{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000241218,0.0001471904,0.0002697616,0.0001113251,0.0001324116,0.0001697171,0.00007461958,0.00006072424,0.00002009264],"category_scores_gemma":[0.00005797482,0.00008772537,0.0001167848,0.000172459,0.0001029448,0.00009203038,0.00006316531,0.0001833412,0.00003303281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002182247,"about_ca_system_score_gemma":0.00003331285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003643697,"about_ca_topic_score_gemma":0.000001038167,"domain_scores_codex":[0.9990109,0.00006649853,0.0001856972,0.0003745196,0.0001731851,0.000189256],"domain_scores_gemma":[0.9990792,0.0003605903,0.00003983672,0.0002283457,0.000202781,0.00008924049],"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":[0.0003459786,0.0003645512,0.001772774,0.0003747643,0.0008534556,0.0002344966,0.001453545,0.000003095732,0.08207881,0.001507338,0.07102837,0.8399828],"study_design_scores_gemma":[0.001219357,0.001071698,0.04307228,0.0006090899,0.001130791,0.0003190595,0.0006434192,0.8998131,0.001254745,0.001929859,0.04855002,0.0003866278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9092236,0.006724657,0.01652406,0.06601506,0.0004859554,0.0004081857,0.00001910966,0.0002133925,0.0003859662],"genre_scores_gemma":[0.9948578,0.0003460475,0.002041143,0.001318689,0.0009771177,0.00002092037,0.0001004803,0.00002561789,0.0003122013],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.89981,"threshold_uncertainty_score":0.3577337,"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."}}