{"id":"W4413259220","doi":"10.4258/hir.2025.31.3.284","title":"Machine Learning-Based Age Prediction with Feature Subset Selection from Magnetic Resonance Angiography Data","year":2025,"lang":"en","type":"article","venue":"Healthcare Informatics Research","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; Ministry of Education; National Research Foundation","keywords":"Random forest; Feature selection; Tortuosity; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Linear regression; Pearson product-moment correlation coefficient; Computer science; Magnetic resonance imaging; AdaBoost; Magnetic resonance angiography; Statistics; Mathematics; Machine learning; Medicine; Radiology; Support vector machine","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":[0.001227022,0.000156589,0.0002990146,0.001008642,0.0004174251,0.0001374973,0.0002851793,0.000143444,0.00003664359],"category_scores_gemma":[0.0003178503,0.0001217433,0.00008123561,0.00304968,0.0001625275,0.0002195286,0.000105986,0.00153734,0.00001849025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000135844,"about_ca_system_score_gemma":0.0005210562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003981988,"about_ca_topic_score_gemma":0.001023674,"domain_scores_codex":[0.9975843,0.0002696394,0.0003893371,0.0002694557,0.001007797,0.0004794247],"domain_scores_gemma":[0.9980211,0.0002274817,0.00008159821,0.0007683319,0.000706278,0.0001952231],"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":[0.00122017,0.0001541535,0.8785723,0.001713658,0.0001513309,0.00006412225,0.0007658405,0.0002866784,0.00005822658,0.00006226095,0.04211896,0.07483232],"study_design_scores_gemma":[0.001750897,0.001250395,0.1563219,0.001646705,0.0001627478,0.0000221528,0.0009348273,0.6001616,0.0001370204,0.00008885365,0.2373586,0.0001642487],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5528542,0.1459233,0.03984849,0.217663,0.0007246932,0.008913867,0.005819408,0.002671597,0.02558137],"genre_scores_gemma":[0.974488,0.001548213,0.01090943,0.001382052,0.0001418926,0.00006213071,0.008374516,0.00003253837,0.003061185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7222503,"threshold_uncertainty_score":0.6679063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05907084053323545,"score_gpt":0.3908488979245628,"score_spread":0.3317780573913274,"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."}}