{"id":"W4317214916","doi":"10.2196/38412","title":"Agreement Between Experts and an Untrained Crowd for Identifying Dermoscopic Features Using a Gamified App: Reader Feasibility Study","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Crowdsourcing; Inter-rater reliability; Bottleneck; Reliability (semiconductor); Identification (biology); Computer science; Artificial intelligence; Gold standard (test); Similarity (geometry); Pattern recognition (psychology); Medicine; Image (mathematics); Mathematics; Statistics; Radiology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03789938,0.0009356907,0.0009559208,0.001856152,0.001255519,0.002337355,0.001335924,0.00163198,0.005328527],"category_scores_gemma":[0.1010212,0.0007688675,0.001461809,0.0004676101,0.00172313,0.002245161,0.003288309,0.001063571,0.002595302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008382502,"about_ca_system_score_gemma":0.0007443804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008829668,"about_ca_topic_score_gemma":0.001136532,"domain_scores_codex":[0.9703745,0.01552925,0.00196729,0.005629458,0.005430637,0.001068824],"domain_scores_gemma":[0.8695473,0.08458821,0.006792022,0.009659678,0.02643849,0.002974251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02382537,0.01528283,0.5784864,0.002928428,0.001091781,0.002166256,0.1431404,0.004245362,0.04602638,0.00235048,0.007954624,0.1725017],"study_design_scores_gemma":[0.001850079,0.04248752,0.7993373,0.0008969688,0.001180929,0.003900361,0.04265394,0.0456991,0.03799358,0.004321334,0.01864864,0.001030208],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9849904,0.000152497,0.009182757,0.00009646261,0.00008316897,0.001334655,0.0002054443,0.0001240477,0.003830621],"genre_scores_gemma":[0.985307,0.00008422649,0.01064697,0.0001382376,0.0000578287,0.001895551,0.0001734367,0.00006305831,0.001633708],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03789938,"threshold_uncertainty_score":0.2004334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1095782061467511,"score_gpt":0.412816470107709,"score_spread":0.3032382639609579,"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."}}