{"id":"W4408573322","doi":"10.3390/bioengineering12030308","title":"Benchmarking Interpretability in Healthcare Using Pattern Discovery and Disentanglement","year":2025,"lang":"en","type":"article","venue":"Bioengineering","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University; University of Toronto; University of Waterloo","funders":"","keywords":"Interpretability; Benchmarking; Computer science; Cluster analysis; Artificial intelligence; Machine learning; Benchmark (surveying); Feature (linguistics); Data mining; Knowledge extraction; Clinical decision support system; Decision support system","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":[0.000276637,0.0001276254,0.0001581145,0.0001970455,0.00005692892,0.0001224829,0.0002625583,0.00004236998,0.000001364205],"category_scores_gemma":[0.00004005383,0.0001324085,0.00002765412,0.0003390992,0.00001510745,0.0003030739,0.0004125935,0.0002151747,3.212246e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002313673,"about_ca_system_score_gemma":0.00004741436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001355669,"about_ca_topic_score_gemma":0.0001917014,"domain_scores_codex":[0.9989113,0.00006307055,0.0002639877,0.0003669371,0.0001125803,0.0002821077],"domain_scores_gemma":[0.9994779,0.0000769049,0.00003556275,0.0003365191,0.00001697606,0.00005616125],"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":[0.00000215135,0.00001474043,0.9086948,0.0004938924,0.000006646097,0.00001117797,0.0004520906,0.004173514,0.0002238624,0.004610729,0.000003375105,0.08131304],"study_design_scores_gemma":[0.0001179515,0.00001918554,0.2236896,0.0003449438,0.000001627965,0.000003561345,0.00002535947,0.775315,0.00008224015,0.0001892764,0.00009322025,0.0001180098],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4419925,0.0006724954,0.5547456,0.001852396,0.0004855155,0.0001486891,0.000001979743,0.00007706203,0.00002376192],"genre_scores_gemma":[0.9903786,0.00001676698,0.009320883,0.0002270315,0.00003198001,0.00001075694,0.00000158706,0.000006395795,0.000005958069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7711415,"threshold_uncertainty_score":0.5399463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01115500667874182,"score_gpt":0.2869032106957597,"score_spread":0.2757482040170179,"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."}}