{"id":"W1979643807","doi":"10.1164/rccm.201304-0694oc","title":"Challenges in Identifying Asthma Subgroups Using Unsupervised Statistical Learning Techniques","year":2013,"lang":"en","type":"article","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Asthma and respiratory diseases","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Population and Public Health","funders":"Medical Research Council","keywords":"Medicine; Asthma; Statistical learning; Unsupervised learning; MEDLINE; Natural language processing; Artificial intelligence; Machine learning; Intensive care medicine; Immunology","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":[0.06469581,0.001635014,0.003267651,0.005085863,0.001388305,0.004745684,0.005337886,0.002375811,0.001130348],"category_scores_gemma":[0.1981532,0.001046825,0.002501335,0.003416062,0.003963626,0.003182461,0.00320268,0.004665734,0.001140673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001413255,"about_ca_system_score_gemma":0.00344084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004536889,"about_ca_topic_score_gemma":0.003803334,"domain_scores_codex":[0.9553716,0.03368653,0.002290942,0.003485117,0.004872957,0.0002927423],"domain_scores_gemma":[0.7318489,0.237181,0.006119183,0.01247671,0.01140992,0.0009643113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005666832,0.0004197723,0.07474336,0.003806602,0.002894986,0.0008550401,0.003533504,0.1194082,0.006611886,0.04404443,0.0205075,0.722608],"study_design_scores_gemma":[0.000218705,0.0003030016,0.02696407,0.00115343,0.0003261886,0.001123232,0.001904819,0.4460581,0.003739237,0.504651,0.01329769,0.0002605358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01616803,0.002177561,0.972669,0.005834268,0.0001485946,0.0007219157,0.0005454978,0.000772852,0.0009621794],"genre_scores_gemma":[0.1223273,0.001066407,0.8723363,0.001498254,0.0003591062,0.001198213,0.0007116966,0.0002313914,0.0002713586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06469581,"threshold_uncertainty_score":0.3421482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05038789107092678,"score_gpt":0.355292667522937,"score_spread":0.3049047764520103,"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."}}