{"id":"W4416574723","doi":"10.1007/s44230-025-00118-1","title":"Prediction of Risk Factors from Gastric Cancer Genetic Data Using Machine Learning","year":2025,"lang":"en","type":"article","venue":"Human-Centric Intelligent Systems","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Science and Engineering Research Board; Department of Biotechnology, Ministry of Science and Technology, India","keywords":"Random forest; Feature selection; Interpretability; Undersampling; Preprocessor; Precision and recall; Classifier (UML); Matthews correlation coefficient; Overfitting","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":[0.0001660797,0.0001757427,0.00021284,0.0001810114,0.0001668568,0.0000342606,0.0004065726,0.0001472168,0.00006933117],"category_scores_gemma":[0.00009038691,0.0001603143,0.00006663767,0.000288519,0.00003853688,0.000006300485,0.0001988612,0.0001462798,0.000002918779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007685086,"about_ca_system_score_gemma":0.000100588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003909919,"about_ca_topic_score_gemma":0.00006577696,"domain_scores_codex":[0.9983735,0.0002074151,0.0005018344,0.0005101408,0.0002061439,0.0002009647],"domain_scores_gemma":[0.9987264,0.00002390286,0.0003770982,0.0006910059,0.0001230629,0.00005851563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005174288,0.0001216012,0.5595368,0.00008760892,0.0002470125,6.908456e-7,0.0001522494,0.01749296,0.4182592,0.00003478223,0.001764071,0.002251337],"study_design_scores_gemma":[0.002169408,0.0003059559,0.143363,0.0008704026,0.0009721356,0.00000719418,0.004223735,0.283976,0.4114226,0.00007142324,0.1517336,0.0008845257],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.916326,0.01621736,0.06540321,0.000003667396,0.001099193,0.0003007098,0.0005123979,0.00002113295,0.0001163651],"genre_scores_gemma":[0.995101,0.002742196,0.0001031075,0.000007869891,0.0002671833,0.00001620588,0.001265019,0.00001911289,0.0004783394],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4161738,"threshold_uncertainty_score":0.6537426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07674531389958915,"score_gpt":0.3141559396423136,"score_spread":0.2374106257427244,"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."}}