{"id":"W236448318","doi":"10.1371/journal.pone.0127428","title":"Personalized Mortality Prediction Driven by Electronic Medical Data and a Patient Similarity Metric","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Metric (unit); Similarity (geometry); Personalized medicine; Computational biology; Computer science; Bioinformatics; Medicine; Biology; Artificial intelligence; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000875111,0.0001096605,0.0002062228,0.00007359155,0.00008644319,0.00006096929,0.000867701,0.000103179,0.000031109],"category_scores_gemma":[0.001625899,0.0001035194,0.00001478217,0.00039087,0.0000580068,0.0003239253,0.0007724983,0.0004879828,0.000009714701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001248582,"about_ca_system_score_gemma":0.0003515865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003716088,"about_ca_topic_score_gemma":0.00006325322,"domain_scores_codex":[0.9972364,0.0003271258,0.0002330709,0.0005361474,0.001349714,0.0003175476],"domain_scores_gemma":[0.9984256,0.0001192929,0.00009384106,0.000858365,0.0001229868,0.0003799284],"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":[0.0000465728,0.002704054,0.9497518,0.0003056913,0.0004830171,0.00003440449,0.003665699,0.0000207664,0.0001587218,0.004171765,0.01358797,0.02506955],"study_design_scores_gemma":[0.0006648614,0.0004718004,0.01572368,0.00005426856,0.00005033291,0.000009797494,0.00003154076,0.9794247,0.00007724731,0.0006935343,0.002640043,0.0001582614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.960874,0.002404833,0.02817407,0.007361969,0.00009328368,0.00040142,0.00009848684,0.0003224337,0.0002695163],"genre_scores_gemma":[0.9935293,0.0001324118,0.00551588,0.0005966709,0.00006028228,0.0000186821,0.0001093086,0.000008979428,0.00002853853],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9794039,"threshold_uncertainty_score":0.4221398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09542917862554046,"score_gpt":0.3121350375905038,"score_spread":0.2167058589649633,"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."}}