{"id":"W4409427291","doi":"10.1016/j.esmorw.2025.100139","title":"The complexity of finding fit-for-purpose real-world data for oncology patients with rare NTRK gene fusions and a novel solution","year":2025,"lang":"en","type":"article","venue":"ESMO Real World Data and Digital Oncology","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bayer (Canada); Thermo Fisher Scientific (Canada)","funders":"Bayer Corporation","keywords":"Gene; Computational biology; Computer science; Oncology; Cancer research; Medicine; Bioinformatics; Internal medicine; Biology; Genetics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08486843,0.001673105,0.003855569,0.00691201,0.001854411,0.01007646,0.00500003,0.004538617,0.002395934],"category_scores_gemma":[0.2440282,0.001876787,0.003830381,0.009195558,0.003420908,0.008537354,0.006794481,0.00574605,0.001168028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002872031,"about_ca_system_score_gemma":0.006946426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007129754,"about_ca_topic_score_gemma":0.009212277,"domain_scores_codex":[0.9137494,0.06314154,0.005884813,0.01131222,0.004915951,0.00099605],"domain_scores_gemma":[0.6766366,0.2557788,0.01996308,0.03221325,0.01109942,0.004308817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002019529,0.001485594,0.5442718,0.007100283,0.005536856,0.002577436,0.004558265,0.06953596,0.00405998,0.03682986,0.04298741,0.279037],"study_design_scores_gemma":[0.001251325,0.001493842,0.1185499,0.002961765,0.001693667,0.004254749,0.01361114,0.3199176,0.002888056,0.4692578,0.06363834,0.0004818334],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2182643,0.01537126,0.5766204,0.1390983,0.00103485,0.003332293,0.03844951,0.002181968,0.005647162],"genre_scores_gemma":[0.4818448,0.002181153,0.487705,0.007930317,0.001006102,0.00210517,0.01632991,0.0002518479,0.0006455589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08486843,"threshold_uncertainty_score":0.4488325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08375329033253037,"score_gpt":0.3527131783647943,"score_spread":0.2689598880322639,"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."}}