{"id":"W4416780876","doi":"10.1016/j.esmorw.2025.100548","title":"352P Pathomic embeddings improve prediction of clinically actionable breast cancer related mutations from whole slide images","year":2025,"lang":"en","type":"article","venue":"ESMO Real World Data and Digital Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Breast cancer; Mutation; Cancer; Feature (linguistics)","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":[0.0002409081,0.000128307,0.0002764895,0.0001748897,0.000121796,0.0001472232,0.0005664334,0.0001000789,0.00001680369],"category_scores_gemma":[0.00008303089,0.0001258328,0.0000400858,0.0005517157,0.0001846417,0.001865411,0.0006834625,0.0002258021,0.00001120776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002296935,"about_ca_system_score_gemma":0.0004502087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001393046,"about_ca_topic_score_gemma":0.0005328003,"domain_scores_codex":[0.9984337,0.00005260608,0.0005763479,0.0006124135,0.0001339297,0.0001909671],"domain_scores_gemma":[0.9983224,0.0005019009,0.0003334136,0.0006496711,0.0001189653,0.00007369737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002373593,0.0003651943,0.07851564,0.00003534274,0.0002703707,0.0000182516,0.0003039561,0.000112238,0.003355413,0.003123794,0.01901612,0.8946463],"study_design_scores_gemma":[0.003903739,0.0008743327,0.6948938,0.0002257402,0.0002908833,0.00006980393,0.0003367121,0.0913186,0.001651085,0.04210526,0.1637805,0.0005494637],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5805412,0.0006906349,0.2209448,0.02572238,0.01205776,0.001781425,0.04228585,0.001719017,0.1142569],"genre_scores_gemma":[0.9908609,0.000267528,0.005882588,0.0001863106,0.000123454,0.00003799846,0.0006102181,0.00001036899,0.002020621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8940969,"threshold_uncertainty_score":0.5131313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01837691542244549,"score_gpt":0.3267523096492561,"score_spread":0.3083753942268107,"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."}}