{"id":"W4387104185","doi":"10.1101/2023.09.26.23295361","title":"An unsupervised machine learning approach to predict recovery from traumatic spinal cord injury","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Spinal Cord Injury Research","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; International Collaboration On Repair Discoveries; Vancouver Coastal Health; University of Saskatchewan","funders":"International Foundation for Research in Paraplegia; Wings for Life; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Spinal cord injury; Rehabilitation; Physical medicine and rehabilitation; Mean squared error; Matching (statistics); Medicine; Physical therapy; Clinical trial; Population; Artificial intelligence; Spinal cord; Machine learning; Computer science; Statistics; Mathematics; Internal medicine","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":[0.003209844,0.00058477,0.0009011419,0.001784814,0.000271638,0.0008113119,0.0009082651,0.0008824579,0.0008494836],"category_scores_gemma":[0.007635172,0.0002050276,0.0008096062,0.0008315777,0.0003706653,0.0004401185,0.0006303991,0.0008513035,0.0003146788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007481413,"about_ca_system_score_gemma":0.0009490422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002783457,"about_ca_topic_score_gemma":0.00240514,"domain_scores_codex":[0.9987034,0.0007068294,0.0001028209,0.000262971,0.0001540076,0.00006993048],"domain_scores_gemma":[0.9968522,0.002103671,0.000406772,0.0002392012,0.0003063839,0.00009175937],"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":[0.0004857572,0.0005319362,0.04216775,0.0001450909,0.0006111578,0.0001467576,0.00006683132,0.7510373,0.0021582,0.002452922,0.002295142,0.1979012],"study_design_scores_gemma":[0.00001419521,0.0001150813,0.003047517,0.00001238974,0.00002297074,0.00003158375,0.000008004478,0.9925743,0.0005008676,0.003423143,0.0002399459,0.000009961904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2465878,0.001416888,0.745786,0.0007556042,0.0001055732,0.0003323462,0.001624541,0.001373171,0.002018009],"genre_scores_gemma":[0.9356364,0.0001800774,0.06143351,0.0001779767,0.00008081319,0.000312701,0.001191235,0.00004561727,0.0009415602],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003209844,"threshold_uncertainty_score":0.01697546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1239137648368182,"score_gpt":0.3892634714382369,"score_spread":0.2653497066014186,"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."}}