{"id":"W4387116260","doi":"10.1186/s40634-023-00662-4","title":"Accelerated evidence synthesis in orthopaedics—the roles of natural language processing, expert annotation and large language models","year":2023,"lang":"en","type":"article","venue":"Journal of Experimental Orthopaedics","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Göteborgs Universitet","keywords":"Annotation; Natural language processing; Computer science; Natural language; Data science; Linguistics; Artificial intelligence; Philosophy","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1377492,0.001490689,0.002799762,0.008316714,0.001590109,0.01171988,0.003484219,0.003475546,0.01366701],"category_scores_gemma":[0.5042319,0.002272058,0.003041062,0.004568704,0.002815271,0.01094952,0.005671476,0.005938631,0.002795688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002660853,"about_ca_system_score_gemma":0.01463356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003706679,"about_ca_topic_score_gemma":0.007840944,"domain_scores_codex":[0.9003575,0.08051383,0.005482618,0.005357761,0.007817745,0.0004705422],"domain_scores_gemma":[0.3117784,0.6286334,0.01180714,0.02408553,0.02119215,0.002503371],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00202383,0.0004042577,0.008857798,0.01299865,0.002945505,0.0006104232,0.003677386,0.02954969,0.00493707,0.06899168,0.04844787,0.8165559],"study_design_scores_gemma":[0.0008992659,0.0004204079,0.007379354,0.00401886,0.001489995,0.0005839789,0.001567616,0.2025619,0.007156605,0.6981159,0.07537995,0.0004260787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.021506,0.02673062,0.8962682,0.03618824,0.002035658,0.001374714,0.005024128,0.003846572,0.007025837],"genre_scores_gemma":[0.2220442,0.007223412,0.759297,0.002270779,0.001332332,0.001239891,0.003145846,0.001263583,0.002182838],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8622508,"threshold_uncertainty_score":0.728496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03212934952285237,"score_gpt":0.3233232041138951,"score_spread":0.2911938545910428,"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."}}