{"id":"W4391971096","doi":"10.21203/rs.3.rs-3853941/v1","title":"A Study on the Feasibility of Optimizing Gastric Cancer Screening to Reduce Screening Costs in China Using a Gradient Boosting Machine: A prospective, large-sample, single-center study","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Gastric Cancer Management and Outcomes","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Science and Technology Program of Zhejiang Province; Medical Science and Technology Project of Zhejiang Province","keywords":"Boosting (machine learning); Gradient boosting; Center (category theory); Cancer; China; Sample (material); Single Center; Medicine; Computer science; Artificial intelligence; Internal medicine; Geography; Chromatography; Chemistry","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":[0.01102693,0.00071467,0.0006854394,0.0003956906,0.0003528509,0.0005045706,0.0007225478,0.0007092299,0.0006994445],"category_scores_gemma":[0.01175211,0.0003849899,0.001005038,0.0004306772,0.0003931831,0.0006276667,0.0004558944,0.0004832151,0.0001108847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001288147,"about_ca_system_score_gemma":0.002653587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01004916,"about_ca_topic_score_gemma":0.006266742,"domain_scores_codex":[0.9982225,0.001265001,0.00006677791,0.0001866103,0.0001275519,0.0001315321],"domain_scores_gemma":[0.9965642,0.001729547,0.0004133819,0.0004162224,0.0005605163,0.0003161485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01146904,0.007671885,0.8311168,0.000380067,0.001039875,0.000500961,0.0006879985,0.05155243,0.004361612,0.0008084577,0.001596806,0.08881403],"study_design_scores_gemma":[0.002972154,0.03253596,0.6879122,0.0000679545,0.001246901,0.0002287975,0.0006545493,0.2682168,0.003958306,0.0005474065,0.001593959,0.00006499916],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970549,0.0000853036,0.002326115,0.0001338706,0.000007022542,0.0001783613,0.00006302797,0.00001428522,0.000137048],"genre_scores_gemma":[0.9954907,0.00005827354,0.003959225,0.00008049421,0.000008732511,0.000152241,0.0001420518,0.000005950582,0.0001023303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01102693,"threshold_uncertainty_score":0.05831671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2081479970598199,"score_gpt":0.45838744491614,"score_spread":0.2502394478563201,"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."}}