[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-study-detail:100659964":3},{"organization":4,"outcomesModule":7,"designInfo":14,"detailedDescription":17,"studyPopulation":18,"armGroups":19,"interventions":13,"overallOfficials":13,"centralContacts":23,"locations":29,"responsibleParty":45,"collaborators":13,"id":49,"slug":50,"hasResults":51,"nctId":52,"briefTitle":53,"officialTitle":54,"acronym":55,"eligibilityCriteria":56,"healthyVolunteers":57,"sex":58,"minAge":59,"maxAge":60,"enrollmentInfo":61,"targetDuration":13,"studyType":64,"phases":13,"briefSummary":65,"conditions":66,"keywords":69,"overallStatus":32,"whyStopped":13,"lastUpdateSubmitDate":78,"lastUpdatePostDateStruct":79,"startDateStruct":82,"completionDateStruct":84,"leadSponsor":86,"locationsCount":87},{"fullName":5,"class":6},"Palacky University","OTHER",{"primaryOutcomes":8,"secondaryOutcomes":13,"otherOutcomes":13},[9],{"measure":10,"description":11,"timeFrame":12},"Short-Term Incidence of Reduced Participation (24, 48, and 72-Hour Discrete-Time Hazard)","Daily morning consensus assessment (at 8:30 AM) of player participation recorded in the club Athlete Management System (AMS) on a 3-point ordinal scale: Full participation (0), Modified training with \\>20% volume reduction or sprint restriction due to medical\u002Fhealth complaints (1), and Complete absence due to injury or illness (2). Levels 1 and 2 are combined into a binary event of reduced participation modeled under a discrete-time survival framework with a 3-day clean washout period (W = 3) for re-entry into the risk set.","Daily assessments across one complete 10-month competitive football season (predicting transitions within 24, 48, and 72 hours).",null,{"allocation":13,"interventionModel":13,"interventionModelDescription":13,"primaryPurpose":13,"observationalModel":15,"timePerspective":16,"maskingInfo":13},"COHORT","PROSPECTIVE","STUDY DESIGN AND COHORT:\n\nThis is a prospective, longitudinal, single-site observational cohort study conducted across one complete 10-month competitive season (2026\u002F2027) within the U16 and U19 squads of an elite youth football academy (SK Sigma Olomouc, Czechia). The cohort comprises approximately 30 elite male youth football players. The unit of analysis is the at-risk player-day in full participation (longitudinal person-period array), yielding an estimated 6,000 to 8,000 observed player-days.\n\nPRIMARY OUTCOME (TARGET VARIABLE):\n\nThe primary outcome is the staff-adjudicated transition event from full participation into any lower category of the daily participation gradient (modified training with \\>20% volume reduction, reduced training intensity, or complete absence due to medical\u002Fhealth reasons). Conditional on full participation on day t, the primary modeled quantity is the one-step discrete-time onset hazard. Operational cumulative onset probabilities are read coherently across 24-, 48-, and 72-hour horizons. To ensure outcome adjudication reliability, an inter-rater agreement analysis (Cohen's kappa) is performed between independent staff members.\n\nMULTIMODAL PREDICTOR DOMAINS:\n\nCandidate predictors span eight pre-specified canonical domains (\\~31 candidate variables; \\~33-36 parameters after categorical expansion):\n\n1. Player Profile \\& Maturation: Baseline anthropometry, body composition (InBody 230: FFM, % body fat), and biological maturation offset (Mirwald equation).\n2. External Load: Catapult Vector GNSS\u002FIMU metrics (total distance, high-speed running \\>20 km\u002Fh, sprinting \\>25.2 km\u002Fh, accelerations\u002Fdecelerations \\>3.0 m\u002Fs², PlayerLoad).\n3. Internal Load: Daily heart rate telemetry and session-RPE derived metrics (training monotony and training strain).\n4. Autonomic Recovery \\& Sleep: Continuously recorded overnight via WHOOP 5.0 wrist-worn wearable bands (resting heart rate, HRV RMSSD during slow-wave sleep, sleep architecture, and skin temperature).\n5. Neuromuscular Capacity: Repeated weekly neuromuscular screening on VALD Systems (ForceFrame hip adduction\u002Fabduction and NordBord eccentric\u002Fisometric hamstring strength and bilateral asymmetries).\n6. Performance Capacity: Periodic physical testing (sprint times, change of direction, and jump mechanics).\n7. Contextual Factors: Microcycle schedule (days to\u002Ffrom match day), match congestion, and playing position.\n8. Daily Subjective Wellness: Morning perceptual ratings on a 1-5 Likert scale (Hooper index: sleep, fatigue, stress, soreness). An objective-only sensitivity model will explicitly exclude subjective wellness to prevent construct overlap and circularity.\n\nRESAMPLING AND LEAKAGE DISCIPLINE:\n\nModel evaluation operates via a calendar-aligned rolling-origin cross-validation scheme with an expanding training window and temporally subsequent held-out test blocks. To prevent data leakage across the train\u002Ftest boundary, an embedded temporal embargo of \\>=72 hours is implemented. All data-dependent preprocessing steps (imputation via MICE\u002FPMM, scaling, dimensionality reduction) are fitted strictly within the training partition of each resample and applied to held-out test data.