{"id":"W3094486545","doi":"10.1038/s41598-020-72475-9","title":"Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trillium Health Centre","funders":"National Cancer Institute; Japan Society for the Promotion of Science; Stand Up To Cancer; Cycle for Survival; Uehara Memorial Foundation; Breast Cancer Research Foundation","keywords":"Microsatellite instability; Endometrial cancer; Computed tomography; Contrast (vision); Mutation; Microsatellite; Computer science; Computational biology; Oncology; Internal medicine; Artificial intelligence; Medicine; Bioinformatics; Biology; Radiology; Cancer; 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":[0.001029075,0.0001375524,0.0004273553,0.0002940549,0.00009067415,0.00006373209,0.00005340247,0.00005420363,0.00006200738],"category_scores_gemma":[0.001498792,0.0001260051,0.00008116131,0.0009691428,0.0003798927,0.00008386751,0.00002930454,0.0003746393,6.168436e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008108107,"about_ca_system_score_gemma":0.0002293843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002478921,"about_ca_topic_score_gemma":0.0000343719,"domain_scores_codex":[0.9978778,0.0001230346,0.0007004045,0.0006489168,0.0004501194,0.0001997311],"domain_scores_gemma":[0.9988648,0.0001612439,0.0003926611,0.0002207695,0.0001509267,0.000209619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008297349,0.0001287474,0.3600541,0.0002339562,0.00008357918,0.0005334185,0.002313432,0.01544851,0.590251,0.000005927263,0.000132105,0.02998547],"study_design_scores_gemma":[0.008839905,0.0006408578,0.2298883,0.0004449191,0.000172369,0.00006658066,0.0002386072,0.6161314,0.1382377,0.0006584274,0.004393833,0.0002870727],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885097,0.0005256271,0.008216713,0.0006870639,0.001382804,0.0005327137,0.00002782729,0.0000712715,0.00004633507],"genre_scores_gemma":[0.9970207,0.000007428489,0.00217912,0.0001143664,0.000127667,0.00001026038,0.0005162761,0.00001399554,0.00001014288],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6006829,"threshold_uncertainty_score":0.5138341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009978434354818428,"score_gpt":0.2425943359160481,"score_spread":0.2326159015612297,"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."}}