{"id":"W3156978057","doi":"10.1016/j.clbc.2021.04.005","title":"Improving Collection of Real-World Data: The Experience of the Joven & Fuerte Prospective Cohort for Mexican Young Women With Breast Cancer","year":2021,"lang":"en","type":"article","venue":"Clinical Breast Cancer","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Instituto Nacional de Cancerología; Roche; Novartis; Pfizer; Myriad Genetics; AstraZeneca; Eli Lilly and Company","keywords":"Data collection; Medicine; Data quality; Breast cancer; Missing data; Psychosocial; Prospective cohort study; Medical physics; Consistency (knowledge bases); Cohort; Data science; Gynecology; Cancer; Computer science; Internal medicine; Artificial intelligence; Statistics; Psychiatry","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":[0.0007978499,0.0001890224,0.0006426439,0.00003033688,0.0001925431,0.00002289532,0.0004373305,0.00007361507,0.0002050452],"category_scores_gemma":[0.0002488181,0.0001050034,0.0001387754,0.000918617,0.0007463354,0.0001851854,0.0002446307,0.0003356986,6.282543e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004746455,"about_ca_system_score_gemma":0.001740947,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02508441,"about_ca_topic_score_gemma":0.04605022,"domain_scores_codex":[0.9976653,0.0001101549,0.0006854864,0.0006203097,0.0005447348,0.0003740032],"domain_scores_gemma":[0.9969593,0.0002627427,0.000586989,0.001058914,0.0009861543,0.0001459051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003270246,0.0001112349,0.9814965,0.00008701686,0.0003215403,0.000002657516,0.0008018682,0.00002530731,0.0008348136,0.00006240522,0.001421101,0.01156535],"study_design_scores_gemma":[0.001374553,0.0001433036,0.9940127,0.0004969252,0.0003308789,0.0001113043,0.001644028,0.0002771755,0.0006601888,0.00003975711,0.0007736455,0.0001355826],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918174,0.0002961914,0.000272927,0.004018227,0.0006042349,0.001145011,0.001083353,0.00002433375,0.0007383367],"genre_scores_gemma":[0.9958385,0.0003645571,0.0002971135,0.000686896,0.000580557,0.0006147564,0.00001572239,0.00002679012,0.001575144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02096581,"threshold_uncertainty_score":0.9814076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08796769502643914,"score_gpt":0.4126427011646951,"score_spread":0.324675006138256,"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."}}