{"id":"W203690341","doi":"10.1007/978-3-642-40017-9_9","title":"Using Machine Learning to Plan Rehabilitation for Home Care Clients: Beyond “Black-Box” Predictions","year":2013,"lang":"en","type":"book-chapter","venue":"Intelligent systems reference library","topic":"Frailty in Older Adults","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Machine learning; Health care; Artificial intelligence; Computer science; Black box; Resource (disambiguation); Resistance (ecology); Plan (archaeology); Rehabilitation; Perception; Data science; Knowledge management; Medicine; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000130694,0.0007172502,0.001070497,0.0007829696,0.0002053948,0.0001881115,0.0003699054,0.0007922139,0.0009498898],"category_scores_gemma":[0.0002001375,0.0006617442,0.000319478,0.00012383,0.0001391828,0.0005628332,0.0002008378,0.000972352,0.0009644902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004308115,"about_ca_system_score_gemma":0.0002770621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002018445,"about_ca_topic_score_gemma":0.00001680681,"domain_scores_codex":[0.9963786,0.00008292547,0.001311722,0.001014247,0.0006783171,0.0005341673],"domain_scores_gemma":[0.9971728,0.0004934577,0.0005030787,0.000878804,0.0004330413,0.0005188259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005681173,0.001243401,0.0597838,0.08128673,0.006546309,0.0003678635,0.07995832,0.03332068,0.002248901,0.2911169,0.3612175,0.07722843],"study_design_scores_gemma":[0.0008560747,0.002829623,0.0002422014,0.01158149,0.0004313481,0.0001010265,0.002704334,0.006596043,0.000219485,0.001605892,0.9717698,0.001062653],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0222564,0.01722035,0.02596814,0.003042415,0.01099909,0.03532125,0.009002937,0.003285092,0.8729043],"genre_scores_gemma":[0.1202947,0.0005469402,0.008453981,0.0003817359,0.001869633,0.0006809294,0.009769612,0.0005761547,0.8574263],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6105524,"threshold_uncertainty_score":0.9999634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05372047603595827,"score_gpt":0.2862023989486295,"score_spread":0.2324819229126712,"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."}}