{"id":"W4411902584","doi":"10.7717/peerj-cs.2968","title":"Comparison of EfficientNet CNN models for multi-label chest X-ray disease diagnosis","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"X-ray; Computer science; Physics; Optics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007054408,0.0002009521,0.0004823831,0.0004518334,0.0002428662,0.00008782367,0.0006424978,0.00004879792,0.000007737583],"category_scores_gemma":[0.0005360588,0.0001841088,0.0001256025,0.001242479,0.000587569,0.0002030587,0.0003589562,0.0001243347,0.000007588747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001627528,"about_ca_system_score_gemma":0.0007593417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004901498,"about_ca_topic_score_gemma":0.00000539542,"domain_scores_codex":[0.997699,0.00002914356,0.0004395729,0.0007424131,0.0006365407,0.0004533255],"domain_scores_gemma":[0.9976047,0.0006507075,0.0001369136,0.0007145848,0.0005853434,0.0003077428],"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":[0.0004872539,0.01513229,0.3774776,0.003064302,0.0001249934,0.00002682231,0.003609855,0.2696702,0.004480719,0.006582899,0.09924892,0.2200941],"study_design_scores_gemma":[0.001740705,0.0002221655,0.05976485,0.0004515784,0.0001097143,3.790482e-7,0.00001345054,0.930659,0.003485837,0.0001129664,0.003285305,0.0001540632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1858651,0.0003955029,0.798851,0.01292335,0.000836824,0.0009510345,0.00002875351,0.0001218906,0.00002651053],"genre_scores_gemma":[0.8307359,0.00001146174,0.1638676,0.005026836,0.00007043748,0.0001377439,0.000009546321,0.00001226466,0.0001281992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6609887,"threshold_uncertainty_score":0.750774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1163668389434021,"score_gpt":0.41776606656497,"score_spread":0.3013992276215678,"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."}}