{"id":"W4240488179","doi":"10.32920/ryerson.14653605.v1","title":"Athlete Health Prediction Using Machine Learning Methods","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Machine learning; Random forest; Computer science; Artificial intelligence; Boosting (machine learning); Ensemble learning; Predictive modelling; Task (project management); Upsampling; Class (philosophy); Data mining; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00176649,0.00065718,0.0008718029,0.002242269,0.0002827208,0.001044844,0.0008585312,0.0008981375,0.002051077],"category_scores_gemma":[0.00479735,0.0002824614,0.0008185968,0.001260997,0.0002173688,0.0007494829,0.00052646,0.001058876,0.0008061685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000586205,"about_ca_system_score_gemma":0.0006135792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007486567,"about_ca_topic_score_gemma":0.006207022,"domain_scores_codex":[0.9994053,0.0002055531,0.00004136057,0.0001642071,0.0001258147,0.00005777343],"domain_scores_gemma":[0.9979461,0.001303751,0.0002007714,0.0001081872,0.0003704095,0.00007070188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001599821,0.0002946839,0.03684587,0.0001010094,0.0001856425,0.0001090182,0.00004561456,0.7479059,0.0006545219,0.001786249,0.004458779,0.2074527],"study_design_scores_gemma":[0.000002879879,0.00001303977,0.001570266,0.00001106516,0.000005669989,0.000009225681,0.00000787948,0.9968187,0.0001146955,0.001255082,0.0001881218,0.000003480141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2220268,0.003117931,0.7616259,0.001692909,0.0003458299,0.0002119741,0.002940748,0.001913215,0.006124591],"genre_scores_gemma":[0.896115,0.001007268,0.09676887,0.0002076012,0.0002942392,0.0001682666,0.0025848,0.00004663868,0.002807393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007486567,"threshold_uncertainty_score":0.01488602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09394424712436228,"score_gpt":0.3969218102149389,"score_spread":0.3029775630905766,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}