{"id":"W4309630525","doi":"10.1016/j.media.2022.102684","title":"Guidelines and evaluation of clinical explainable AI in medical image analysis","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"BC Cancer Foundation","keywords":"Guideline; Computer science; Data mining; Artificial intelligence; Medical physics; Medicine; Pathology","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03186496,0.0002342665,0.001226778,0.001799347,0.000241636,0.0001255317,0.001850192,0.0001830551,0.007003912],"category_scores_gemma":[0.01511698,0.000217691,0.0006793704,0.01144297,0.0004437199,0.0007372114,0.00146413,0.000756394,0.00002528405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001319545,"about_ca_system_score_gemma":0.0008804736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00260452,"about_ca_topic_score_gemma":0.002236819,"domain_scores_codex":[0.9876338,0.002349663,0.002491142,0.001045174,0.005939686,0.0005405658],"domain_scores_gemma":[0.9955252,0.001023817,0.0004635105,0.001155003,0.001260175,0.0005723198],"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":[0.0001374334,0.003131842,0.1890351,0.00009712,0.009828517,0.002493722,0.003499475,0.02091805,0.0006025819,0.007407364,0.01603569,0.7468131],"study_design_scores_gemma":[0.0004191904,0.00008315849,0.008704822,0.00001054392,0.002200094,0.000008409175,0.000725102,0.9841737,0.0003265788,0.002186808,0.000944874,0.0002166758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3209193,0.0007578935,0.6552469,0.02126199,0.0002184164,0.0002837507,0.000008958584,0.00008436309,0.001218361],"genre_scores_gemma":[0.9821557,0.0002305511,0.01441965,0.002694298,0.000126194,0.0001215047,0.00005066841,0.00001384424,0.0001876347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9632557,"threshold_uncertainty_score":0.9968988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.106462754669057,"score_gpt":0.4673112791791384,"score_spread":0.3608485245100814,"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."}}