{"id":"W4413040066","doi":"10.3233/shti250922","title":"Human in the Loop: Embedding Medical Expert Input in Large Language Models for Clinical Applications","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Automatic summarization; Ontology; Dravet syndrome; Epilepsy; Unified Medical Language System; Artificial intelligence; Natural language processing; Data science; Medicine; Psychiatry","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":[0.005355183,0.001040949,0.0006734629,0.001233185,0.0004369646,0.001713122,0.001422287,0.001518631,0.00392427],"category_scores_gemma":[0.02443224,0.0005284834,0.00101265,0.0009446771,0.0007861348,0.003023257,0.002311238,0.00144744,0.001493794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001121568,"about_ca_system_score_gemma":0.002081912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007836538,"about_ca_topic_score_gemma":0.01248731,"domain_scores_codex":[0.9971347,0.001889558,0.0001187916,0.0003936553,0.00036803,0.00009534162],"domain_scores_gemma":[0.986488,0.01146576,0.0003826353,0.0008845194,0.0005759351,0.0002031731],"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":[0.001251276,0.0005330006,0.005140395,0.00049267,0.0002900755,0.0006219558,0.001621535,0.3758378,0.008179623,0.01670604,0.01216266,0.5771629],"study_design_scores_gemma":[0.00003858652,0.00005604804,0.0001623359,0.00002348121,0.00003026808,0.00004680114,0.00007448415,0.9779999,0.002294172,0.01644805,0.00281011,0.00001578783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01415363,0.0003658906,0.9751917,0.0009815253,0.00005367614,0.0001842389,0.0004900182,0.007246773,0.001332613],"genre_scores_gemma":[0.4304849,0.0004897856,0.562987,0.0008777702,0.0001193636,0.0005089954,0.001817411,0.0006382876,0.002076504],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007836538,"threshold_uncertainty_score":0.02832121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08934316528721445,"score_gpt":0.4816703637891037,"score_spread":0.3923271985018892,"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."}}