{"id":"W4380200289","doi":"10.1038/s41698-023-00406-8","title":"Bayesian risk prediction model for colorectal cancer mortality through integration of clinicopathologic and genomic data","year":2023,"lang":"en","type":"article","venue":"npj Precision Oncology","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences; National Cancer Institute; National Heart, Lung, and Blood Institute; Gary Bennett Family Fund; National Institutes of Health; Orionin Tutkimussäätiö; Suomen Kulttuurirahasto; Mitsukoshi Health and Welfare Foundation; American Association for Cancer Research; American Society of Clinical Oncology; Japan Society for the Promotion of Science; Prevent Cancer Foundation; Cancer Research UK; Conquer Cancer Foundation; Stand Up To Cancer; Centers for Disease Control and Prevention","keywords":"Interpretability; Colorectal cancer; Oncology; Medicine; Internal medicine; Hazard ratio; Proportional hazards model; Cancer; Machine learning; Computer science; Confidence interval","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001285789,0.0001333897,0.0004291279,0.0001257696,0.0001185257,0.0000086961,0.0001272861,0.0003015499,0.00002465128],"category_scores_gemma":[0.0008934864,0.0001123542,0.00007369595,0.0002705395,0.0001185612,0.0001572664,0.0001865794,0.0002470558,0.000003445108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000176196,"about_ca_system_score_gemma":0.0002791821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003250321,"about_ca_topic_score_gemma":0.001107321,"domain_scores_codex":[0.9984349,0.0001349593,0.000521765,0.0005383521,0.0001769595,0.0001930456],"domain_scores_gemma":[0.998601,0.0004719501,0.0003039261,0.0003868839,0.0001671789,0.00006911366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01874636,0.0002953685,0.08245319,0.0001378719,0.0001692836,0.00001005802,0.002338673,0.006397001,0.05333216,0.00008078907,0.007393991,0.8286452],"study_design_scores_gemma":[0.001685989,0.004068506,0.184956,0.00004805926,0.0002504206,0.00002362375,0.0001592279,0.8033692,0.001977728,0.002556154,0.0008215171,0.00008354441],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8427629,0.0002371128,0.1543076,0.0001956615,0.0005706864,0.0007984734,0.0006744524,0.0001353638,0.000317718],"genre_scores_gemma":[0.987525,0.001919812,0.009567273,0.00007642947,0.0002140583,0.0002082648,0.0003477043,0.00001909429,0.0001223371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8285617,"threshold_uncertainty_score":0.4581672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1643315568415908,"score_gpt":0.4394133971430981,"score_spread":0.2750818403015072,"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."}}