{"id":"W4411678460","doi":"10.1101/2025.06.25.25330260","title":"Causal machine learning for assessing the effectiveness of off-label use of amiodarone in new-onset atrial fibrillation","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Amiodarone; Atrial fibrillation; Medicine; Internal medicine; Cardiology; Computer science; Artificial intelligence; Machine learning; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.02632298,0.001156372,0.001681096,0.0027573,0.0004621749,0.001513925,0.001230568,0.001758985,0.003581209],"category_scores_gemma":[0.08261812,0.000474788,0.002539648,0.00123707,0.001226804,0.001182457,0.001087716,0.002763445,0.0002622871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001464367,"about_ca_system_score_gemma":0.001208056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006990652,"about_ca_topic_score_gemma":0.002860602,"domain_scores_codex":[0.9892699,0.008283176,0.0005016476,0.00107861,0.0004951032,0.0003716241],"domain_scores_gemma":[0.7992731,0.1892822,0.00702038,0.00180633,0.00150934,0.001108733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002039312,0.0007371661,0.2322652,0.0003657765,0.001987326,0.0003420951,0.0001207001,0.7132378,0.0003492995,0.005636146,0.001874316,0.04104492],"study_design_scores_gemma":[0.00009443817,0.0003177271,0.01354438,0.00005299209,0.0003035592,0.00007092363,0.00002958099,0.9767733,0.0002469962,0.008079779,0.0004604553,0.00002580393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7757846,0.005428171,0.2028927,0.00677273,0.0003617227,0.0005460263,0.004700012,0.0005935204,0.002920525],"genre_scores_gemma":[0.9916107,0.0002746306,0.006527149,0.0002774248,0.00009747875,0.0001014835,0.0007746522,0.00001355634,0.0003229942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02632298,"threshold_uncertainty_score":0.1392109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09609106033770369,"score_gpt":0.3852843285233419,"score_spread":0.2891932681856382,"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."}}