{"id":"W4406755361","doi":"10.1016/j.smhl.2025.100540","title":"Human knowledge-based artificial intelligence methods for skin cancer management: Accuracy and interpretability study","year":2025,"lang":"en","type":"article","venue":"Smart Health","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Alberta Children's Hospital; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Artificial intelligence; Machine learning; Computer science; Medicine","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":[0.001307273,0.000150365,0.0003442521,0.0002411463,0.0002674093,0.00003412368,0.00008537131,0.00003770982,0.0000871218],"category_scores_gemma":[0.00009794372,0.0001390603,0.00007529191,0.0002937119,0.00005695307,0.00002590484,0.00009402585,0.0001413539,0.000004895462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002781961,"about_ca_system_score_gemma":0.0001491858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003887377,"about_ca_topic_score_gemma":0.001459724,"domain_scores_codex":[0.9985328,0.0002221919,0.0004565387,0.0004382219,0.00008286658,0.0002674099],"domain_scores_gemma":[0.9991605,0.0001835912,0.00008972826,0.0003654289,0.00007779167,0.0001229027],"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":[0.000316415,0.0008713653,0.002173535,0.001507275,0.0001420946,0.000002963031,0.0007559665,0.000006436846,0.00005708946,0.004924467,0.001026452,0.9882159],"study_design_scores_gemma":[0.006010641,0.008668018,0.1272934,0.001859026,0.001505973,0.00001647452,0.0179582,0.04098444,0.007022542,0.02199733,0.7655106,0.001173351],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.177545,0.002382952,0.7734909,0.01366328,0.002967659,0.01513196,0.00002087908,0.0004092581,0.01438814],"genre_scores_gemma":[0.9867808,0.00004692225,0.009042499,0.001700425,0.00007901839,0.000549445,0.000006306124,0.00001538236,0.001779153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9870426,"threshold_uncertainty_score":0.5670714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06060773830380185,"score_gpt":0.4790257530197869,"score_spread":0.4184180147159851,"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."}}