{"id":"W2771573249","doi":"10.15353/vsnl.v3i1.182","title":"Automated Screening for Diabetic Retinopathy Using Compact Deep Networks","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Nvidia","keywords":"Diabetic retinopathy; Blindness; Retinopathy; Medicine; Fundus (uterus); Diabetes mellitus; Optometry; Retinal; Retina; Ophthalmology; Intensive care medicine; Computer science; Neuroscience; Psychology; Endocrinology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0008553136,0.0001305424,0.0004725092,0.0002053726,0.0004486183,0.0004420536,0.000106769,0.00002963193,0.000002509367],"category_scores_gemma":[0.0002179656,0.0000979994,0.0001777992,0.0000592952,0.00009386965,0.0002812097,0.00002248857,0.000158477,5.630978e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003845991,"about_ca_system_score_gemma":0.00005149205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002854877,"about_ca_topic_score_gemma":1.241846e-7,"domain_scores_codex":[0.998749,0.00006668912,0.0005560521,0.0001173244,0.0003426825,0.0001682308],"domain_scores_gemma":[0.9979328,0.0001982753,0.0009076881,0.0001323498,0.0006636492,0.0001652398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000358315,0.000120119,0.4387736,0.0003048959,0.0003659811,0.0001181241,0.0002007364,0.5344855,0.001969188,0.00007711175,0.002425245,0.02080118],"study_design_scores_gemma":[0.001248167,0.00009731705,0.1622361,0.001104808,0.0001862233,0.001180361,0.0001287753,0.833446,0.000005185452,0.00006008437,0.0002236978,0.00008325903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.476975,0.001792854,0.5193614,0.001168703,0.0004256543,0.0001494445,0.000002449256,0.00004258836,0.00008191726],"genre_scores_gemma":[0.9882476,0.0000136232,0.01116441,0.0001132161,0.0003932807,4.430247e-7,0.000007243866,0.00001802283,0.00004220723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5112725,"threshold_uncertainty_score":0.4262733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02637068858273546,"score_gpt":0.3566245915677359,"score_spread":0.3302539029850005,"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."}}