{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001274835,0.0005749656,0.0007173807,0.002195799,0.0001941278,0.0006962708,0.0003989572,0.0004367233,0.0003065872],"category_scores_gemma":[0.004085619,0.0001639921,0.0008109575,0.001311134,0.0001219855,0.0003560382,0.0003438164,0.0006435461,0.0002378946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004256827,"about_ca_system_score_gemma":0.0005232176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003869137,"about_ca_topic_score_gemma":0.00586622,"domain_scores_codex":[0.9994608,0.0001577948,0.00004828344,0.0001452989,0.0001365301,0.00005142153],"domain_scores_gemma":[0.9985645,0.0007986534,0.0002151619,0.0001430508,0.0002277777,0.00005087445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005468345,0.0003809773,0.5025673,0.000228934,0.0006498485,0.0009955852,0.0001337451,0.1374604,0.01707537,0.0007843815,0.003385248,0.3357914],"study_design_scores_gemma":[0.00004986031,0.0002743,0.165153,0.00007156812,0.0001901716,0.000648978,0.0001405162,0.8164465,0.009497449,0.004614757,0.002857108,0.00005574364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8670127,0.002270408,0.1244537,0.0005434821,0.00007680939,0.0001034869,0.003822437,0.0007714484,0.0009455536],"genre_scores_gemma":[0.9450972,0.0004383796,0.04881261,0.00007752536,0.0000582073,0.00005672088,0.005168962,0.00002049052,0.000269998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003869137,"threshold_uncertainty_score":0.007693231,"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."}}