{"id":"W4406677985","doi":"10.3390/a18020055","title":"Mitigating Digital Ageism in Skin Lesion Detection with Adversarial Learning","year":2025,"lang":"en","type":"article","venue":"Algorithms","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Toronto Rehabilitation Institute; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Skin Aging; Adversarial system; Computer science; Artificial intelligence; Lesion; Computer vision; Skin lesion; Pattern recognition (psychology); Machine learning; Medicine; Pathology; Dermatology","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":[0.00009074951,0.00009808997,0.0001462965,0.0002115816,0.00008203421,0.00004261346,0.00003121827,0.00005767312,0.00002452124],"category_scores_gemma":[0.00006352182,0.00008620301,0.00003999895,0.0003308789,0.00002572758,0.00007123873,0.00003532868,0.0002419725,0.00002345539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001200633,"about_ca_system_score_gemma":0.00002952809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001303876,"about_ca_topic_score_gemma":0.00008066477,"domain_scores_codex":[0.9993,0.00002018349,0.0001565867,0.0002123947,0.0001504287,0.0001604067],"domain_scores_gemma":[0.9997525,0.00003596139,0.00004103978,0.0001019528,0.00002713824,0.00004146843],"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":[0.0002726037,0.00008252469,0.003429117,0.00004492925,0.00005558955,0.000417704,0.0002539703,0.0002647762,0.003575366,0.00004283454,0.00005088612,0.9915097],"study_design_scores_gemma":[0.03971755,0.007000338,0.1741202,0.003523994,0.000723585,0.003049066,0.0190941,0.2566749,0.136842,0.0009286074,0.3563131,0.002012546],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9164407,0.00005179452,0.04600089,0.0004007829,0.0005404503,0.0005352431,7.619273e-7,0.0002191934,0.03581019],"genre_scores_gemma":[0.9921532,0.000007760179,0.000933343,0.0001214131,0.0001274038,0.00001619691,0.000009189289,0.00001170585,0.006619833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9894971,"threshold_uncertainty_score":0.3515257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007381227387904614,"score_gpt":0.2423796257355944,"score_spread":0.2349983983476898,"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."}}