{"id":"W3013347747","doi":"10.2196/16018","title":"Intra-Rater and Inter-Rater Reliability of Tongue Coating Diagnosis in Traditional Chinese Medicine Using Smartphones: Quasi-Delphi Study","year":2020,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Traditional Chinese Medicine Studies","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Technology Sydney; Hong Kong Baptist University","keywords":"Tongue; Reliability (semiconductor); Delphi method; Medicine; Computer science; Artificial intelligence; Pathology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008954829,0.0003240254,0.001098898,0.0002364491,0.0001520185,0.000007337543,0.00007072706,0.00008214517,0.00007600814],"category_scores_gemma":[0.0008107901,0.0002223576,0.00004369094,0.0005174167,0.0003801741,0.0001405631,0.00005754199,0.0005143596,0.000001206875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192135,"about_ca_system_score_gemma":0.0002449384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001291266,"about_ca_topic_score_gemma":0.0003429899,"domain_scores_codex":[0.9971983,0.0002466739,0.001130154,0.0005757909,0.000458661,0.0003904656],"domain_scores_gemma":[0.9981362,0.0006507417,0.0002604168,0.0001997997,0.0001559781,0.000596837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006549003,0.0008310493,0.9702014,0.003137034,0.00002873095,0.00003982992,0.02335487,0.00000456361,0.0001146614,0.00005254611,0.0004722533,0.001108173],"study_design_scores_gemma":[0.004936106,0.004266587,0.982774,0.0005276842,0.0001070964,0.0000552629,0.005507966,0.001185758,0.000008783427,0.0004253847,0.00005175969,0.0001535813],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.966445,0.0009705117,0.00005390919,0.03083662,0.0002004548,0.001305357,0.00006275552,0.00004101584,0.00008434583],"genre_scores_gemma":[0.9944694,0.0003587816,0.0003840705,0.003716328,0.0008552496,0.0001299887,0.00005389683,0.00002867796,0.00000360094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02802438,"threshold_uncertainty_score":0.9067481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1224617060456337,"score_gpt":0.3966747538520281,"score_spread":0.2742130478063943,"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."}}