{"id":"W2946345509","doi":"10.1016/j.artmed.2019.05.002","title":"Combining clustering and classification ensembles: A novel pipeline to identify breast cancer profiles","year":2019,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Medical Research Council; University of Nottingham","keywords":"Cluster analysis; Computer science; Ensemble learning; Breast cancer; Artificial intelligence; Consensus clustering; Pipeline (software); Robustness (evolution); Statistical classification; Machine learning; Data mining; Pattern recognition (psychology); Cancer; Correlation clustering; CURE data clustering algorithm; Medicine; Biology","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":[0.0003372732,0.0001305011,0.0001621263,0.0001367726,0.00004374929,0.00002067546,0.0001492061,0.00009392598,0.0001048781],"category_scores_gemma":[0.00008638325,0.0001154449,0.00001918235,0.0002597941,0.00007271986,0.00000886426,0.0000760462,0.00009988805,0.00003215504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002766724,"about_ca_system_score_gemma":0.00004240615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001549626,"about_ca_topic_score_gemma":0.0002623199,"domain_scores_codex":[0.9988028,0.00003338508,0.0003763178,0.0004285951,0.0001639365,0.0001949192],"domain_scores_gemma":[0.9994227,0.00002011948,0.00009262231,0.0002632867,0.0001072454,0.00009401227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001215026,0.00003836207,0.004081565,0.00002459113,0.000004601678,3.872081e-7,0.0004743238,0.000416886,0.938384,0.0004784318,0.0005026977,0.05547264],"study_design_scores_gemma":[0.0007708085,0.0006759334,0.1448195,0.001343475,0.00004558393,0.00005770865,0.01561453,0.06996203,0.7468935,0.001199458,0.01765653,0.000960958],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9056767,0.0003369835,0.08619744,0.006141077,0.000568531,0.0004718569,0.000009942147,0.00001666929,0.0005808054],"genre_scores_gemma":[0.9977931,0.0002511496,0.0003882575,0.0008394719,0.0002811789,0.00008079368,0.00002986624,0.00001622096,0.0003199693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1914905,"threshold_uncertainty_score":0.4707704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06018250865939074,"score_gpt":0.3751015892239202,"score_spread":0.3149190805645294,"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."}}