{"id":"W4290944545","doi":"10.1145/3534678.3542675","title":"Automatic Phenotyping by a Seed-guided Topic Model","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Inference; Computer science; Topic model; Machine learning; Artificial intelligence; Bayesian inference; Source code; Prior probability; Vocabulary; Natural language processing; Bayesian probability; Data science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.00440188,0.001023565,0.001280499,0.002605442,0.000768343,0.001634142,0.002651284,0.001579295,0.00246516],"category_scores_gemma":[0.01263438,0.000946254,0.002228431,0.002566776,0.0007172727,0.002303644,0.001851131,0.002279076,0.00151589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001261518,"about_ca_system_score_gemma":0.002151579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02135822,"about_ca_topic_score_gemma":0.03142092,"domain_scores_codex":[0.9980165,0.0007439831,0.0001200147,0.0007616094,0.0002125316,0.0001453948],"domain_scores_gemma":[0.9925783,0.005782578,0.0002928044,0.0005867283,0.0006072733,0.0001522773],"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":[0.001395539,0.0004838325,0.09751209,0.0007674703,0.0007186952,0.001165878,0.003523418,0.2797492,0.01701395,0.07238176,0.06276914,0.4625191],"study_design_scores_gemma":[0.00008818589,0.00002473394,0.003076951,0.0000514375,0.00007896448,0.0001794958,0.00008700868,0.9532216,0.001397581,0.03707407,0.004688293,0.00003174095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04088304,0.0007483593,0.9492942,0.0008181927,0.00006868021,0.0001662749,0.004075778,0.003076717,0.00086884],"genre_scores_gemma":[0.4380885,0.0008773024,0.5305647,0.0006769002,0.0002986286,0.0005809713,0.02464075,0.0008313424,0.003440879],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02135822,"threshold_uncertainty_score":0.04246783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08150570998099894,"score_gpt":0.3294082098277484,"score_spread":0.2479024998467494,"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."}}