{"id":"W2012510097","doi":"10.1007/s10926-013-9430-4","title":"Development of a Computer-Based Clinical Decision Support Tool for Selecting Appropriate Rehabilitation Interventions for Injured Workers","year":2013,"lang":"en","type":"article","venue":"Journal of Occupational Rehabilitation","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"Workers Compensation Board of Alberta; University of Toronto; Public Health Ontario; University of Manitoba; Institute for Work & Health; Alberta Health; University of Alberta","funders":"","keywords":"Rehabilitation; Psychological intervention; Machine learning; Population; Categorization; Medicine; Artificial intelligence; Workers' compensation; Physical therapy; Applied psychology; Physical medicine and rehabilitation; Computer science; Psychology; Nursing; Compensation (psychology)","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":[0.003809066,0.001409741,0.001554623,0.00302618,0.0005759111,0.002775027,0.002068546,0.001424461,0.01116308],"category_scores_gemma":[0.02012788,0.0007498022,0.0007430617,0.001367521,0.0002712428,0.001711415,0.00106284,0.001044268,0.002496249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00068058,"about_ca_system_score_gemma":0.002115773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00378178,"about_ca_topic_score_gemma":0.003199483,"domain_scores_codex":[0.9982659,0.0005279591,0.0003832909,0.0002853099,0.0004528722,0.00008463683],"domain_scores_gemma":[0.9774161,0.01789456,0.000901342,0.0005474141,0.002430947,0.0008097258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004943717,0.003184951,0.01994689,0.001170499,0.0004548486,0.00121746,0.0009702284,0.01418115,0.01651511,0.001367219,0.03917637,0.8968716],"study_design_scores_gemma":[0.00521703,0.004374087,0.03702386,0.001594523,0.001286687,0.004067092,0.001581936,0.8304104,0.0560953,0.007811502,0.04984208,0.0006955148],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.198693,0.00091927,0.68346,0.002524115,0.0006160209,0.00826493,0.00746452,0.08928622,0.008771984],"genre_scores_gemma":[0.259481,0.0003326196,0.7312937,0.0006370714,0.0001268026,0.002757124,0.002583365,0.0004567942,0.002331545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01116308,"threshold_uncertainty_score":0.03734422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05086849456533966,"score_gpt":0.4176875835885615,"score_spread":0.3668190890232218,"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."}}