{"id":"W4392137444","doi":"10.1016/j.heliyon.2024.e26939","title":"A hybridized feature extraction for COVID-19 multi-class classification on computed tomography images","year":2024,"lang":"en","type":"article","venue":"Heliyon","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Support vector machine; Pattern recognition (psychology); Feature extraction; Computer science; Classifier (UML); Coronavirus disease 2019 (COVID-19); Histogram of oriented gradients; Histogram; Feature (linguistics); Machine learning; Deep learning; Medicine; Pathology","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":[0.0003552375,0.0002500757,0.0003072324,0.0005826018,0.0001652606,0.0001349994,0.00009526044,0.0002029583,0.00005089655],"category_scores_gemma":[0.0007093243,0.0002269372,0.0002889624,0.0006198229,0.00006778235,0.0001284554,0.00002031134,0.0003736231,0.0001073765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005188645,"about_ca_system_score_gemma":0.0003342497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002497527,"about_ca_topic_score_gemma":0.00001938822,"domain_scores_codex":[0.9983605,0.00007879274,0.0002671925,0.0006714491,0.0003243956,0.0002977046],"domain_scores_gemma":[0.9980116,0.001051151,0.0000890287,0.0004246185,0.0001525844,0.0002709698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001876464,0.001596167,0.001320215,0.01186861,0.0003752339,0.0002743985,0.0006967206,0.0003629816,0.3309391,0.001217896,0.6157811,0.03369108],"study_design_scores_gemma":[0.003517824,0.0004676334,0.01591118,0.001791192,0.0003004819,0.00008032011,0.00008334681,0.02912697,0.0238772,0.00006120474,0.9244697,0.0003129553],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.07047132,0.01825806,0.1967468,0.6952465,0.005450532,0.007517733,0.0005955367,0.005228506,0.0004850159],"genre_scores_gemma":[0.8890024,0.001764703,0.02038625,0.08085292,0.001775053,0.001078847,0.001173367,0.0002415707,0.003724916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.818531,"threshold_uncertainty_score":0.9254231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0635331868377676,"score_gpt":0.3845975216815026,"score_spread":0.321064334843735,"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."}}