{"id":"W3178029650","doi":"10.1016/j.jbi.2021.103864","title":"Development of a generalizable natural language processing pipeline to extract physician-reported pain from clinical reports: Generated using publicly-available datasets and tested on institutional clinical reports for cancer patients with bone metastases","year":2021,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Pipeline (software); Medicine; Computer science","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":[0.001820154,0.002171065,0.0008432942,0.003983861,0.0006290567,0.001501564,0.001385944,0.001140846,0.004800575],"category_scores_gemma":[0.006162251,0.0007240726,0.002269258,0.002128907,0.0002809648,0.001391285,0.001587962,0.001525146,0.005852227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000806859,"about_ca_system_score_gemma":0.003228376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01808545,"about_ca_topic_score_gemma":0.02557496,"domain_scores_codex":[0.9988939,0.0001746908,0.0001702603,0.0004423078,0.0002106386,0.0001081274],"domain_scores_gemma":[0.9971245,0.001439968,0.000214034,0.0003220522,0.0007573618,0.0001419523],"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":[0.001399791,0.001528838,0.04602175,0.003463568,0.001271561,0.002509578,0.001470604,0.02454751,0.06878597,0.002635506,0.2887266,0.5576388],"study_design_scores_gemma":[0.0006924433,0.0007226102,0.07194856,0.0004208128,0.0008492614,0.002740075,0.001750523,0.7068785,0.07021215,0.01222778,0.1312392,0.00031806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1124898,0.001668313,0.3911177,0.00254626,0.0006758941,0.002959282,0.2832936,0.2017421,0.003507056],"genre_scores_gemma":[0.1329415,0.000630532,0.4379558,0.000515666,0.0001882087,0.001653478,0.4212384,0.001815998,0.003060481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01808545,"threshold_uncertainty_score":0.03596038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07284276618582329,"score_gpt":0.3608962595140042,"score_spread":0.2880534933281809,"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."}}