{"id":"W1656413649","doi":"10.5430/jbgc.v5n2p1","title":"Evaluating agreement between solid tumor measurements used to assess response","year":2015,"lang":"en","type":"article","venue":"Journal of Biomedical Graphics and Computing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute; Memorial Sloan-Kettering Cancer Center","keywords":"Limits of agreement; Mean difference; Bland–Altman plot; Statistics; Significant difference; Plot (graphics); Distribution (mathematics); Mathematics; Nuclear medicine; Medicine; Mathematical analysis; Confidence interval","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":[0.01204316,0.0001637864,0.0005676927,0.0004859261,0.0001274139,0.00007276345,0.0001810807,0.00007190373,0.000007382824],"category_scores_gemma":[0.004218765,0.0001233283,0.0001270599,0.0004849069,0.0001382379,0.00005464984,0.0001391153,0.000714876,0.000001860566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008807527,"about_ca_system_score_gemma":0.000404321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009789202,"about_ca_topic_score_gemma":3.192025e-7,"domain_scores_codex":[0.9964559,0.000335479,0.0008764096,0.000209496,0.001782016,0.0003406688],"domain_scores_gemma":[0.9971808,0.0004260626,0.0004365884,0.0001444471,0.000492977,0.001319152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003068101,0.0009439341,0.5775863,0.0003849321,0.001401366,0.001323683,0.005603537,0.0004735302,0.09823431,0.0001600048,0.00714675,0.3036735],"study_design_scores_gemma":[0.03878432,0.0271335,0.5475237,0.009267756,0.00201782,0.004854201,0.003161956,0.3282299,0.003722936,0.002720333,0.03100033,0.001583259],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.952975,0.0002289366,0.03838033,0.007793075,0.0004224086,0.0001449397,9.946814e-7,0.00001487599,0.00003940489],"genre_scores_gemma":[0.9777507,0.000004875357,0.01987591,0.001522399,0.0008125807,6.577501e-7,0.000002292192,0.00001818521,0.00001236606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3277564,"threshold_uncertainty_score":0.505056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2153681260112936,"score_gpt":0.4435325674470571,"score_spread":0.2281644414357635,"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."}}