{"resourceId":"lnipe-preprint-ml-injury-risk-ncaa-di-cohort-unverified-2026-10-17","versions":[{"version":"external-4aefe0d56ab36c442b596c9d5517be2b4a7eb56611d459ac7fa9e83cdc2f84d0","resource":{"id":"lnipe-preprint-ml-injury-risk-ncaa-di-cohort-unverified-2026-10-17","title":"Self-archived paper claims XGBoost injury model (AUC 0.89) and 34% fewer injuries in an unnamed NCAA Division I cohort, but provenance and design limit trust","organization":"Lakshmibai National Institute of Physical Education (LNIPE), Guwahati, India (authors); deposited on Zenodo","sector":"Sports medicine and athlete support","geography":"Study claims a single unnamed NCAA Division I institution (United States); authors based in India","publishedAt":"Zenodo record published October 17, 2026 (PDF states published October 15, 2026)","publicationDate":"2026-10-17","eventDate":null,"sourceName":"Zenodo (Bhattacharjee, Bhattacharjee and Das)","sourceLabel":"Self-archived research paper","sourceUrl":"https://zenodo.org/records/23432801","evidenceClass":"academic-research","outcomeClass":"cautionary","topics":["data-security","governance-procurement","operating-model"],"finding":"The paper reports a two-season prospective cohort of 412 NCAA Division I athletes in six sports (388 analyzed, 8,946 athlete-weeks, 204 injuries) combining GPS/IMU load, neuromuscular tests, wellness self-reports and injury history. Using athlete-grouped cross-validation, XGBoost reached AUC 0.89 (sensitivity 0.85, specificity 0.88) versus logistic regression at 0.75; lowering the threshold to 0.35 raised sensitivity to 0.93 but cut specificity to 0.76. In season two, athletes above a 0.65 risk score were referred to sports medicine, who used clinical judgement on load changes. The authors report four-week injury incidence of 8.9% versus 13.5% in season-one high-risk athletes who were not referred, a 34% decrease, and state this is observational, not randomized. The paper does not name the institution or the approving board beyond 'the Institutional Review Board', and lists the authors as two master's students and an assistant professor at an Indian physical-education institute. Its limitations section cites a single institution, few rare-injury events and the observational design.","sledRelevance":"Why now: deposited October 17, 2026 and not archived. Collegiate injury-prediction claims like this are what vendors and staff may cite when buying athlete-monitoring AI. Interpretation: the claimed AUC is far above the 0.70 reported by the archived Frontiers collegiate cohort (Sep 30), and two recent reviews opened this run say external validation is rare and internal validation inflates estimates. That makes this a cautionary example of an attractive figure without verifiable provenance.","evidence":"Self-archived paper on Zenodo; the PDF shows received/accepted/published dates but no journal name, and peer review could not be confirmed. No data or code availability statement was found. Internal validation only; the intervention comparison uses a historical control.","architectureImplications":"Describes a weekly pipeline joining wearable load, jump testing, wellness questionnaires and injury records into rolling 7- and 28-day features, with SHAP explanations on a staff risk dashboard. Interpretation: this data integration, not the model choice, is the main build effort for any department.","governanceImplications":"Model flags were referred to clinicians rather than acted on automatically, a human-in-the-loop design worth copying. Interpretation: provenance gaps (unnamed site and board, no data statement) mean buyers should not treat the reported effect as evidence.","securityPrivacyImplications":"Combines biometric, wellness and medical-history data on student-athletes, which brings HIPAA (where applicable) and FERPA boundaries, consent and access controls into scope. The paper says consent was obtained but gives no data-handling detail.","caveats":"Unverifiable site and ethics approval; no journal identified; internal validation only; observational historical comparison; internal inconsistencies (wellness compliance described as 'low' at 91.4%). Treat all figures as author claims.","streamIds":["college-athletics"],"roles":{"sales":"Sales framing: injury-prediction claims are a strong selling point for athlete-monitoring AI, and this paper offers headline numbers that are hard to verify. Interpretation: sports medicine leaders may value an independent evidence check before buying tools that cite similar figures. A bounded offer is an evidence review of vendor injury-prediction claims against validation standards. Do not cite the 34% reduction or AUC 0.89 as proof; the site is unnamed and the design is observational.","engineering":"Engineering framing: the paper describes a sensible feature pipeline — rolling load ratios, jump asymmetry, wellness and prior injury — with