{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04588804,0.0008471851,0.0008541698,0.006012175,0.001355623,0.005992034,0.003622832,0.003206789,0.004310925],"category_scores_gemma":[0.2092664,0.0005094201,0.0009743534,0.002934138,0.002244338,0.002522666,0.002345152,0.00240308,0.001612262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004042863,"about_ca_system_score_gemma":0.0103825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006923895,"about_ca_topic_score_gemma":0.01305818,"domain_scores_codex":[0.9528369,0.03109116,0.006197035,0.001145842,0.008068644,0.0006604524],"domain_scores_gemma":[0.7892036,0.1178602,0.009148144,0.008429112,0.07077319,0.004585631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001578672,0.001180697,0.03706142,0.004847665,0.0004107282,0.0008410404,0.005399383,0.007683339,0.003610012,0.06548743,0.06697012,0.8049295],"study_design_scores_gemma":[0.002277124,0.004474422,0.08403593,0.03388808,0.00213495,0.007019957,0.0126579,0.1001872,0.0477797,0.2221847,0.4826831,0.0006768981],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1524741,0.1254035,0.400709,0.156161,0.00237056,0.01360998,0.005310349,0.004734193,0.1392273],"genre_scores_gemma":[0.4174567,0.01459972,0.5488986,0.006193096,0.0003320062,0.003988579,0.002517598,0.0005299671,0.005483813],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04588804,"threshold_uncertainty_score":0.2426821,"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."}}