{"id":"W2528467911","doi":"10.1371/journal.pone.0164095","title":"Optical Coherence Tomography in the UK Biobank Study – Rapid Automated Analysis of Retinal Thickness for Large Population-Based Studies","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Medical Research Council; Moorfields Eye Hospital NHS Foundation Trust; Northwest Regional Development Agency; Queen's University; Queen's University Belfast; University of Southampton; Fight for Sight UK; King's College London; Diabetes UK; University of Leeds; National Institute for Health and Care Research; British Heart Foundation; Wellcome Trust; University of Bristol; Kingston University","keywords":"Optical coherence tomography; Computer science; Segmentation; Artificial intelligence; Population; Biobank; Software; Image segmentation; Computer vision; Medicine; Ophthalmology; Bioinformatics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005819476,0.0001590126,0.0004409533,0.0004712688,0.00006872661,0.00001821017,0.0003025264,0.00006706701,0.00004984734],"category_scores_gemma":[0.000224921,0.0001017758,0.0001443127,0.002572821,0.00007516699,0.00005701839,0.00002033373,0.00009585267,0.000003387828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003031176,"about_ca_system_score_gemma":0.00001155928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001742618,"about_ca_topic_score_gemma":0.0003061748,"domain_scores_codex":[0.9986128,0.00007858031,0.0004299657,0.0002384951,0.0003670774,0.0002730914],"domain_scores_gemma":[0.9981148,0.00110319,0.00006429814,0.0004629566,0.0002123276,0.00004247668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005289972,0.002864433,0.9822233,0.0001687614,0.003785184,0.00000142387,0.0005930095,0.0005563239,0.006505676,0.002852145,0.00004669685,0.0003501567],"study_design_scores_gemma":[0.0009263216,0.0002688763,0.9522457,0.0001446947,0.002385361,8.25093e-8,0.0006261253,0.04080776,0.001951276,0.0004106626,0.000002264384,0.0002308399],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944779,0.0001731758,0.003405234,0.0002146143,0.00001434006,0.001182295,0.0001376781,0.0002993732,0.00009536669],"genre_scores_gemma":[0.9944705,0.00001251728,0.004540114,0.00002005433,0.00001381839,0.0009004402,0.00002583771,0.000014842,0.000001927762],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04025143,"threshold_uncertainty_score":0.4150297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04783807735211091,"score_gpt":0.2878219458844443,"score_spread":0.2399838685323334,"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."}}