athlete-grouped cross-validation and SHAP explanations. The weak point is validation: no external or temporal hold-out on another site. Proof of value for any department is a temporally separated test on its own historical data, with calibration and false-alarm rates reported. Applicability depends on consistent wearable compliance and reliable injury records.","delivery":"Delivery framing: the useful element here is the referral workflow — flags go to sports medicine, who decide on load changes. Interpretation: departments piloting similar tools should define the risk threshold, the clinician response and the false-alarm burden before go-live, and track outcomes against a concurrent comparison group rather than last season. Acceptance should rest on clinician-reviewed decisions and calibration, not headline AUC."},"roleDetails":{"sales":{"customerProblem":"Sports medicine teams are offered AI injury-risk tools backed by impressive but unverified accuracy and reduction claims.","stakeholders":["Head athletic trainer and team physicians","Director of sports performance","Strength and conditioning coaches","University compliance and privacy office","Athletics IT"],"discoveryQuestions":["Has the model been validated on a different institution or season?","What false-alarm rate can staff absorb each week?","Who reviews flags, and what actions follow?","Which medical and wellness data would the tool hold, and under what consent?","Can the vendor share calibration results?"],"valueHypothesis":"A clinician-reviewed risk flag could help focus load-management attention, if validated locally and calibrated.","potentialEngagement":"An evidence and validation review of an injury-prediction tool using the department's own historical data before purchase.","unsupportedClaims":["A 34% injury reduction","AUC 0.89 transferring to another program","Causal injury prevention","Peer-reviewed status"]},"engineering":{"fit":"Departments with consistent GPS/IMU use, routine jump testing, daily wellness reporting and reliable injury records.","architectureIntegration":"Weekly join of wearable load, neuromuscular testing, wellness and injury-history data into rolling features feeding a gradient-boosted model and SHAP dashboard for sports medicine.","prerequisites":["Clean multi-season injury records","High wearable and questionnaire compliance","Data-sharing agreement between performance and sports medicine","Defined referral threshold"],"constraints":["Single-site evidence only","Rare injuries poorly predicted","HIPAA and FERPA boundaries on medical data","Observational evidence for benefit"],"security":"Medical history and biometric data require role-based access, audit logs, consent records and retention limits, and must stay within sports medicine control.","proofOfValue":["Temporal hold-out test on the department's own prior season","Report calibration and weekly false-alarm counts","Compare outcomes with a concurrent, not historical, group","Clinician review of a sample of flags"]},"delivery":{"work":"Build the data pipeline, validate locally, set the referral workflow and monitor flags and outcomes.","dependencies":["Sports medicine sign-off","Wearable vendor data access","Injury surveillance records","Privacy office review"],"ownership":"Head athletic trainer or team physician, with sports performance as data steward.","skillsAdoption":"Clinicians need to read SHAP explanations and probabilities; coaches need to accept that flags prompt review, not automatic load cuts.","governanceCheckpoints":["Privacy and consent review before data integration","Local validation report before use","Monthly false-alarm and outcome review","Annual model revalidation"],"acceptanceCriteria":["Proposed: local temporal-validation AUC and calibration reported before go-live","Proposed: every flag reviewed by a clinician within 48 hours","Proposed: weekly false alarms below an agreed ceiling"],"risks":["Overreliance on inflated accuracy figures","Alert fatigue from false positives","Medical data exposure","Misattributing injury changes to the model"]}},"retrievedAt":"2026-10-19T22:12:55-05:00","enrichedAt":"2026-10-19T22:19:40-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Adds interpretation work for athletic trainers; staff need training to use probabilistic flags alongside clinical judgement.","procurementImplications":"Vendor claims citing studies like this should be checked for external validation, named sites and data availability before purchase.","operatingModelImplications":"Places an AI referral step between performance data and sports medicine decisions, requiring clear ownership of the threshold and response.","sourceVerification":{"responseId":"curl-zenodo-23432801-20261020T031255Z","openedUrl":"https://zenodo.org/records/23432801","referenceExcerpt":"XGBoost had an AUC of 0.89","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}