

Choose a role to see its takeaway beside every record in the ledger.

Patterns across the evidence

Synthesis · Lighthouse Advisory interpretation

1 pattern, each supported by at least two sources

  1. Treat fatigue-monitoring accuracy and athlete-data rights as joint acceptance tests

    Xu shows multi-sensor ML can outperform single load indicators for fatigue classification in a collegiate cohort, while Duke shows U.S. wearable/performance-tech practice still rests on non-binding NCAA guidance and uneven consent. Together they support requiring both prediction-quality checks and enforceable purpose/access/consent controls before routine use. Neither proves U.S. injury reduction or that any specific vendor stack is compliant.

    Operating questionBefore a fatigue or readiness model influences practice or medical decisions, which accuracy thresholds and which athlete consent, access, retention, and secondary-use limits must both be met?

    Supporting evidenceGuizhou Normal University (School of Physical Education)Duke University Deep Tech / Tech Policy Program

Evidence ledger

Full record · every source keeps its link and limitations

3 records
  1. Vendor claimEmergingNew this fortnight

    ASU football projects prep-time savings from an on-device play-card AI agent

    Intel describes a six-month ASU football proof-of-concept: a local AI agent on Lenovo/Intel vPro laptops that maps opponent film to digital play-card diagrams, with coaching staff expecting up to 15–20% less game-prep time and on-device handling of playbooks, health metrics, and film.

    Intel / Arizona State University AthleticsUnited States (Arizona; Division I football)2026-09-04

    Why it matters, evidence and limitations
    Why it matters
    Why now: first major attributed U.S. Division I coaching-workflow agent claim found in this research window that was not yet in the college-athletics archive, despite publication shortly before the 2026-09-13 edition. Speaks directly to coaching operations and local-data architecture for athletic departments.
    Evidence and measured results
    Newsroom bullets and body state Intel–ASU collaboration, custom play-card agent behavior (upload film → identify positions/movement → whiteboard drawings), projected 15–20% prep-time reduction, and on-device IP/privacy framing. Named ASU athletics staff quote on efficiency. No independent measurement table is provided.
    Limitations and uncertainty
    Projected—not measured—savings; vendor authorship; no published accuracy of formation/route extraction; not evidence of wins, injury reduction, or transferable ROI for smaller programs.
    Vendor newsroom announcement Role takeaways & implementation
  2. Academic researchMixedNewly relevant · Feb 2026

    Collegiate soccer study: multi-sensor ML beats single load markers for fatigue prediction

    In 48 male collegiate players monitored 12 weeks, an XGBoost model fusing GPS, heart-rate, wellness and related features predicted operationally defined fatigue with AUC 0.895 (LOSO 0.847), outperforming sRPE- or ACWR-only models; wellness, ACWR and morning HRV dominated feature importance.

    Guizhou Normal University (School of Physical Education)China (university football/soccer team)2026-02-18

    Why it matters, evidence and limitations
    Why it matters
    Why now: fills the archive gap on measured collegiate multi-sensor fatigue modeling (not just vendor claims or injury-review caution). Newly relevant alongside continuing U.S. wearable adoption debates even though the cohort is Chinese collegiate rather than NCAA.
    Evidence and measured results
    Prospective design; 536 sessions + 24 matches; reported correlations (e.g., Player Load vs TRIMP r=0.81); Table 5 model metrics; SHAP/feature ranks; explicit limitations on sample, season coverage, and missing biochemical gold standard. Fatigue is a composite label (≥2 of CMJ drop, HRV drop, low wellness, high RPE), not confirmed injury.
    Limitations and uncertainty
    Not U.S. NCAA; male-only; fatigue≠injury prevention proof; single institution; equipment-specific; academic calendar effects incompletely controlled.
    Peer-reviewed research article Role takeaways & implementation

How to read this edition

Source findings, measured results and limitations come from the cited publications. Patterns, operating questions, role takeaways and implementation considerations are Lighthouse Advisory interpretation, stated as questions to validate locally rather than guaranteed outcomes. Vendor and operator claims are labeled as claims. Full research method.

Vendor claim
A supplier-provided assertion that has not been upgraded to independent evidence.
Academic research
Research produced through an academic institution or peer-reviewed venue.
Independent research
Research conducted outside the implementing organization.