{"id":"W4380576500","doi":"10.1007/s11604-023-01458-3","title":"Construction of prediction model for KRAS mutation status of colorectal cancer based on CT radiomics","year":2023,"lang":"en","type":"article","venue":"Japanese Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"KRAS; Radiomics; Medicine; Receiver operating characteristic; Colorectal cancer; Stage (stratigraphy); Internal medicine; Oncology; Area under the curve; Radiology; Cancer; Biology","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":[0.0006774784,0.00008812804,0.0004337048,0.0003895073,0.00003734593,0.000002421153,0.0000579979,0.00005831979,0.0000130052],"category_scores_gemma":[0.0009474931,0.00006966129,0.0001447204,0.0002287165,0.0001907493,0.00005906096,0.000005494733,0.0002262416,3.47008e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001208483,"about_ca_system_score_gemma":0.0002809885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003157369,"about_ca_topic_score_gemma":0.000001571672,"domain_scores_codex":[0.9988415,0.00007494849,0.0005672727,0.0001075908,0.0002053304,0.000203419],"domain_scores_gemma":[0.9986109,0.0003843674,0.0005296394,0.00007582326,0.0002781488,0.0001211323],"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":[0.003592546,0.0001269621,0.09428799,0.0001984378,0.0002069324,0.00003839134,0.001453796,0.6626955,0.2205803,0.0003271014,0.0007564176,0.01573571],"study_design_scores_gemma":[0.003862133,0.001249764,0.0315667,0.00008681109,0.0001271372,0.001126055,0.0003510134,0.9564648,0.004735717,0.0003279238,0.00005477747,0.00004719341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9794968,0.00005197146,0.01893282,0.0007700977,0.0004603685,0.0001970087,0.0000262655,0.00001600828,0.00004868086],"genre_scores_gemma":[0.9903309,0.0001627718,0.009190526,0.0001066703,0.0001422132,0.000009938319,0.00002891667,0.00001450839,0.00001359415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2937693,"threshold_uncertainty_score":0.2840705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01509256012639945,"score_gpt":0.3111056901805981,"score_spread":0.2960131300541987,"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."}}