{"resourceId":"moganan-rae-ai-loading-screening-2026-07-22","versions":[{"version":"external-3c51094a43cc226436c7ac2be50fb4df5710a35c0a83c3640c8cf28f8879c57d","resource":{"id":"moganan-rae-ai-loading-screening-2026-07-22","title":"Frontiers: Malaysian university RAE confirmed, but Holomotion AI loading-risk indices show no birth-quartile differences","organization":"Sultan Idris Education University / National Sports Institute of Malaysia / Frontiers in Sports and Active Living","sector":"University sport talent ID / AI markerless screening","geography":"Malaysia (national-level university athletes); international open-access journal","publishedAt":"July 22, 2026","publicationDate":"2026-07-22","eventDate":null,"sourceName":"Frontiers in Sports and Active Living","sourceLabel":"Peer-reviewed cross-sectional study (PDF)","sourceUrl":"https://www.frontiersin.org/journals/sports-and-active-living/articles/10.3389/fspor.2026.1884958/pdf","evidenceClass":"academic-research","outcomeClass":"mixed","topics":["developers-agents","governance-procurement","operating-model","accessibility-workforce"],"finding":"Moganan et al. assessed 170 national-level Malaysian university athletes (116 male, 54 female; mean age 18.6) with Holomotion markerless motion capture, deriving total movement score, exercise risk score, joint-pain risk index, and ligament-strain risk index (modelled tissue loading, not clinical injuries). Significant relative age effect overall (χ²(3)=11.74, p=.008, w=0.26) and in males (p=.036; Q1:Q4=2.06), not females (p=.286; underpowered). Kruskal–Wallis tests found no birth-quartile differences on any AI-derived loading outcome (all p≥.720; η²≈0); binary high-risk classifications similarly null. Authors caution cross-sectional design cannot speak to prospective injury.","sledRelevance":"Unarchived July 2026 university-athlete AI screening result that contradicts the intuition that selection asymmetries leave AI-detectable loading signatures—useful control evidence for athletics buyers of markerless risk AI after recent high-metric injury-model editions.","evidence":"Opened Frontiers PDF states methods, χ²/RAE statistics, Kruskal–Wallis nulls across four AI outcomes, modelled-vs-clinical caveat, and limitations (cross-sectional; female power; Malaysian context).","architectureImplications":"If deploying markerless AI screens, store raw kinematics, separate modelled loading from injury labels, and validate against demographic strata before operational alerts.","governanceImplications":"Prohibit using AI loading scores to justify or correct relative-age selection decisions without prospective injury evidence.","securityPrivacyImplications":"Markerless full-body video of university athletes requires consent, retention limits, and restricted coach dashboards for risk labels.","caveats":"Malaysia university/national pathway—not NCAA; cross-sectional; AI indices are modelled loading; female RAE non-significance likely Type II; transferability limits apply.","streamIds":["college-athletics"],"roles":{"sales":"Sales framing: Talent and sports-med buyers tempted to treat AI markerless loading risk scores as explanations for relative-age selection should see this null: Malaysian university athletes show RAE, but Holomotion AI loading indices do not differ by birth quartile. Sell validation of AI risk tools against known selection biases before roster or medical use. Unsupported: that null proves no injury differences prospectively, or U.S. NCAA transfer.","engineering":"Engineering framing: Fit is external validity testing for markerless AI movement-risk products in university sport. Architecture: motion-capture risk indices with pre-registered outcomes; compare against demographic strata (birth quartile); keep clinical injury labels separate from modelled tissue loading. Prerequisites: clear cut-offs, sex-stratified power, prospective injury link. Constraints: Malaysia university sample; cross-sectional; female subsample underpowered for RAE; indices are modelled loading not clinical events. Security: biomechanical video under consent. Proof of value: pre-registered null/alternative tests vs selection covariates.","delivery":"Delivery framing: If deploying Holomotion-like AI screens, forbid using loading scores to explain birth-quartile selection; require prospective injury endpoints before clinical decisions. Dependencies: sports science, coaching, IRB. Ownership: sports medicine owns clinical interpretation. Risks: overreading AI risk labels as talent fairness metrics."},"roleDetails":{"sales":{"customerProblem":"Vendors market AI movement-risk scores that departments may wrongly treat as talent-equity or injury destiny signals.","stakeholders":["Sports medicine","Pathway coaches","Analytics","Compliance"],"discoveryQuestions":["Are risk indices clinical events or modelled loading?","Was the tool validated against selection biases?","What prospective injury endpoint exists?"],"valueHypothesis":"Demonstrating null association with known RAE strata can prevent misuse of AI loading scores in selection narratives.","potentialEngagement":"Validation study design review for one markerless AI screen against demographic strata.","unsupportedClaims":["Prospective injury proof","NCAA transfer","Female RAE absence as proven"]},"engineering":{"fit":"Validation harness for AI markerless loading indices in university athletes.","architectureIntegration":"Capture to vendor indices to research warehouse with birth-quartile and sex covariates to pre-registered tests.","prerequisites":["Consent","Outcome definitions","Power analysis","Injury surveillance plan"],"constraints":["Cross-sectional","Malaysia sample","Modelled not clinical injury","Female n=54"],"security":"Secure markerless video and derived biomechanics; limited coach display of risk labels.","proofOfValue":["Pre-registered analysis report","Calibration vs injuries when available"]},"delivery":{"work":"Pilot screen as research assist only; educate coaches on null RAE-loading finding; plan prospective follow-up.","dependencies":["IRB","Coaching buy-in","Vendor data export"],"ownership":"Sports medicine leads clinical meaning; research lead owns validation.","skillsAdoption":"Teach staff difference between modelled loading and injury events.","governanceCheckpoints":["No selection use gate","Sex-powered analysis gate"],"acceptanceCriteria":["Written prohibited uses","Documented null/alternative results","Prospective plan dated"],"risks":["Label misuse in selection","False reassurance","Underpowered subgroup claims"]}},"retrievedAt":"2026-10-03T22:17:05-05:00","enrichedAt":"2026-10-03T22:18:14-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Risk labels can stigmatize athletes if shown without counseling; staff need clear not-a-diagnosis scripting.","procurementImplications":"Require vendors to disclose whether outputs are clinical events or modelled loading and to support demographic validation exports.","operatingModelImplications":"Keeps AI movement screens in research/assist mode until prospective injury links exist.","sourceVerification":{"responseId":"curl-frontiers-rae-20261003T221705","openedUrl":"https://www.frontiersin.org/journals/sports-and-active-living/articles/10.3389/fspor.2026.1884958/pdf","referenceExcerpt":"A significant RAE was observed overall","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}