{"id":"W4399465217","doi":"10.1007/s00371-024-03384-5","title":"HRDC challenge: a public benchmark for hypertension and hypertensive retinopathy classification from fundus images","year":2024,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"DiagnoCure (Canada); École de Technologie Supérieure","funders":"","keywords":"Fundus (uterus); Hypertensive retinopathy; Benchmark (surveying); Ophthalmology; Medicine; Diabetic retinopathy; Computer science; Artificial intelligence; Optometry; Cartography; Endocrinology; Diabetes mellitus; Geography","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":[0.004074429,0.00358,0.002084842,0.004222638,0.001612283,0.002952508,0.003571457,0.004748637,0.005814081],"category_scores_gemma":[0.01058832,0.0005419641,0.002266699,0.002478255,0.0007957272,0.001840935,0.00367746,0.002292094,0.008169448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0020534,"about_ca_system_score_gemma":0.002931249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03859501,"about_ca_topic_score_gemma":0.04239252,"domain_scores_codex":[0.9958579,0.0008138444,0.0003635148,0.001044208,0.001411777,0.0005087369],"domain_scores_gemma":[0.9947382,0.001340324,0.0003034018,0.001220503,0.001631582,0.0007659448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002527266,0.002396044,0.0184774,0.00257865,0.0009090879,0.001409523,0.0002232981,0.01699539,0.009036463,0.001447267,0.6497694,0.2942303],"study_design_scores_gemma":[0.002573144,0.00263335,0.1449592,0.001726232,0.001231656,0.008133762,0.002749967,0.4531133,0.04364922,0.01347255,0.3252784,0.0004792578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.4135622,0.01984951,0.04281058,0.009955642,0.004852635,0.003352345,0.4227037,0.05123321,0.03168021],"genre_scores_gemma":[0.2245943,0.002526814,0.05644091,0.001582613,0.0007926393,0.000607289,0.6993738,0.001408184,0.01267338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03859501,"threshold_uncertainty_score":0.07674074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0584703625238991,"score_gpt":0.317125072834909,"score_spread":0.2586547103110099,"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."}}