{"id":"W4379280031","doi":"10.1007/978-3-031-34344-5_21","title":"BERT for Complex Systematic Review Screening to Support the Future of Medical Research","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Workflow; Task (project management); Systematic review; Encoder; Data science; Transformer; Artificial intelligence; Data mining; Machine learning; Information retrieval; Database; MEDLINE","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.01372286,0.0003726739,0.001094233,0.0007243808,0.000357087,0.0002866504,0.009834318,0.0003008288,0.00002490012],"category_scores_gemma":[0.001160359,0.0002487005,0.0002227949,0.001338327,0.0004915532,0.0001928452,0.003399136,0.001054363,0.00003890893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001362362,"about_ca_system_score_gemma":0.0008623029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002885138,"about_ca_topic_score_gemma":0.0001557443,"domain_scores_codex":[0.9921676,0.0001749778,0.001125123,0.001336896,0.004382004,0.0008133987],"domain_scores_gemma":[0.9933636,0.00284159,0.0003121071,0.002448423,0.0007702734,0.000263978],"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":[0.00000792998,0.00003191378,0.000007782296,0.09901012,0.00006686654,0.0001084062,0.002273341,0.00669102,0.00002221755,0.2125962,0.002745948,0.6764383],"study_design_scores_gemma":[0.000215105,0.0003238848,0.00001197442,0.1045082,0.00003596671,0.000108101,0.000002110385,0.8339071,0.00004312095,0.05659956,0.003689257,0.0005557009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000001394368,0.003037237,0.9714674,0.02132367,0.001184967,0.002568306,0.000007722973,0.000095179,0.0003140934],"genre_scores_gemma":[0.006085038,0.001822669,0.9685447,0.01889305,0.002565666,0.0004165895,0.00001942575,0.0001309427,0.001521964],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.827216,"threshold_uncertainty_score":0.9999965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.135825626249986,"score_gpt":0.3828264763855156,"score_spread":0.2470008501355296,"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."}}