{"id":"W3201105472","doi":"10.21203/rs.3.rs-883606/v1","title":"Dataset Size Sensitivity Analysis of Machine Learning Classifiers to Differentiate Molecular Markers of Pediatric Low-Grade Gliomas Based on MRI","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Glioma Diagnosis and Treatment","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Random forest; Artificial intelligence; Receiver operating characteristic; Radiomics; Medicine; Machine learning; Glioma; Artificial neural network; Training set; Sample size determination; Cross-validation; Area under the curve; Internal medicine; Computer science; Statistics; Mathematics","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":[0.001774673,0.0004307745,0.001507557,0.00298441,0.0001018363,0.00006373385,0.0002272287,0.0003232463,0.0004123751],"category_scores_gemma":[0.002264082,0.000378628,0.0008685217,0.003647168,0.0001203869,0.00002679669,0.0007880123,0.001342843,0.000008783982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003508057,"about_ca_system_score_gemma":0.0004705901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001895716,"about_ca_topic_score_gemma":0.0002929149,"domain_scores_codex":[0.9934064,0.001815121,0.0006330484,0.001095055,0.002394584,0.0006557532],"domain_scores_gemma":[0.9948066,0.00199354,0.0002903602,0.001658773,0.0007153915,0.000535346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002719701,0.007076088,0.8098891,0.007441222,0.01066297,0.008749418,0.000288683,0.1216467,0.02782711,0.00002126371,0.002270991,0.001406702],"study_design_scores_gemma":[0.003203757,0.001751454,0.827581,0.001677851,0.007375316,0.000004652476,0.0004312287,0.1199969,0.03730808,0.000008607922,0.0001413044,0.0005198485],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892884,0.0006946097,0.0003535849,0.001106546,0.00006369239,0.001226106,0.007157023,0.00002453984,0.00008552954],"genre_scores_gemma":[0.9803465,0.000444709,0.0005493178,0.00005001996,0.00004918615,0.0001182826,0.01836673,0.0000551381,0.00002010173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01769187,"threshold_uncertainty_score":0.9998665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03925411078944597,"score_gpt":0.3672442191624218,"score_spread":0.3279901083729759,"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."}}