{"id":"W4412163711","doi":"10.1158/1557-3265.aimachine-pr-06","title":"Abstract PR-06: Analysis of pathologists’ intraobserver, interobserver and AI agreement in breast cancer HER2 scoring: AI-assessed intra-sample tumor heterogeneity relates to lower agreement among pathologists and with AI","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medicine; Breast cancer; Cancer; Pathology; Radiology; Internal medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.02915453,0.0004962892,0.0004225665,0.002304437,0.0004745273,0.001004744,0.0008686661,0.0007603992,0.001700324],"category_scores_gemma":[0.07656926,0.0003514604,0.001164209,0.001034906,0.000969733,0.001300367,0.001261904,0.0005214136,0.0005029265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000410131,"about_ca_system_score_gemma":0.0003824481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000721261,"about_ca_topic_score_gemma":0.0006240963,"domain_scores_codex":[0.9683881,0.0189939,0.003291831,0.003792553,0.00501191,0.0005217091],"domain_scores_gemma":[0.8671628,0.09794671,0.01481982,0.006706137,0.01197731,0.001387278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009099139,0.0001065872,0.9781014,0.0001635887,0.0005928041,0.00006489488,0.0009919064,0.001100112,0.001620011,0.00015032,0.0004407433,0.01575779],"study_design_scores_gemma":[0.00004904209,0.00127133,0.9750079,0.00004377888,0.0002605518,0.0007281055,0.001271982,0.01720398,0.002820976,0.0004695474,0.0008392248,0.00003358196],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834532,0.0003023903,0.0134376,0.00006450454,0.00004262945,0.000142367,0.0002615161,0.000104045,0.002191771],"genre_scores_gemma":[0.9970334,0.00001957987,0.002486149,0.00002164258,0.00001524283,0.00006349821,0.0001617607,0.00002217196,0.0001766639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02915453,"threshold_uncertainty_score":0.1541857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07702883829687934,"score_gpt":0.4738085197229119,"score_spread":0.3967796814260326,"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."}}