{"id":"W2549514397","doi":"10.1016/j.patcog.2016.11.007","title":"A multi-kernel based framework for heterogeneous feature selection and over-sampling for computer-aided detection of pulmonary nodules","year":2016,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Ministry of Science and Technology; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Artificial intelligence; Pattern recognition (psychology); Feature selection; Kernel (algebra); Computer science; Feature (linguistics); Pairwise comparison; Multiple kernel learning; CAD; Kernel method; Machine learning; Mathematics; Support vector machine; Engineering","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":[0.0001651482,0.000169978,0.0002596871,0.0001694227,0.00009602456,0.00001958827,0.00003326582,0.0002173479,0.00001075332],"category_scores_gemma":[0.0003092151,0.0001437781,0.0001392325,0.00009483063,0.00002838596,0.00007984824,0.00001510805,0.00009241536,0.000002401786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001197174,"about_ca_system_score_gemma":0.00002233915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004041203,"about_ca_topic_score_gemma":0.00005046689,"domain_scores_codex":[0.9989942,0.00003749515,0.0002364722,0.0004011694,0.000123854,0.0002068439],"domain_scores_gemma":[0.9984572,0.0009161853,0.0001899218,0.0001314139,0.0002326566,0.00007262186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005843804,0.0002973817,0.006827422,0.0008701258,0.00005606676,0.000001876254,0.00003980022,0.00003586671,0.2782767,2.99178e-7,0.00003384176,0.7129762],"study_design_scores_gemma":[0.008008023,0.002073815,0.07406012,0.005115954,0.0005523583,0.0001301659,0.00001748839,0.2869473,0.6203191,0.001432918,0.0007958939,0.0005468741],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4321299,0.00003733203,0.5659795,0.0008281684,0.0001560957,0.0006866736,0.0001215116,0.00006070895,1.306296e-7],"genre_scores_gemma":[0.9095949,0.00002757686,0.08788741,0.001685299,0.0003506138,0.0002966684,0.0001071955,0.00004574962,0.000004608095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7124293,"threshold_uncertainty_score":0.58631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05678598965032451,"score_gpt":0.3248705977243455,"score_spread":0.268084608074021,"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."}}