{"id":"W4413112717","doi":"10.1016/j.jcjo.2025.07.008","title":"Quantifying the repeatability and reproducibility of Dr. Noon CVD, AI software as medical device for cardiovascular risk assessment via retinal imaging","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Ophthalmology","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Repeatability; Reproducibility; Noon; Software; Retinal; Medicine; Optometry; Ophthalmology; Computer science; Artificial intelligence; Biomedical engineering; Medical physics; Statistics; Mathematics; Geology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009919646,0.0001555782,0.0007858667,0.0002559231,0.0002463198,0.00002772071,0.0002513351,0.00009896933,0.0001470884],"category_scores_gemma":[0.01429746,0.0001112016,0.0006387891,0.0003094171,0.0005466745,0.00007731351,0.00004180207,0.0006815065,5.377152e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001813444,"about_ca_system_score_gemma":0.002526336,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01544141,"about_ca_topic_score_gemma":0.0002561918,"domain_scores_codex":[0.9974456,0.0005345869,0.0007940597,0.0005663616,0.000339802,0.0003196057],"domain_scores_gemma":[0.9965135,0.0005523938,0.0003474753,0.001192088,0.000972004,0.0004224986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001305135,0.00003444968,0.9874424,0.0002880791,0.0008438699,0.00244553,0.0001030588,0.0000266043,0.00007344515,0.00004699084,0.0003700618,0.008194956],"study_design_scores_gemma":[0.002319324,0.0007427593,0.8512309,0.000986536,0.004744827,0.126131,0.001172523,0.002013237,0.001082661,0.004908304,0.00437459,0.0002932758],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9717815,0.007483121,0.005270998,0.0141994,0.0003953429,0.0002708841,0.00001737171,0.000004337171,0.0005770725],"genre_scores_gemma":[0.9968734,0.00003125224,0.002609496,0.000222832,0.0001245575,0.000005872689,0.000006821853,0.00001191631,0.0001138862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1362115,"threshold_uncertainty_score":0.9940055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03164429047296894,"score_gpt":0.3644132712547857,"score_spread":0.3327689807818167,"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."}}