{"id":"W4413848866","doi":"10.1016/j.knosys.2025.114383","title":"Prostate cancer forecasting in small samples based on lightweight neural networks using ensemble learning","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nipissing University","funders":"National Natural Science Foundation of China","keywords":"Artificial neural network; Ensemble learning; Prostate cancer; Computer science; Artificial intelligence; Machine learning; Ensemble forecasting; Cancer; Medicine; Internal 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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.002045234,0.0004254528,0.0007265047,0.000676772,0.001532945,0.00005780265,0.0003288834,0.0004958549,0.00006509795],"category_scores_gemma":[0.0008918273,0.0003943927,0.0001300487,0.001352525,0.00008049572,0.00009117626,0.00009107753,0.001835128,0.00005540359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001505968,"about_ca_system_score_gemma":0.001749438,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01223716,"about_ca_topic_score_gemma":0.02952024,"domain_scores_codex":[0.9933582,0.002726163,0.001573163,0.0007567698,0.0002174843,0.001368235],"domain_scores_gemma":[0.9942113,0.003907029,0.0005288144,0.0004996854,0.0006417636,0.0002114753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001932235,0.00006298802,0.4670506,0.001523239,0.000009331737,0.00001450499,0.001316725,0.5241205,0.0001310167,0.0002935485,0.0001965589,0.005087762],"study_design_scores_gemma":[0.0005400894,0.0001023909,0.001406161,0.008398158,0.00002104442,4.287526e-7,0.002377759,0.9820666,0.000306975,0.00004381579,0.004409931,0.0003266161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9470875,0.004909234,0.02797518,0.0007813331,0.008988461,0.00442324,0.00002815997,0.0004316046,0.005375267],"genre_scores_gemma":[0.995596,0.000012285,0.0002178906,0.0004493441,0.0008315246,0.00096344,0.00003393507,0.00008722217,0.001808349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4656445,"threshold_uncertainty_score":0.9998508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2263426364595368,"score_gpt":0.4359370765796723,"score_spread":0.2095944401201355,"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."}}