{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009390474,0.0009182313,0.000699015,0.001518425,0.0004582961,0.001100099,0.001589047,0.001347354,0.001382683],"category_scores_gemma":[0.04442261,0.0002632167,0.0005874727,0.0006209355,0.001641379,0.001329824,0.001859678,0.001515574,0.0003640141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009908816,"about_ca_system_score_gemma":0.001123398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003249149,"about_ca_topic_score_gemma":0.002836216,"domain_scores_codex":[0.996808,0.001385278,0.0001953308,0.0007002181,0.0007770743,0.0001340768],"domain_scores_gemma":[0.9676935,0.02384839,0.002071064,0.003078332,0.002829733,0.0004790395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006402538,0.0001856673,0.08046688,0.0003250536,0.0002781648,0.0001789916,0.0001690809,0.7642814,0.003469607,0.004523864,0.003290498,0.1421906],"study_design_scores_gemma":[0.0000185505,0.00006573826,0.003969694,0.00004155315,0.00001912425,0.00006041918,0.00002156407,0.989557,0.003173095,0.002722003,0.0003402104,0.00001107976],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5987158,0.001960104,0.3926053,0.0009439908,0.000138443,0.0001929632,0.0008774028,0.001233061,0.003332851],"genre_scores_gemma":[0.9794336,0.0001298535,0.01933412,0.00008259344,0.00003490612,0.00002982827,0.0006663447,0.00003134341,0.0002573987],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009390474,"threshold_uncertainty_score":0.04966217,"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."}}