{"id":"W3211439143","doi":"10.2196/27210","title":"A Question-and-Answer System to Extract Data From Free-Text Oncological Pathology Reports (CancerBERT Network): Development Study","year":2021,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Topic Modeling","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Alberta Health Services","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Terminology; SNOMED CT; Named-entity recognition; Pathology; Deep learning; Information retrieval; Medicine; Linguistics","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":[0.002490372,0.001028766,0.0004371952,0.001098755,0.0003114268,0.0008302681,0.001962889,0.001243934,0.007873648],"category_scores_gemma":[0.005464146,0.0004765602,0.0006637853,0.0005662933,0.000424902,0.00355539,0.001280766,0.001408512,0.005608228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001127791,"about_ca_system_score_gemma":0.001792061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01068799,"about_ca_topic_score_gemma":0.009901321,"domain_scores_codex":[0.9989986,0.0002827119,0.00006683627,0.0002946874,0.0002795102,0.00007765908],"domain_scores_gemma":[0.9965288,0.001899872,0.000131593,0.0002995452,0.0009351504,0.000204973],"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":[0.001191094,0.0021539,0.0096131,0.001724416,0.0002380708,0.00140145,0.001372017,0.02102517,0.05611581,0.006394966,0.09005897,0.8087111],"study_design_scores_gemma":[0.000502148,0.001910405,0.01235726,0.0002845366,0.0002193944,0.002042063,0.0008727735,0.7507362,0.1081719,0.003526517,0.1191704,0.0002064232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3376039,0.003369079,0.4575252,0.002542256,0.0007489149,0.003997927,0.01993209,0.1550085,0.01927199],"genre_scores_gemma":[0.3359288,0.001595642,0.5645797,0.001498359,0.0001313483,0.001955151,0.06236663,0.001867676,0.0300767],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01068799,"threshold_uncertainty_score":0.02634001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1647109952524415,"score_gpt":0.4493167053224617,"score_spread":0.2846057100700201,"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."}}