{"id":"W4410406672","doi":"10.1016/j.acra.2025.04.064","title":"External Validation of a CT-Based Radiogenomics Model for the Detection of EGFR Mutation in NSCLC and the Impact of Prevalence in Model Building by Using Synthetic Minority Over Sampling (SMOTE): Lessons Learned","year":2025,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Radiogenomics; Sampling (signal processing); Medicine; Mutation; Computer science; Oncology; Radiology; Radiomics; Biology; Computer vision; Genetics; Gene","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":[0.001802758,0.0001084875,0.0003979157,0.0003337275,0.00004426055,0.000003019767,0.0001339408,0.0001270104,7.338598e-7],"category_scores_gemma":[0.001263923,0.00007394709,0.00009835999,0.0002699633,0.0003337374,0.00005048163,0.00002570744,0.0005140975,9.242964e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001453465,"about_ca_system_score_gemma":0.0001637032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000901309,"about_ca_topic_score_gemma":0.000003394355,"domain_scores_codex":[0.9988082,0.0001789205,0.0005396028,0.0002064624,0.00009470588,0.0001720959],"domain_scores_gemma":[0.9981552,0.001298413,0.000329705,0.0001509271,0.00004188405,0.00002385318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004963459,0.00001628215,0.009281352,0.0001499622,0.00002857319,1.985699e-7,0.0003291695,0.6069381,0.372298,0.0003299256,0.000001722753,0.01013031],"study_design_scores_gemma":[0.00300178,0.00004514047,0.005506542,0.0003218805,0.0001408072,0.00002510357,0.00003660548,0.9731909,0.01381526,0.003864894,6.21127e-7,0.0000504425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5760891,0.001454184,0.4217511,0.0003651201,0.00002002309,0.0003083619,0.000006828113,0.00000262325,0.000002710119],"genre_scores_gemma":[0.9950585,0.0009104847,0.003919989,0.00005732761,0.00001615622,0.00001885817,0.000003402778,0.000009243829,0.000006054995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4189694,"threshold_uncertainty_score":0.3015475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04173479569458079,"score_gpt":0.3902909876567432,"score_spread":0.3485561919621625,"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."}}