{"id":"W3198718561","doi":"10.1016/j.compbiomed.2021.104812","title":"Incorporating clinical knowledge with constrained classifier chain into a multimodal deep network for melanoma detection","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vancouver Coastal Health Research Institute; University of British Columbia; Vancouver Coastal Health","funders":"Canadian Institutes of Health Research; VGH and UBC Hospital Foundation; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Canadian Dermatology Foundation","keywords":"Computer science; Checklist; Classifier (UML); Artificial intelligence; CAD; Extractor; Melanoma diagnosis; Machine learning; Domain knowledge; Pattern recognition (psychology); Melanoma; 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":[0.0005881183,0.0001496388,0.0004745099,0.0001076769,0.0001080056,0.000004764264,0.00003981789,0.0001832862,0.00001844426],"category_scores_gemma":[0.0001990251,0.0001100107,0.0000436174,0.0002155203,0.0004259131,0.00001601422,0.00005395557,0.0002461034,0.000001532061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004638729,"about_ca_system_score_gemma":0.00007059452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002010776,"about_ca_topic_score_gemma":0.0008394372,"domain_scores_codex":[0.9987963,0.0001459266,0.000404103,0.0003910734,0.00004544032,0.0002171876],"domain_scores_gemma":[0.9990312,0.0004742484,0.0001065605,0.000154186,0.0001023767,0.0001314021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00199208,0.0002675657,0.07588929,0.0002606797,0.0003212555,0.0004200697,0.0007888416,0.00004043528,0.003727538,0.004947047,0.0007182828,0.9106269],"study_design_scores_gemma":[0.08603612,0.03527693,0.2210509,0.003443603,0.001153937,0.008265683,0.005753591,0.4924129,0.001538578,0.01809913,0.1253134,0.001655268],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4986091,0.001654394,0.4896448,0.003850635,0.002670502,0.001017743,0.000001462986,0.0001075278,0.002443871],"genre_scores_gemma":[0.9698281,0.00008962274,0.02741046,0.001366938,0.001063085,0.00004202014,0.00004825333,0.00001214843,0.0001393675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9089717,"threshold_uncertainty_score":0.4486108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.027053751503503,"score_gpt":0.3389652491120251,"score_spread":0.3119114976085221,"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."}}