{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008681499,0.001323851,0.0009853748,0.003760137,0.0004546467,0.002938941,0.001296525,0.001482914,0.0008713026],"category_scores_gemma":[0.03864729,0.0002632328,0.001114677,0.002285141,0.001126841,0.001966592,0.002347863,0.001755395,0.0004009433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001519526,"about_ca_system_score_gemma":0.001734366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006207922,"about_ca_topic_score_gemma":0.005528387,"domain_scores_codex":[0.9920812,0.004103367,0.0008390165,0.0014478,0.001295133,0.0002335776],"domain_scores_gemma":[0.9746479,0.01912555,0.00151191,0.00288419,0.001435812,0.0003946693],"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":[0.001907168,0.0009205687,0.1150431,0.001167628,0.0008128117,0.0006675167,0.0009648332,0.3656172,0.006487782,0.008143301,0.007565083,0.490703],"study_design_scores_gemma":[0.0001173295,0.0005899503,0.01638895,0.0001094321,0.0000953149,0.000394189,0.0003296243,0.9470558,0.009838794,0.02080344,0.004215339,0.00006187436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6401749,0.003788576,0.3351821,0.004329578,0.0002083369,0.000572386,0.005568229,0.004642723,0.005533276],"genre_scores_gemma":[0.8734682,0.0005453041,0.1179191,0.0003650457,0.00005887049,0.0001654777,0.006636255,0.0001208502,0.0007209548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008681499,"threshold_uncertainty_score":0.04591274,"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."}}