{"id":"W3185777129","doi":"10.3390/cancers13153723","title":"Site-Specific Variation in Radiomic Features of Head and Neck Squamous Cell Carcinoma and Its Impact on Machine Learning Models","year":2021,"lang":"en","type":"article","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre; Princess Margaret Cancer Centre; Jewish General Hospital; University of Toronto; University Health Network","funders":"National Center for Advancing Translational Sciences","keywords":"Head and neck squamous-cell carcinoma; Medicine; Larynx; Head and neck; Basal cell; Head and neck cancer; Radiology; Pathology; Radiation therapy; Surgery","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":[],"consensus_categories":[],"category_scores_codex":[0.0001653616,0.0001291769,0.0003038225,0.0001212556,0.00005083071,0.00001343603,0.00003009875,0.00006569935,0.00003819144],"category_scores_gemma":[0.00009697277,0.0001114443,0.00004282896,0.0001502606,0.00004217105,0.00004849757,0.00002297357,0.0004680192,7.163482e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003397914,"about_ca_system_score_gemma":0.0002142582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009206122,"about_ca_topic_score_gemma":0.00002684199,"domain_scores_codex":[0.9991699,0.00006356765,0.0001728548,0.0002615644,0.0001513855,0.0001807545],"domain_scores_gemma":[0.9995402,0.0001030886,0.00007383421,0.0001102645,0.00004044069,0.0001321367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001883646,0.0001567524,0.3656478,0.001054365,0.00006570085,0.0008898238,0.01286829,0.3114921,0.2889973,0.0008300616,0.001189462,0.01492468],"study_design_scores_gemma":[0.005089714,0.0004683218,0.5115201,0.000176442,0.00004775817,0.0001721621,0.0001028562,0.478361,0.003469229,0.00009617092,0.0003158949,0.000180293],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9842358,0.01393405,0.0001085548,0.0003289752,0.00007958816,0.0001225845,0.000007672846,0.00001392593,0.001168894],"genre_scores_gemma":[0.9981933,0.0008311877,0.0003139313,0.000177374,0.00007443973,0.000003553724,0.00002786314,0.00002192901,0.0003564291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2855281,"threshold_uncertainty_score":0.4544566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01450488404224773,"score_gpt":0.2753893608817958,"score_spread":0.2608844768395481,"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."}}