{"id":"W6939675451","doi":"10.6084/m9.figshare.26559653.v1","title":"Additional file 1 of A deep learning model for the classification of atrial fibrillation in critically ill patients","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Atrial fibrillation; Sinus rhythm; Deep learning; Critically ill; Noise (video); Table (database); Pattern recognition (psychology); Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009487085,0.00113333,0.0008308594,0.001042171,0.0003564407,0.00101406,0.001714764,0.001190112,0.7408426],"category_scores_gemma":[0.01467658,0.0004284688,0.0007467339,0.001226259,0.0001895549,0.0009482697,0.0007722111,0.0009248723,0.1590436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006251694,"about_ca_system_score_gemma":0.001105667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003823735,"about_ca_topic_score_gemma":0.01010553,"domain_scores_codex":[0.9997451,0.00004149579,0.00003518738,0.00009027464,0.00005429586,0.00003363516],"domain_scores_gemma":[0.9948798,0.00381362,0.0002240564,0.000363357,0.0005806669,0.0001384494],"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":[0.0003440595,0.00008817524,0.003177356,0.001253263,0.00005866997,0.000088396,0.00002057611,0.001972054,0.0001545757,0.0004823868,0.974562,0.01779847],"study_design_scores_gemma":[0.00880178,0.001009141,0.03970437,0.003531521,0.0003700655,0.001606375,0.0003095068,0.05256138,0.003670662,0.02936523,0.8588009,0.0002691104],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0004340227,0.00003144215,0.0009822941,0.0001468219,0.00003656161,0.00006642346,0.9969898,0.0007739775,0.0005385606],"genre_scores_gemma":[0.0115806,0.0001199717,0.007142391,0.0004769393,0.0001336439,0.001035658,0.9731849,0.0007250482,0.005600772],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7408426,"threshold_uncertainty_score":0.3696566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09023552084011013,"score_gpt":0.3301007657649728,"score_spread":0.2398652449248627,"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."}}