{"id":"W4400682601","doi":"10.3390/life14070882","title":"Differentiating Gliosarcoma from Glioblastoma: A Novel Approach Using PEACE and XGBoost to Deal with Datasets with Ultra-High Dimensional Confounders","year":2024,"lang":"en","type":"article","venue":"Life","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton; Université du Québec à Trois-Rivières","funders":"","keywords":"GSM; Probabilistic logic; Metric (unit); Confounding; Computer science; Glioblastoma; Gradient boosting; Statistics; Artificial intelligence; Mathematics; Machine learning; Random forest; Medicine","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":[0.0001706659,0.0002257888,0.0003269086,0.0001274778,0.000137701,0.0001463664,0.00007851931,0.00005434391,0.00002743649],"category_scores_gemma":[0.00007447918,0.000152051,0.00002712501,0.0002256683,0.000140206,0.0001041619,0.00005852794,0.0004611616,0.000005011891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004853329,"about_ca_system_score_gemma":0.0001652241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008764386,"about_ca_topic_score_gemma":0.00002883478,"domain_scores_codex":[0.9985182,0.00003387229,0.0001975092,0.0005079034,0.000436318,0.0003061923],"domain_scores_gemma":[0.9990731,0.0002043159,0.00004755288,0.0001996606,0.00003074982,0.0004445837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01340955,0.003377015,0.188306,0.005137716,0.009038956,0.006098313,0.01961482,0.02114131,0.6320758,0.01254339,0.02852418,0.06073291],"study_design_scores_gemma":[0.01041444,0.001617841,0.04183778,0.004000424,0.001435437,0.003228953,0.001518487,0.9239452,0.001663413,0.00007138264,0.009005617,0.00126102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8981149,0.0003207806,0.09934871,0.001515771,0.00007603031,0.000258603,0.0001170668,0.00009968537,0.0001484324],"genre_scores_gemma":[0.9197086,0.000003478925,0.07797144,0.001602797,0.0002948177,0.000008089843,0.0003230993,0.00005174493,0.00003590546],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9028039,"threshold_uncertainty_score":0.620046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01410362956052414,"score_gpt":0.2657087386505754,"score_spread":0.2516051090900512,"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."}}