{"id":"W3165071810","doi":"10.1016/j.imu.2021.100620","title":"COV-SNET: A deep learning model for X-ray-based COVID-19 classification","year":2021,"lang":"en","type":"article","venue":"Informatics in Medicine Unlocked","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Deep learning; Coronavirus disease 2019 (COVID-19); Artificial intelligence; Transfer of learning; Computer science; Robustness (evolution); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Machine learning; Offset (computer science); Artificial neural network; Medicine; Infectious disease (medical specialty); Pathology; Disease","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001420102,0.0002993406,0.0007103871,0.0005917876,0.0001808455,0.00003165495,0.0002007537,0.0002446678,0.00009955842],"category_scores_gemma":[0.01285799,0.0002762543,0.0001252352,0.0008463798,0.0002276428,0.0001540368,0.00005519691,0.0005833327,0.00002785751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008742512,"about_ca_system_score_gemma":0.001909678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004899825,"about_ca_topic_score_gemma":0.0001122165,"domain_scores_codex":[0.9971415,0.0000866128,0.00129014,0.0002875928,0.0007074787,0.0004866218],"domain_scores_gemma":[0.9963083,0.001786239,0.0003965302,0.000634493,0.0005023119,0.0003721245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001312796,0.00115333,0.01428476,0.01048864,0.0002604976,0.0002222925,0.06771562,0.786718,0.01079276,0.004575354,0.07582798,0.02664793],"study_design_scores_gemma":[0.008389166,0.0002618485,0.000357401,0.000583435,0.0001633822,0.00002501973,0.003587288,0.8797739,0.0005025914,0.0005201022,0.1056026,0.0002331813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0543088,0.000312782,0.8570764,0.08522205,0.0003051567,0.00153425,0.00001331391,0.0003287925,0.0008984564],"genre_scores_gemma":[0.7469634,0.0001442774,0.06776407,0.1830064,0.0002686732,0.000397835,0.0008272453,0.00007672885,0.0005513876],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7893124,"threshold_uncertainty_score":0.9999689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09894683164934899,"score_gpt":0.388953911736358,"score_spread":0.290007080087009,"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."}}