{"id":"W2793376278","doi":"10.1016/j.artmed.2018.02.003","title":"Inflection point analysis: A machine learning approach for extraction of IEGM active intervals during atrial fibrillation","year":2018,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Mitacs","keywords":"Inflection point; Computer science; Offset (computer science); Waveform; Maximization; Pattern recognition (psychology); Artificial intelligence; Algorithm; Cluster analysis; Logarithm; Mathematics; Mathematical optimization","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001804088,0.001040575,0.0008377678,0.005698784,0.0005111702,0.001736031,0.0009349804,0.0009637576,0.003483583],"category_scores_gemma":[0.00765085,0.0002254054,0.001168915,0.004446993,0.0003286854,0.00122008,0.00112952,0.001492935,0.002293885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003172192,"about_ca_system_score_gemma":0.0005751994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002234885,"about_ca_topic_score_gemma":0.002052402,"domain_scores_codex":[0.9992137,0.000150515,0.0001269973,0.0002539835,0.0001762616,0.00007850422],"domain_scores_gemma":[0.9962411,0.002132652,0.0005187231,0.000281169,0.0007006195,0.0001257708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001726604,0.0002535654,0.04350876,0.000541242,0.0003821089,0.0008735564,0.000683513,0.01649617,0.03020516,0.002898452,0.006334422,0.8960963],"study_design_scores_gemma":[0.0002030553,0.001066312,0.2201262,0.0004764418,0.000642076,0.004619027,0.001103535,0.6881853,0.03345351,0.02441533,0.02536836,0.000340917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1205408,0.002903329,0.8605925,0.000312307,0.0002163094,0.0002943839,0.005696678,0.005247563,0.004196067],"genre_scores_gemma":[0.5685788,0.001353997,0.4198318,0.0001358073,0.0003119995,0.0004663481,0.006270587,0.0006376478,0.002413056],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005698784,"threshold_uncertainty_score":0.01165378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1198912017350803,"score_gpt":0.4108085864424901,"score_spread":0.2909173847074098,"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."}}