{"id":"W4407239334","doi":"10.2460/ajvr.24.09.0282","title":"Machine learning predicts selected cat diseases using insurance data amid challenges in interpretability","year":2025,"lang":"en","type":"article","venue":"American Journal of Veterinary Research","topic":"Veterinary Oncology Research","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"CATS; Random forest; Medicine; Logistic regression; Predictive modelling; Breed; Interpretability; Machine learning; Statistics; Artificial intelligence; Computer science; Internal medicine; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004078686,0.0008150521,0.0005908115,0.001861838,0.0003159079,0.001251345,0.000632815,0.0005487014,0.0009808415],"category_scores_gemma":[0.01125597,0.0002012991,0.0008741932,0.0009874254,0.0003533945,0.0007649008,0.0007074549,0.0008683892,0.0002847098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007873009,"about_ca_system_score_gemma":0.0007592273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01177902,"about_ca_topic_score_gemma":0.01262474,"domain_scores_codex":[0.9990569,0.0004275808,0.00007957263,0.0002468462,0.0001231115,0.00006601019],"domain_scores_gemma":[0.9931695,0.005102447,0.0006180527,0.0004562677,0.0005426051,0.0001111378],"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":[0.0003414614,0.0003218087,0.7998582,0.0001062153,0.0004445523,0.00026075,0.0001782455,0.1292151,0.001556516,0.0005627825,0.001275339,0.06587905],"study_design_scores_gemma":[0.00002053118,0.0001817328,0.155188,0.00007570579,0.00009709179,0.0001788406,0.0001895939,0.8398574,0.001116405,0.002099921,0.0009747657,0.00002004606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9662378,0.0005015737,0.0290662,0.0005744388,0.00002797842,0.0000957893,0.002162388,0.0002089521,0.001124912],"genre_scores_gemma":[0.9884987,0.00009936743,0.008533515,0.00005054359,0.000019778,0.00003271285,0.002499167,0.00000921733,0.0002569076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01177902,"threshold_uncertainty_score":0.02342087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2707421072598328,"score_gpt":0.4933886929285375,"score_spread":0.2226465856687047,"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."}}