{"id":"W4246120193","doi":"10.2196/preprints.18149","title":"LesionMap: A Method and Tool for the Semantic Annotation of Dermatological Lesions for Documentation and Machine Learning (Preprint)","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Documentation; Computer science; JavaScript; Preprint; Health records; Resource (disambiguation); World Wide Web; Software; Annotation; Information retrieval; Artificial intelligence; Multimedia; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001879491,0.001668208,0.0007617907,0.003521689,0.000705532,0.002582337,0.001590603,0.002045071,0.05143096],"category_scores_gemma":[0.008528745,0.001022928,0.001198056,0.001649501,0.0007168244,0.002636428,0.003178598,0.001553075,0.03630514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006643447,"about_ca_system_score_gemma":0.001388023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001213108,"about_ca_topic_score_gemma":0.001677188,"domain_scores_codex":[0.9984402,0.0002908761,0.0001998725,0.000304131,0.0006891279,0.0000758676],"domain_scores_gemma":[0.9966723,0.001487676,0.0002733061,0.0007892574,0.0005673369,0.0002101585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000304832,0.0001579696,0.002174488,0.0009994046,0.0001131165,0.0007382097,0.000565896,0.002540431,0.01571599,0.01991971,0.5518371,0.4049328],"study_design_scores_gemma":[0.0001498003,0.00007336118,0.004763596,0.0003437479,0.00004471356,0.003150269,0.0002367965,0.04958209,0.04593395,0.04342386,0.852084,0.0002138101],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001242251,0.0001960504,0.8340642,0.0004754675,0.0002401375,0.0002378442,0.01072687,0.1480096,0.004807569],"genre_scores_gemma":[0.02669388,0.0005465393,0.8543319,0.0006938402,0.000252542,0.0008874754,0.04327083,0.05307603,0.020247],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05143096,"threshold_uncertainty_score":0.1720537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05283110915974307,"score_gpt":0.3447483502553326,"score_spread":0.2919172410955895,"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."}}