{"id":"W4399040553","doi":"10.1016/j.cmpb.2024.108231","title":"Empirical validation of Conformal Prediction for trustworthy skin lesions classification","year":2024,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Field (mathematics); Machine learning; Conformal map; Trustworthiness; Monte Carlo method; Deep learning; Dropout (neural networks); Artificial neural network; Data mining; Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.001004796,0.0001017225,0.0002425124,0.0003476474,0.0000328541,0.00002394559,0.00003398669,0.0000893727,0.00001330126],"category_scores_gemma":[0.00002711501,0.00007716729,0.0000629049,0.0004188568,0.00009723274,0.00004907716,0.00002799791,0.0001072562,8.125993e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003578011,"about_ca_system_score_gemma":0.00002899403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008996633,"about_ca_topic_score_gemma":0.000001160824,"domain_scores_codex":[0.9990299,0.00007373263,0.0003941096,0.000241494,0.0001279038,0.0001328419],"domain_scores_gemma":[0.9995155,0.0001566296,0.00005339942,0.0001331725,0.00006337331,0.00007794773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001160923,0.0001038143,0.001964716,0.0005118456,0.00004815447,0.000006091894,0.000536485,0.000002368978,0.001638901,0.0005317901,0.000551761,0.993988],"study_design_scores_gemma":[0.003080416,0.005021043,0.05607418,0.001025981,0.000364119,0.0004095445,0.0005692723,0.4210339,0.003590736,0.00122192,0.5073924,0.0002165493],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1280565,0.0005960075,0.8670594,0.001738534,0.001055464,0.001126536,0.000006062239,0.0001190405,0.0002425054],"genre_scores_gemma":[0.6299953,0.0002092387,0.3684229,0.0001844621,0.0005853865,0.0001324839,0.0002371858,0.00001766973,0.0002153185],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9937714,"threshold_uncertainty_score":0.3146791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1191603702847794,"score_gpt":0.4205057411941767,"score_spread":0.3013453709093972,"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."}}