{"id":"W4413979894","doi":"10.1109/tnnls.2025.3600443","title":"Integrating Clinical Knowledge Graphs and Gradient-Based Neural Systems for Enhanced Melanoma Diagnosis via the Seven-Point Checklist","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Vancouver Coastal Health","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Checklist; Point (geometry); Melanoma diagnosis; Computer science; Artificial neural network; Melanoma; Artificial intelligence; Medicine; Medical physics; Psychology; Natural language processing; Mathematics; Cognitive psychology; Cancer research","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":[0.001148744,0.000296819,0.0004295332,0.000164243,0.001230015,0.0005234014,0.0003467745,0.0001859061,8.134771e-7],"category_scores_gemma":[0.00003281585,0.0002212278,0.0001972607,0.0005758043,0.0001505153,0.0002432571,0.000008560522,0.0009826449,8.077488e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007485882,"about_ca_system_score_gemma":0.00003496529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000275553,"about_ca_topic_score_gemma":0.0001381913,"domain_scores_codex":[0.9972374,0.0008763252,0.000665058,0.0006760185,0.0001532808,0.0003919119],"domain_scores_gemma":[0.996812,0.002307182,0.0002562054,0.000376511,0.0001325385,0.0001155219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009272848,0.0000787584,0.000594258,0.000199664,0.00009996013,0.00000213459,0.0004245279,0.8506836,0.00006454219,0.0007917534,0.0002869775,0.1466811],"study_design_scores_gemma":[0.0006894098,0.0005901151,0.0003141931,0.0003144966,0.00006023246,0.00002191248,0.0002898838,0.9961753,0.0001256285,0.00002449133,0.001175878,0.0002183874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06443879,0.003340417,0.9235396,0.0004191413,0.007016361,0.0009442788,0.00000320738,0.0002552482,0.00004291613],"genre_scores_gemma":[0.9980838,0.0002330043,0.0001910814,0.0001239323,0.0001832069,0.0008226945,0.000001595264,0.00002369819,0.0003369722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.933645,"threshold_uncertainty_score":0.9460402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01796228811516171,"score_gpt":0.2815856936904686,"score_spread":0.2636234055753069,"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."}}