{"id":"W4200219457","doi":"10.1145/3483411","title":"Computer-Assisted Cohort Identification in Practice","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Computing for Healthcare","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Computer science; Machine learning; Artificial intelligence; Classifier (UML); Strengths and weaknesses; Cohort; Identification (biology); Data mining; Statistics; Psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0008666164,0.0001836673,0.0002553777,0.0002436632,0.0003504099,0.0002321058,0.001027036,0.0001293303,0.00000187224],"category_scores_gemma":[0.0002799813,0.0002210305,0.00009824447,0.0009556751,0.00002806477,0.0005313671,0.00005636667,0.0003607137,0.00001353192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002622317,"about_ca_system_score_gemma":0.0002850926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002542788,"about_ca_topic_score_gemma":0.0002005205,"domain_scores_codex":[0.9976315,0.0002764757,0.0005918685,0.0008006518,0.0003071741,0.0003922622],"domain_scores_gemma":[0.996374,0.001193384,0.0002101054,0.001624824,0.0004876937,0.0001100063],"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":[0.00002033708,0.0004482302,0.0008329814,0.0001167378,0.00004256837,0.00004081057,0.0007217241,0.0007820683,0.000134134,0.005760749,0.0004808832,0.9906188],"study_design_scores_gemma":[0.00487443,0.00232073,0.172587,0.002401338,0.0002149429,0.001780617,0.001564978,0.7074401,0.03854699,0.02492379,0.04045628,0.00288884],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005489881,0.00007798603,0.9785588,0.01375493,0.0008273828,0.0005284444,0.00004416281,0.0006404399,0.0000779595],"genre_scores_gemma":[0.4314193,0.00002830009,0.5674451,0.0009052156,0.000052763,0.00005190799,0.00005958422,0.00001595524,0.00002187341],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9877299,"threshold_uncertainty_score":0.9013361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0432534408866383,"score_gpt":0.3560104240515721,"score_spread":0.3127569831649338,"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."}}