\n\nSTATISTICAL MODELLING AND EVALUATION:\n\nPre-specified candidate models include baseline logistic regressions, Generalised Additive Mixed Models (GAMM) with player-level random intercepts, and tree-based learners (Survival XGBoost with functional monotonicity constraints). Model evaluation follows a calibration-first hierarchy (Brier score, calibration slopes\u002Fcurves), followed by discrimination under class imbalance (Precision-Recall AUC, Matthews Correlation Coefficient). Model behavior and domain contributions are interpreted using explainable artificial intelligence (XAI) frameworks (SHAP and LIME).","Elite male youth football players (categories U16 and U19) registered in a licensed national youth football academy (SK Sigma Olomouc, Czechia) competing in top-tier national youth leagues.",[20],{"label":21,"type":13,"description":22,"interventionNames":13},"Elite Youth Football Squads (U16 & U19)","Approximately 30 registered male youth football players from U16 and U19 academy squads (SK Sigma Olomouc) undergoing regular training and competitive match microcycles with continuous multimodal monitoring across one full season.",[24],{"name":25,"role":26,"phone":27,"phoneExt":13,"email":28},"David Prycl","CONTACT","775111781","david.prycl@upol.cz",[30],{"facility":31,"status":32,"city":33,"state":13,"zip":34,"country":35,"countryCode":13,"cosmosGeoPoint":36,"geoPoint":41,"contacts":42},"SK Sigma Olomouc Academy & AC Baluo, Palacký University Olomouc","RECRUITING","Olomouc","77900","Czechia",{"type":37,"coordinates":38},"Point",[39,40],17.25175,49.59552,{"lat":40,"lon":39},[43],{"name":44,"role":26,"phone":27,"phoneExt":13,"email":28},"David Prycl, Mgr.",{"type":46,"investigatorFullName":47,"investigatorTitle":48,"investigatorAffiliation":5,"oldNameTitle":13,"oldOrganization":13},"PRINCIPAL_INVESTIGATOR","Karel Hulka","doc. Mgr., Ph.D., Head of Department","100659964","multimodal-machine-learning-for-predicting-reduced-participation-in-elite-youth-football-100659964",false,"NCT07870460","Multimodal Machine Learning for Predicting Reduced Participation in Elite Youth Football","Machine Learning-Based Short-Term Prediction of Reduced Participation Within the Competitive Microcycle in Elite Youth Football Players Using Multimodal Data","PREDICT-YOUTH","Inclusion Criteria:\n\n* Registered player in the U16 or U19 squad of an elite football academy (SK Sigma Olomouc).\n* At least three years of structured football training within an organized academy programme.\n* Regular active participation in microcycle team training and competitive league matches.\n* Written informed assent by the player and written informed consent by a parent or legal guardian (for minor participants).\n* Monitoring compliance rate \\> 80% during the initial 14-day passive run-in period.\n\nExclusion Criteria:\n\n* Pre-existing severe musculoskeletal injury, orthopedic surgery, or neurological disorder preventing full participation at baseline.\n* Known cardiovascular, metabolic, or systemic disease contraindicating maximal athletic exertion.\n* Inability or refusal to wear continuous monitoring sensors (Catapult GNSS unit during training, WHOOP strap during sleep).\n* Prolonged absence from the squad due to non-medical administrative reasons (transfer, academic leave, disciplinary suspension).",true,"MALE","15 Years","19 Years",{"count":62,"type":63},30,"ESTIMATED","OBSERVATIONAL","This study protocol describes a prospective longitudinal observational study designed to evaluate the accuracy of machine learning models in predicting the short-term (24-72 h) risk of reduced participation (training modification or absence due to health complaints, injury, or illness) among elite youth football players (categories U16 to U19).\n\nFull participation in training and matches is a key determinant of athletic development and squad availability in elite youth football. Conventional injury surveillance typically reduces athlete availability to a binary time-loss state and overlooks the continuum on which athletes remain active despite emerging fatigue, minor musculoskeletal complaints, or functional limitations.\n\nIn this study, continuous multimodal monitoring integrates external training and match locomotion (Catapult Vector 10 Hz GNSS \u002F 100 Hz IMU), nocturnal autonomic nervous regulation (WHOOP 5.0 wrist-worn photoplethysmography evaluating resting heart rate, heart rate variability RMSSD, and sleep architecture), daily subjective wellness (AMS Hooper Index: sleep quality, stress, fatigue, mood, and muscle soreness), weekly neuromuscular screening (VALD ForceDecks countermovement jumps and NordBord hamstring strength), and anthropometrics with biological maturation offset.\n\nParticipation status is adjudicated daily by designated coaching and medical staff. The primary objective is to develop, compare, and internally validate short-term prediction models for the onset transition from full participation to reduced participation, formulated as a single one-step discrete-time hazard read coherently across 24-, 48-, and 72-hour operational horizons. The study aims to evaluate explainable machine learning models (Survival XGBoost, GAMM with SHAP\u002FLIME interpretation) to support training load management and injury risk mitigation within elite academies.",[67,68],"Athletic Injury","Fatigue Recovery",[70,71,72,73,74,75,76,77],"youth footbal","injury prevention","machine learning","multimodal monitoring","catapult GPS","WHOOP HRV","VALD dynamometry","reduced participation","2026-10-06",{"date":80,"type":81},"2026-10-13","ACTUAL",{"date":83,"type":81},"2026-07-15",{"date":85,"type":63},"2028-06-30",{"name":5,"class":6},1]