{"id":"W4367678680","doi":"10.3390/computers12050095","title":"Rethinking Densely Connected Convolutional Networks for Diagnosing Infectious Diseases","year":2023,"lang":"en","type":"article","venue":"Computers","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Hyperparameter; Computer science; Transfer of learning; Convolutional neural network; Artificial intelligence; Deep learning; Receiver operating characteristic; Coronavirus disease 2019 (COVID-19); Machine learning; Precision and recall; F1 score; Pattern recognition (psychology); Medicine; Pathology; Infectious disease (medical specialty); Disease","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":[0.0001823276,0.0001640374,0.0002876197,0.0002194363,0.0002545477,0.00006211309,0.00009551564,0.00009872682,0.0000143326],"category_scores_gemma":[0.0007812553,0.0001736863,0.0001650271,0.000527247,0.00009624403,0.00006737253,0.00008938108,0.0001578529,0.00002905075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002282068,"about_ca_system_score_gemma":0.0001620018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002697545,"about_ca_topic_score_gemma":0.00000853705,"domain_scores_codex":[0.9987663,0.00004924234,0.0002312594,0.0003663607,0.0002058593,0.0003809988],"domain_scores_gemma":[0.9958999,0.003436595,0.00008257169,0.0002338439,0.0001734139,0.0001737477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002052191,0.0003067187,0.1513557,0.0004691055,0.0003821603,0.0002870358,0.0009816701,0.0877637,0.0002199573,0.002557121,0.7367918,0.01867984],"study_design_scores_gemma":[0.003846721,0.0003220484,0.2265037,0.0009800628,0.0002891486,0.00005794169,0.00002202752,0.7257621,0.00007293011,0.002956818,0.03880139,0.0003850804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7551059,0.0007790964,0.2038819,0.03084188,0.004699632,0.001559278,0.00004317981,0.003054794,0.00003441894],"genre_scores_gemma":[0.9781993,0.00006418528,0.001185387,0.01914068,0.0009278525,0.0001067194,0.0002847808,0.00004838706,0.00004269533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6979904,"threshold_uncertainty_score":0.7082723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03803358597651233,"score_gpt":0.3080784421247301,"score_spread":0.2700448561482177,"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."}}