{"id":"W4409965136","doi":"10.1186/s12885-025-14204-x","title":"Exploring the potential of machine learning in gastric cancer: prognostic biomarkers, subtyping, and stratification","year":2025,"lang":"en","type":"article","venue":"BMC Cancer","topic":"Gastric Cancer Management and Outcomes","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Cancer Research Center, Tehran University of Medical Sciences; Tehran University of Medical Sciences and Health Services","keywords":"Subtyping; Surgical oncology; Medicine; Stratification (seeds); Risk stratification; Oncology; Cancer; Internal medicine; Computational biology; Biology; Computer science","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":[0.0001661465,0.00008864519,0.0001652668,0.0002007991,0.0000527923,0.00001604846,0.00005983724,0.0000190532,0.00005289059],"category_scores_gemma":[0.00006610263,0.00006629185,0.00003725287,0.0005513604,0.00004876346,0.00007117731,0.00004105519,0.000123674,4.331409e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009305685,"about_ca_system_score_gemma":0.0001510565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003016802,"about_ca_topic_score_gemma":0.002412987,"domain_scores_codex":[0.999308,0.00003295503,0.0002107598,0.0001733411,0.0001283036,0.0001466317],"domain_scores_gemma":[0.9996807,0.00005667907,0.00008435151,0.000116936,0.00003780585,0.00002352806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001569266,0.00002026682,0.9140232,0.0002907649,0.00006149767,0.000001702714,0.0001015212,0.0004291704,0.0009991573,0.0001519435,0.0001807623,0.08358315],"study_design_scores_gemma":[0.0009793877,0.00003511495,0.9923615,0.0002915856,0.0001634253,0.000001311658,0.0003004371,0.004282447,0.0002699283,0.0000250692,0.00123759,0.00005219819],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892685,0.006892669,0.0007508429,0.001767628,0.0003053025,0.0005228412,0.000004358744,0.00002839233,0.0004594675],"genre_scores_gemma":[0.995123,0.003332596,0.0001475631,0.0000638913,0.00006392564,0.0002116709,0.000007325119,0.000007489825,0.001042587],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08353095,"threshold_uncertainty_score":0.4560523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04419170229673327,"score_gpt":0.2915249625757961,"score_spread":0.2473332602790628,"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."}}