{"id":"W4410946881","doi":"10.2196/64506","title":"Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study","year":2025,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Logistic regression; Medicine; Random forest; Cohort; Machine learning; Confounding; Colorectal cancer; Artificial intelligence; Propensity score matching; Nomogram; Cancer; Oncology; Internal medicine; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006996649,0.0005727515,0.0006701713,0.001371128,0.000828747,0.001228875,0.001228071,0.00122325,0.001466098],"category_scores_gemma":[0.01533226,0.0006673832,0.00116966,0.001278395,0.0007374806,0.000736775,0.0007420198,0.001401429,0.0002390866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007019152,"about_ca_system_score_gemma":0.000734196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005803341,"about_ca_topic_score_gemma":0.004792098,"domain_scores_codex":[0.9957808,0.002081599,0.0003794464,0.001012358,0.0004608221,0.0002849135],"domain_scores_gemma":[0.9885151,0.005872631,0.002452208,0.002040743,0.0006761583,0.0004431459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001716864,0.001018708,0.989654,0.00009174878,0.0009176776,0.000489149,0.0001543988,0.001071088,0.0003002516,0.0002785449,0.0004854403,0.00382206],"study_design_scores_gemma":[0.0004953379,0.002290197,0.9630904,0.0001180714,0.001168776,0.002147134,0.0004528202,0.02709263,0.0005287472,0.0007342757,0.001813595,0.00006802331],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969125,0.00052225,0.00162347,0.0001089736,0.0000202102,0.0001040109,0.0004561136,0.000009681697,0.0002427431],"genre_scores_gemma":[0.9974389,0.0001598568,0.001360085,0.00005134169,0.00003846554,0.0001194795,0.0007191462,0.00000432287,0.0001083633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006996649,"threshold_uncertainty_score":0.03700227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04037719020193765,"score_gpt":0.3745165215935605,"score_spread":0.3341393313916229,"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."}}