{"id":"W4399013580","doi":"10.2196/59680","title":"Is Boundary Annotation Necessary? Evaluating Boundary-Free Approaches to Improve Clinical Named Entity Annotation Efficiency: Case Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Annotation; Computer science; Boundary (topology); Information retrieval; Natural language processing; Data mining; Artificial intelligence; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02263596,0.001501308,0.001090887,0.002278775,0.001280879,0.002124501,0.002165582,0.002577162,0.001235733],"category_scores_gemma":[0.05578799,0.0005116272,0.001221112,0.001930458,0.00124468,0.003203992,0.002687151,0.001460108,0.000749744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002031251,"about_ca_system_score_gemma":0.001596654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004567425,"about_ca_topic_score_gemma":0.005239975,"domain_scores_codex":[0.9863153,0.00832463,0.001154094,0.002307116,0.001550785,0.000348169],"domain_scores_gemma":[0.9351792,0.04957693,0.002803676,0.005261,0.006235687,0.0009436186],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005227504,0.002220911,0.09243552,0.005149535,0.0008819777,0.003963755,0.008674208,0.1516732,0.03045985,0.004823888,0.01335999,0.6811297],"study_design_scores_gemma":[0.0005375718,0.003638524,0.05118015,0.0008721758,0.001109672,0.004184576,0.005149188,0.812237,0.08915498,0.009220521,0.0223627,0.0003529157],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7939178,0.004837139,0.1917346,0.001156428,0.0002404659,0.001021857,0.001025318,0.002511251,0.003555161],"genre_scores_gemma":[0.7685136,0.001071226,0.226017,0.0002762758,0.0001057959,0.0004641435,0.002245701,0.0003824016,0.0009238328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9773641,"threshold_uncertainty_score":0.1197118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.132606346198434,"score_gpt":0.4013234067763562,"score_spread":0.2687170605779222,"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."}}