{"id":"W3002402144","doi":"10.1088/1361-6560/ab6e54","title":"Data clustering to select clinically-relevant test cases for algorithm benchmarking and characterization","year":2020,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medoid; Benchmarking; Cluster analysis; Algorithm; Computer science; Workflow; Data mining; Ground truth; Statistical hypothesis testing; Artificial intelligence; Statistics; Mathematics; Database","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":[0.06331763,0.001792655,0.0018325,0.006324275,0.001528659,0.004060332,0.002843979,0.001730139,0.00174386],"category_scores_gemma":[0.2154408,0.0005302062,0.001825602,0.00298919,0.00201243,0.002212025,0.00346543,0.00173304,0.0006363807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002130116,"about_ca_system_score_gemma":0.004475978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003549283,"about_ca_topic_score_gemma":0.002672351,"domain_scores_codex":[0.9502987,0.02722802,0.007154312,0.005867428,0.008198307,0.001253176],"domain_scores_gemma":[0.8336881,0.1101162,0.0105787,0.02136513,0.02320348,0.001048528],"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":[0.002557383,0.002273585,0.1389163,0.001478926,0.001028581,0.0006649092,0.003654188,0.2235597,0.02993011,0.01967932,0.007311958,0.5689449],"study_design_scores_gemma":[0.0005009197,0.002339509,0.04176928,0.0004354002,0.0003155049,0.0006802948,0.002018298,0.8357171,0.08061798,0.02574145,0.009618805,0.000245459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1550151,0.000292813,0.8359151,0.0004604922,0.00009251588,0.002399764,0.0007959089,0.002955973,0.002072251],"genre_scores_gemma":[0.5246673,0.00004845405,0.4699341,0.0001795179,0.00002413804,0.002103755,0.002279533,0.000485986,0.0002772291],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06331763,"threshold_uncertainty_score":0.3348596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2363964357711582,"score_gpt":0.4405806988614017,"score_spread":0.2041842630902435,"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."}}