{"id":"W4408664434","doi":"10.2196/62833","title":"Association Between Risk Factors and Major Cancers: Explainable Machine Learning Approach","year":2025,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Association (psychology); Risk factor; Cancer; Protective factor; Factor (programming language); Medicine; Oncology; Psychology; Computer science; Internal medicine; World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003066316,0.0001671379,0.0002167885,0.0001505941,0.0003582611,0.0001697617,0.0003091848,0.0001291187,0.00002242403],"category_scores_gemma":[0.00005537965,0.0001555426,0.00004975787,0.0006197426,0.00002276013,0.0004910631,0.000182271,0.0004091162,0.000003531351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001716792,"about_ca_system_score_gemma":0.000168569,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007216594,"about_ca_topic_score_gemma":0.0003258251,"domain_scores_codex":[0.9986473,0.0001202212,0.0001883005,0.0004625909,0.0002628096,0.0003187498],"domain_scores_gemma":[0.9992528,0.0001387646,0.0002253929,0.0002435599,0.00007695792,0.00006254024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007200344,0.000009682775,0.9601413,0.000056758,0.0001577862,3.784216e-7,0.0009289011,0.001512839,0.00004754755,0.0002741704,0.002339888,0.03452357],"study_design_scores_gemma":[0.001681372,0.0001717667,0.6753166,0.0001316427,0.0001925384,9.887488e-7,0.0003277319,0.134984,0.005459778,0.002129867,0.1788398,0.0007638985],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5950649,0.003562138,0.3873295,0.001451142,0.001481402,0.0009977453,0.0000600988,0.0007549088,0.009298212],"genre_scores_gemma":[0.9910553,0.0004211114,0.002272745,0.0000971574,0.0001908051,0.0003274733,0.000006962751,0.00001446165,0.005614002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3959904,"threshold_uncertainty_score":0.9993944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01374000277521076,"score_gpt":0.268782725291892,"score_spread":0.2550427225166812,"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."}}