{"id":"W4401070453","doi":"10.1109/jbhi.2024.3435085","title":"CALLM: Enhancing Clinical Interview Analysis Through Data Augmentation With Large Language Models","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"China Scholarship Council","keywords":"Computer science; Natural language processing; Data science; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.006323828,0.0001176364,0.0004702753,0.0002817349,0.0001122937,0.0001789469,0.0007071752,0.00008268598,0.00001368583],"category_scores_gemma":[0.00005842065,0.00007408125,0.00007671552,0.0008200681,0.00006366454,0.001514686,0.000211087,0.0007174088,0.000005753197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006755001,"about_ca_system_score_gemma":0.0006493771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009916533,"about_ca_topic_score_gemma":0.0001164678,"domain_scores_codex":[0.9968176,0.0002059479,0.001890289,0.0001422509,0.0006544695,0.0002893859],"domain_scores_gemma":[0.9982479,0.000241286,0.0006509624,0.0003944454,0.0000999315,0.0003655424],"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":[0.0000287003,0.0002017535,0.001344977,0.005899952,0.000936678,0.0001686331,0.06346943,0.0005884377,0.000001318168,0.005641634,0.01026699,0.9114515],"study_design_scores_gemma":[0.0004170689,0.0006940953,0.0005079585,0.0008306911,0.0001000885,0.0002004226,0.001005482,0.9799159,0.000001430964,0.0004132704,0.01581368,0.00009991006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00684735,0.003449857,0.9755062,0.01338021,0.0006097064,0.00009335086,0.00002454596,0.00004119732,0.00004758227],"genre_scores_gemma":[0.5890582,0.005889103,0.3928346,0.01138047,0.0007108767,0.000002279387,0.0000732228,0.00001462697,0.00003663943],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9793274,"threshold_uncertainty_score":0.3116824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1447949056643628,"score_gpt":0.4637682632839094,"score_spread":0.3189733576195466,"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."}}