{"id":"W4379280017","doi":"10.1007/978-3-031-34344-5_15","title":"Batch Integrated Gradients: Explanations for Temporal Electronic Health Records","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Leverage (statistics); Usability; Sequence (biology); Temporal database; Point (geometry); Electronic health record; Health records; Data mining; Artificial intelligence; Information retrieval; Human–computer interaction; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002408668,0.0006277707,0.000744235,0.001542763,0.0006505924,0.000469125,0.003820458,0.0003468363,0.00001539101],"category_scores_gemma":[0.0004368754,0.0005969174,0.0001923766,0.001581739,0.0003087458,0.0004859499,0.0007818244,0.001775386,0.00005968101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001451933,"about_ca_system_score_gemma":0.003532857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007020697,"about_ca_topic_score_gemma":0.003558229,"domain_scores_codex":[0.9944077,0.0001173244,0.0009031767,0.002055289,0.0009911979,0.00152537],"domain_scores_gemma":[0.995996,0.00106767,0.0005741591,0.001540743,0.000501452,0.000320003],"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":[0.00001013466,0.00003068855,0.0003711438,0.0001730573,0.00002047149,0.00002031279,0.001234167,0.01327922,0.000001932473,0.116296,0.0006733394,0.8678895],"study_design_scores_gemma":[0.0004056189,0.0009353638,0.000246768,0.0006535971,0.000005291611,0.0000493873,8.692464e-7,0.7177722,0.0000177581,0.2481356,0.03096657,0.0008109102],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002755092,0.0003457483,0.9825233,0.01120404,0.003611896,0.001192384,0.00003879423,0.000682266,0.0003740037],"genre_scores_gemma":[0.0507506,0.0003516325,0.934155,0.007253404,0.001353103,0.0002578399,0.0003532147,0.0002406646,0.005284465],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8670786,"threshold_uncertainty_score":0.9996482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02986729053671333,"score_gpt":0.309257202080594,"score_spread":0.2793899115438807,"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."}}