{"id":"W3021150726","doi":"10.1186/s12874-020-00991-3","title":"Feasibility and evaluation of a large-scale external validation approach for patient-level prediction in an international data network: validation of models predicting stroke in female patients newly diagnosed with atrial fibrillation","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"U.S. National Library of Medicine; Innovative Medicines Initiative; Health Promotion Administration, Ministry of Health and Welfare; Korea Health Industry Development Institute; European Commission; European Federation of Pharmaceutical Industries and Associations","keywords":"Observational study; Standardization; Atrial fibrillation; Computer science; Predictive modelling; Scale (ratio); Cross-validation; Medicine; Data mining; Internal medicine; Artificial intelligence; Machine learning","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03711225,0.0001201073,0.0003713638,0.000284811,0.00007299471,0.0000330027,0.0007723467,0.0002708671,0.00001597259],"category_scores_gemma":[0.03656566,0.0001113373,0.00003613296,0.0005716947,0.0001144574,0.001008104,0.000632439,0.0005611142,1.341064e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001536635,"about_ca_system_score_gemma":0.0009001856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004485045,"about_ca_topic_score_gemma":0.000647499,"domain_scores_codex":[0.9812464,0.01368509,0.0009928038,0.0009010775,0.002766057,0.0004085895],"domain_scores_gemma":[0.9908752,0.006820493,0.0004073712,0.0005294867,0.001157708,0.0002096969],"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":[0.0007937796,0.00007754679,0.7161408,0.0001585742,0.000007718131,3.035064e-7,0.00274855,0.2351561,0.00002583169,0.0002392685,0.000003611183,0.04464791],"study_design_scores_gemma":[0.003369788,0.0006754387,0.2662031,0.00008536856,0.000008501925,9.55039e-7,0.000260677,0.728455,0.00005380398,0.0008335197,0.000001832274,0.00005200224],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.506096,0.00004089539,0.4925832,0.00008597719,0.00008272259,0.001009929,0.00008045475,0.00001060449,0.00001025797],"genre_scores_gemma":[0.6496955,0.00001771704,0.3495591,0.0000111508,0.000186912,0.00003802679,0.0004833888,0.000007716861,4.531088e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4932989,"threshold_uncertainty_score":0.9914955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6334701342418498,"score_gpt":0.5302730048634271,"score_spread":0.1031971293784227,"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."}}