{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01038276,0.0002891668,0.0005789535,0.0003174111,0.0004448522,0.000132064,0.003911375,0.0003356395,0.0000112804],"category_scores_gemma":[0.006022205,0.0001786804,0.0002845449,0.0005852154,0.0006570116,0.0001782476,0.0006638559,0.0008457121,8.380504e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001251027,"about_ca_system_score_gemma":0.001965507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000744816,"about_ca_topic_score_gemma":0.0001422164,"domain_scores_codex":[0.9960073,0.0002363009,0.00120922,0.0008707948,0.00132305,0.0003533865],"domain_scores_gemma":[0.968235,0.02735449,0.001040132,0.001709078,0.001606902,0.00005438759],"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":[0.000005902304,0.00002654103,0.0001771146,0.0002747414,0.00002832453,1.658777e-7,0.0007334874,0.1178481,5.447877e-7,0.103817,0.00004231509,0.7770457],"study_design_scores_gemma":[0.0002607509,0.0001195868,0.001360492,0.0006161705,0.00005773316,0.000001961567,6.807773e-7,0.7780064,0.00004414909,0.2189709,0.0004275876,0.0001336044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006918543,0.0004494236,0.9883714,0.004945337,0.002521014,0.003462284,0.00003118471,0.00005565122,0.00009447119],"genre_scores_gemma":[0.152266,0.00002100409,0.8464245,0.0005368714,0.0003282039,0.000355196,0.000006204754,0.00001656029,0.00004539579],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7769121,"threshold_uncertainty_score":0.7286377,"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."}}