{"id":"W2551779716","doi":"10.1109/ijcnn.2016.7727866","title":"Feature leaning with deep Convolutional Neural Networks for screening patients with paroxysmal atrial fibrillation","year":2016,"lang":"en","type":"article","venue":"","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Feature extraction; Classifier (UML); Pattern recognition (psychology); Deep learning; Atrial fibrillation; Feature (linguistics); Artificial neural network; Paroxysmal atrial fibrillation; Machine learning; Cardiology; Medicine","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":[0.00007667242,0.0001271108,0.0001979255,0.00005410661,0.0001372064,0.00001824959,0.00002997275,0.00007312048,0.0000217891],"category_scores_gemma":[0.00004511475,0.00006307732,0.0001022849,0.0001260926,0.0000402385,0.0001130588,0.0000113118,0.0000746895,0.000001283224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003494501,"about_ca_system_score_gemma":0.00002132142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001368621,"about_ca_topic_score_gemma":0.00001662719,"domain_scores_codex":[0.9991792,0.00001544226,0.0001069312,0.0002236103,0.0002408349,0.0002339707],"domain_scores_gemma":[0.9993501,0.0001365183,0.0000820067,0.000114738,0.0002200249,0.00009657108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001726505,0.00000631121,0.9546191,0.000009932307,0.0001752235,0.000001534321,0.00001084906,0.008970669,0.00001633623,0.00003304584,0.0001908202,0.03423971],"study_design_scores_gemma":[0.01695286,0.00210284,0.5830449,0.000394158,0.0008526117,0.00001972288,0.00008452771,0.3935824,0.00008501208,0.00001109995,0.00246549,0.0004044115],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5961522,0.00009865047,0.4021551,0.001027213,0.0001077915,0.000267121,0.00000532815,0.00008193258,0.0001046259],"genre_scores_gemma":[0.979414,0.000003054011,0.01705047,0.00004339979,0.002019943,0.000003786748,0.00008724066,0.00002033682,0.001357717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3851046,"threshold_uncertainty_score":0.2572218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01119414526533147,"score_gpt":0.2339974859515652,"score_spread":0.2228033406862338,"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."}}