{"id":"W4401028347","doi":"10.1007/978-3-031-66535-6_33","title":"Manually-Curated Versus LLM-Generated Explanations for Complex Patient Cases: An Exploratory Study with Physicians","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Computer science; Exploratory research; Information retrieval; World Wide Web; Data science","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":[0.01405606,0.0004788841,0.0006149925,0.001241109,0.001300898,0.002563715,0.001808679,0.001651101,0.0055135],"category_scores_gemma":[0.1567827,0.0004404788,0.0005103963,0.001010916,0.0007998995,0.002133545,0.002489214,0.001474664,0.001480081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001478082,"about_ca_system_score_gemma":0.001749641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00303658,"about_ca_topic_score_gemma":0.004199722,"domain_scores_codex":[0.9855022,0.0108516,0.000665894,0.001079675,0.001573478,0.000327128],"domain_scores_gemma":[0.6934864,0.2865438,0.00694147,0.004026369,0.007189695,0.001812206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.004427205,0.009314213,0.1371407,0.004462501,0.0003216054,0.004465266,0.4099065,0.0051897,0.00933052,0.001548186,0.01565531,0.3982383],"study_design_scores_gemma":[0.002411917,0.02063436,0.4169951,0.004931763,0.001376727,0.01271633,0.3284549,0.07359892,0.02531826,0.006559171,0.1062317,0.0007707651],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989727,0.0004029474,0.004329999,0.000440107,0.00002764433,0.0004371696,0.0004771632,0.0002712414,0.003886723],"genre_scores_gemma":[0.9758386,0.0004461674,0.01832967,0.0004431058,0.00003739307,0.0005416728,0.000862068,0.0002074814,0.003293969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01405606,"threshold_uncertainty_score":0.07433653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2282105092543523,"score_gpt":0.4355079741253901,"score_spread":0.2072974648710378,"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."}}