{"id":"W3041337690","doi":"10.1164/ajrccm-conference.2020.201.1_meetingabstracts.a4781","title":"Using Machine Learning to Develop and Validate a Pragmatic Conversion Formula Between ACT and ACQ Scores in Patients with Asthma","year":2020,"lang":"en","type":"article","venue":"","topic":"Heart Failure Treatment and Management","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Computer science; Asthma; Artificial intelligence; Machine learning; Natural language processing; 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":[0.02401277,0.0007352221,0.001370733,0.001213257,0.0007768525,0.002952229,0.001023898,0.001399868,0.00126757],"category_scores_gemma":[0.09119638,0.0005525814,0.001078822,0.001146992,0.0008210247,0.001223097,0.001280078,0.003143118,0.0005548294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001252084,"about_ca_system_score_gemma":0.001651766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002839121,"about_ca_topic_score_gemma":0.004014079,"domain_scores_codex":[0.9803104,0.01214117,0.002249084,0.001478323,0.003519383,0.0003015999],"domain_scores_gemma":[0.94729,0.04128549,0.003588941,0.002056729,0.00533057,0.0004483666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002376492,0.00128981,0.7881365,0.0004572387,0.001300529,0.0002225358,0.0007923231,0.01274457,0.001458769,0.003638073,0.007063162,0.18052],"study_design_scores_gemma":[0.001064134,0.003585049,0.5971036,0.0008123097,0.00109456,0.001484437,0.001287542,0.3614122,0.006032453,0.0153169,0.01058918,0.0002176741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8791878,0.001865525,0.1024781,0.002542842,0.0008604999,0.001091746,0.001235945,0.000597194,0.01014046],"genre_scores_gemma":[0.9580144,0.0001691756,0.03955888,0.0005065291,0.00008596712,0.0004807668,0.0005858394,0.00004376519,0.0005545595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02401277,"threshold_uncertainty_score":0.1269932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02501514153444859,"score_gpt":0.2643827489085752,"score_spread":0.2393676073741266,"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."}}