{"id":"W4224055339","doi":"10.3390/bioengineering9040175","title":"Comparison of Unsupervised Machine Learning Approaches for Cluster Analysis to Define Subgroups of Heart Failure with Preserved Ejection Fraction with Different Outcomes","year":2022,"lang":"en","type":"article","venue":"Bioengineering","topic":"Heart Failure Treatment and Management","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Medoid; Heart failure with preserved ejection fraction; Hierarchical clustering; Heart failure; Ejection fraction; Population; Cluster (spacecraft); Computer science; Artificial intelligence; Machine learning; Medicine; Internal 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":[0.0001325848,0.0001662522,0.0005831884,0.0003948888,0.0000692392,0.000007326723,0.00004438061,0.00002524284,0.00004464644],"category_scores_gemma":[0.00001506103,0.0001133505,0.000130407,0.0005154239,0.0000100085,0.00004525218,0.0000472256,0.0001207032,3.053456e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008761024,"about_ca_system_score_gemma":0.000009162189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001201466,"about_ca_topic_score_gemma":0.0001817399,"domain_scores_codex":[0.9990687,0.00003015645,0.000247238,0.0002090382,0.0002808038,0.0001640575],"domain_scores_gemma":[0.999562,0.00005972683,0.00007894651,0.0001911475,0.00004358183,0.00006462452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005657205,0.0002941605,0.7750732,0.0002187525,0.00130941,4.358114e-7,0.0001742433,0.2205774,0.001537181,0.00002122282,0.000112327,0.0001158485],"study_design_scores_gemma":[0.004322734,0.004241969,0.5349023,0.00006333464,0.003028626,0.000003440568,0.001771732,0.4356272,0.006626953,8.473251e-7,0.009136183,0.0002747001],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8855851,0.00005743384,0.1119786,0.001399857,0.00001983363,0.0008765004,0.000009655956,0.00005924279,0.00001381197],"genre_scores_gemma":[0.982777,0.000001104118,0.01660153,0.00001793206,0.00001425848,0.0002408604,0.0001870734,0.00002511869,0.0001351358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.240171,"threshold_uncertainty_score":0.4622301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03812222560005974,"score_gpt":0.2681501681866252,"score_spread":0.2300279425865655,"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."}}