{"id":"W2049624386","doi":"10.1007/s12551-009-0023-6","title":"Creating robust, reliable, clinically relevant classifiers from spectroscopic data","year":2009,"lang":"en","type":"review","venue":"Biophysical Reviews","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Machine learning; Data mining","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"],"consensus_categories":[],"category_scores_codex":[0.0008496331,0.0009152139,0.004000233,0.00007570464,0.0001656755,0.0001001397,0.001804781,0.0006058739,0.00008161554],"category_scores_gemma":[0.001621574,0.0006541289,0.001110263,0.0003903001,0.0001506122,0.000009436793,0.001129011,0.0007164397,0.0004247523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005656612,"about_ca_system_score_gemma":0.0002918625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002779001,"about_ca_topic_score_gemma":0.000008337054,"domain_scores_codex":[0.9946918,0.0003946309,0.001959555,0.002007457,0.0002945373,0.0006520428],"domain_scores_gemma":[0.9949434,0.0001521199,0.001217393,0.00337536,0.00005980759,0.0002519436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002013007,0.0002083144,0.000003729332,0.002387893,0.0004153302,0.00001031875,0.000003300235,1.735633e-7,0.001105835,0.0003245115,0.06088425,0.9346362],"study_design_scores_gemma":[0.0001808902,0.000315154,0.000008965274,0.00401997,0.001276244,0.000002957301,0.000002571513,0.00001183505,0.00002336804,0.0001061358,0.9933879,0.0006640422],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001425427,0.9936011,0.0004875264,0.00005605679,0.0004783049,0.001201927,0.0003426407,0.00002904575,0.003789104],"genre_scores_gemma":[0.000001623205,0.9738603,0.01643224,0.0002835834,0.003238723,0.00009291882,0.004005998,0.00008883268,0.001995749],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9339722,"threshold_uncertainty_score":0.999591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1236308932161407,"score_gpt":0.3834250146392627,"score_spread":0.259794121423122,"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."}}