{"id":"W3120864196","doi":"10.1016/j.ejrad.2021.109552","title":"Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features","year":2021,"lang":"en","type":"article","venue":"European Journal of Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"China Scholarship Council; Wellcome Trust; Health Service Executive; Royal College of Surgeons in Ireland; China Postdoctoral Science Foundation; Canadian Institute for Theoretical Astrophysics","keywords":"Medicine; Radiomics; Coronavirus disease 2019 (COVID-19); Receiver operating characteristic; Artificial intelligence; Random forest; Pneumonia; Kappa; Radiology; Cohen's kappa; Pattern recognition (psychology); Nuclear medicine; Machine learning; Internal medicine; Disease; Computer science; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002003367,0.0005630047,0.0007596087,0.002808996,0.00023784,0.0009555238,0.0004679064,0.0007492354,0.0006415371],"category_scores_gemma":[0.004576872,0.0001979357,0.000532781,0.0005314464,0.0002187909,0.0006190505,0.000600784,0.0003311116,0.0005003755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003211599,"about_ca_system_score_gemma":0.0002735816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000948708,"about_ca_topic_score_gemma":0.001454443,"domain_scores_codex":[0.9990565,0.0002108704,0.0001197684,0.0003093264,0.0001902211,0.0001132276],"domain_scores_gemma":[0.9982591,0.0005404463,0.0004564802,0.0001383041,0.0004499252,0.000155676],"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":[0.001232439,0.0001976935,0.8708547,0.0001535981,0.0001951145,0.0004801486,0.0001150794,0.005911828,0.02959201,0.00009918286,0.0009291192,0.09023898],"study_design_scores_gemma":[0.00005121352,0.0005814072,0.786635,0.0000701426,0.0002140274,0.002175767,0.0002430618,0.192876,0.01531836,0.0004332516,0.001343347,0.00005847513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9772593,0.0007752916,0.01996337,0.000101707,0.00003692753,0.00008787354,0.0008238043,0.0002217645,0.0007300256],"genre_scores_gemma":[0.9856825,0.0001282396,0.01257229,0.00003256551,0.00004541948,0.00003750273,0.001312848,0.00001591237,0.000172554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002808996,"threshold_uncertainty_score":0.01059496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02945081606757059,"score_gpt":0.3023062421771026,"score_spread":0.272855426109532,"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."}}