{"id":"W2990040492","doi":"10.1148/rycan.2019190031","title":"Imaging-based Biomarkers for Predicting and Evaluating Cancer Immunotherapy Response","year":2019,"lang":"en","type":"review","venue":"Radiology Imaging Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"National Natural Science Foundation of China; Ministry of Science and Innovation, New Zealand","keywords":"Immunotherapy; Molecular imaging; Medicine; Cancer immunotherapy; Functional imaging; Cancer; Modalities; Biomarker; Oncology; Medical physics; Internal medicine; Radiology; Biology; In vivo","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003092483,0.0007918451,0.002746501,0.0006019698,0.0002426687,0.00008478053,0.0003235431,0.0002832347,0.0001036919],"category_scores_gemma":[0.001339184,0.000651483,0.0006655222,0.0003244361,0.0005396535,0.0001001765,0.00007947221,0.001184768,0.000004481893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008572377,"about_ca_system_score_gemma":0.002623799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003309096,"about_ca_topic_score_gemma":0.000002681071,"domain_scores_codex":[0.9957329,0.000747274,0.001010247,0.001235764,0.0003287288,0.0009451088],"domain_scores_gemma":[0.9955844,0.002460026,0.0008299198,0.0006622185,0.0002079133,0.0002554987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007632633,0.00002544516,0.01227012,0.01042813,0.000887629,0.00002827836,0.00008767322,0.00005037483,0.0002311123,0.000004936218,0.003652031,0.971571],"study_design_scores_gemma":[0.003894026,0.0001442511,0.0006040279,0.02047945,0.003124267,0.0006144994,0.00002408634,0.09517748,0.000004126405,0.00001527647,0.8752646,0.0006538823],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0005507807,0.9876768,0.00219208,0.00447323,0.002022462,0.002590718,0.0001328462,0.0003109678,0.00005010015],"genre_scores_gemma":[0.0001831634,0.9890862,0.004162229,0.003127569,0.001044306,0.001494313,0.0001422607,0.0004277237,0.0003322902],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9709171,"threshold_uncertainty_score":0.9995936,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04577564204199543,"score_gpt":0.4388238504037026,"score_spread":0.3930482083617072,"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."}}