{"id":"W1513225749","doi":"10.1155/2015/623619","title":"Combined Methods for Diabetic Retinopathy Screening, Using Retina Photographs and Tear Fluid Proteomics Biomarkers","year":2015,"lang":"en","type":"article","venue":"Journal of Diabetes Research","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital","funders":"European Social Fund; UCL Institute of Ophthalmology, University College London; Peterborough K. M. Hunter Charitable Foundation; Moorfields Eye Hospital NHS Foundation Trust; Hungarian Scientific Research Fund; Nemzeti Kutatási és Technológiai Hivatal; European Commission; Biomedical Research Council; Canadian Institutes of Health Research; National Institute for Health and Care Research; Ontario Ministry of Health and Long-Term Care","keywords":"Diabetic retinopathy; Medicine; Ophthalmology; Retina; Proteomics; Diabetes mellitus; Chemistry; Biology; Endocrinology; Neuroscience","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002454371,0.001185629,0.0009440554,0.002872024,0.0003531219,0.001109339,0.0007334218,0.0008360398,0.002286181],"category_scores_gemma":[0.003898976,0.0005189122,0.001112696,0.001147953,0.0002630808,0.000965951,0.001060706,0.0007187907,0.001534534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005656891,"about_ca_system_score_gemma":0.0005261166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00139937,"about_ca_topic_score_gemma":0.002348503,"domain_scores_codex":[0.997969,0.0006452437,0.0001192634,0.0004416158,0.0007591867,0.00006583489],"domain_scores_gemma":[0.9979849,0.0007008687,0.0002734871,0.0002514661,0.0007194994,0.00006973438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001185959,0.0009539304,0.09334166,0.0005968545,0.0009829071,0.0002696116,0.0001444488,0.025906,0.07722918,0.0009386585,0.003047127,0.7954037],"study_design_scores_gemma":[0.0001051544,0.001277674,0.07303335,0.0001058669,0.0006059725,0.001568276,0.0001175189,0.8575476,0.05758577,0.002901471,0.004997687,0.0001536353],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2043637,0.002392276,0.7845876,0.0004311862,0.0001981727,0.0006634907,0.0013635,0.002750393,0.003249761],"genre_scores_gemma":[0.5373967,0.0009160876,0.4562185,0.0002387635,0.0001266459,0.0006524118,0.001003039,0.0001113195,0.003336573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002872024,"threshold_uncertainty_score":0.0129801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1523129586203013,"score_gpt":0.4699793278367508,"score_spread":0.3176663692164496,"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."}}