{"id":"W4391481307","doi":"10.1016/j.isci.2024.109081","title":"A machine learning algorithm for peripheral artery disease prognosis using biomarker data","year":2024,"lang":"en","type":"article","venue":"iScience","topic":"Peripheral Artery Disease Management","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Biomarker; Prospective cohort study; Medicine; Cohort; Machine learning; Internal medicine; Algorithm; Peripheral; Computer science; 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":[0.000333093,0.000153858,0.0001493467,0.0001121736,0.0001879431,0.0002323052,0.0002933765,0.00001982823,0.0001755929],"category_scores_gemma":[0.00007565999,0.0001228341,0.00008175117,0.0003958107,0.0001397728,0.0005100068,0.000293076,0.00009370365,0.00002403261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009671836,"about_ca_system_score_gemma":0.0001724846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002082542,"about_ca_topic_score_gemma":0.000002627191,"domain_scores_codex":[0.9984106,0.00002842235,0.0001817201,0.0006797112,0.0003446225,0.0003548717],"domain_scores_gemma":[0.9991761,0.00003127076,0.00002669056,0.0004475387,0.00003732718,0.0002810935],"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":[0.00009165001,0.0002459672,0.01169676,0.0004861514,0.0001098994,0.0005219418,0.0002207447,0.0001007471,0.005430879,0.00006720354,0.003683175,0.9773449],"study_design_scores_gemma":[0.0002779761,0.00006789474,0.009482805,0.0002074897,0.0001617055,0.00002645642,0.00004238532,0.9058147,0.00001826745,0.00005584778,0.0837,0.0001444623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2678805,0.01948092,0.6922367,0.01062168,0.001997944,0.003765519,0.001266382,0.00125585,0.001494564],"genre_scores_gemma":[0.9621164,0.00004490648,0.03379919,0.0008405546,0.0002814084,0.0001074293,0.0003142469,0.00004033398,0.0024556],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9772004,"threshold_uncertainty_score":0.5009028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06997897492459619,"score_gpt":0.3392090563132563,"score_spread":0.2692300813886601,"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."}}