{"id":"W4402473640","doi":"10.1109/ccece59415.2024.10667245","title":"Adapting Large Language Models for Automatic Annotation of Radiology Reports for Metastases Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Annotation; Artificial intelligence; Natural language processing","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":[0.003221545,0.001635776,0.0008719325,0.002870386,0.0005711034,0.001741528,0.002318128,0.001365768,0.001215876],"category_scores_gemma":[0.009759118,0.0008080166,0.002280236,0.001751686,0.0004221715,0.00248213,0.001098914,0.002251402,0.002580994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001279931,"about_ca_system_score_gemma":0.001779608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01814032,"about_ca_topic_score_gemma":0.03272371,"domain_scores_codex":[0.998354,0.0005824431,0.000163048,0.0005578565,0.0002254103,0.0001173576],"domain_scores_gemma":[0.9914005,0.00615044,0.0005387645,0.0007440635,0.001006312,0.0001598088],"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":[0.0009515437,0.0008743239,0.02689724,0.000792664,0.0006658753,0.0008153365,0.000991895,0.2902848,0.03128271,0.003382326,0.03166493,0.6113964],"study_design_scores_gemma":[0.00002747164,0.00005774385,0.00210915,0.00002383861,0.00008376688,0.0001378218,0.0001011776,0.9865259,0.004492356,0.002686092,0.003720635,0.00003417799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1227461,0.002572681,0.8391684,0.001434636,0.0004139763,0.0004558847,0.00726385,0.02385212,0.00209233],"genre_scores_gemma":[0.5365109,0.001259725,0.4317301,0.0006427054,0.0004124787,0.0007974526,0.02303733,0.001095862,0.004513469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01814032,"threshold_uncertainty_score":0.03606945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03076148918633741,"score_gpt":0.2961688213673668,"score_spread":0.2654073321810294,"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."}}