{"id":"W4411521362","doi":"10.1007/978-3-031-95838-0_29","title":"CUE-X: A Framework for the Automatic Evaluation of Clinical Usefulness of Explanations for the Multimorbidity Problem","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Computer science; Artificial intelligence; Theoretical computer 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":[0.005089018,0.001830896,0.0012127,0.004823737,0.0007558859,0.002716043,0.002693164,0.0023873,0.01678823],"category_scores_gemma":[0.02124367,0.0006317662,0.001488068,0.001749615,0.0007186835,0.002572662,0.003159177,0.001621222,0.003431057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010891,"about_ca_system_score_gemma":0.00230689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007225036,"about_ca_topic_score_gemma":0.01146525,"domain_scores_codex":[0.9969091,0.001121435,0.0002961797,0.0006067194,0.0008891395,0.0001774544],"domain_scores_gemma":[0.9901865,0.006974296,0.0006309575,0.0006894618,0.00114761,0.0003713462],"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":[0.001940933,0.0003831605,0.01035513,0.001458891,0.0004257577,0.0004682655,0.0005923692,0.0163356,0.007564767,0.02418702,0.06996406,0.8663241],"study_design_scores_gemma":[0.0005448706,0.0005141221,0.0101679,0.0005591275,0.0003513278,0.0008725784,0.0005473475,0.8085713,0.0271329,0.09339666,0.05713906,0.0002028336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01534304,0.001876068,0.9108531,0.0008118061,0.0002057535,0.0009062602,0.009143643,0.05708089,0.003779428],"genre_scores_gemma":[0.1276203,0.0004081674,0.8597222,0.0002650242,0.0001084402,0.0006948415,0.007597932,0.001132708,0.002450298],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01678823,"threshold_uncertainty_score":0.05616218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1478508910738148,"score_gpt":0.4269790255840672,"score_spread":0.2791281345102524,"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."}}