{"id":"W3180425562","doi":"","title":"Development and performance of a novel ‘offline’ deep learning (DL)-based glaucoma screening tool integrated on a portable smartphone-based fundus camera","year":2021,"lang":"en","type":"article","venue":"Investigative Ophthalmology & Visual Science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; University of Toronto","funders":"","keywords":"Fundus (uterus); Glaucoma; Computer science; Fundus camera; Optometry; Ophthalmology; Artificial intelligence; Computer vision; Medicine; Retinal; Ophthalmoscopy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002830097,0.0005098497,0.0004502149,0.0006495688,0.0001780388,0.0004455526,0.0009257993,0.0004872908,0.006495023],"category_scores_gemma":[0.0009079462,0.0002728714,0.000248188,0.0002851923,0.0001338136,0.0005201495,0.0006744524,0.0004036329,0.002252611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003815017,"about_ca_system_score_gemma":0.000893089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003588726,"about_ca_topic_score_gemma":0.006354992,"domain_scores_codex":[0.999703,0.00002107045,0.00001909907,0.0000771273,0.0001342904,0.00004542056],"domain_scores_gemma":[0.9995858,0.0001013901,0.00003864677,0.00004075206,0.00017447,0.00005896267],"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":[0.0008519382,0.0004583101,0.01480148,0.0005235975,0.0001470801,0.0008930722,0.0001478234,0.00438282,0.2897471,0.0009944667,0.01828528,0.6687671],"study_design_scores_gemma":[0.0003701721,0.002088301,0.04793032,0.0001583004,0.0002887149,0.005064447,0.0001784054,0.4350297,0.4532161,0.001105254,0.05435821,0.0002120534],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2652083,0.001522994,0.6915645,0.000730426,0.0005170386,0.001121312,0.002296489,0.02564577,0.01139321],"genre_scores_gemma":[0.6065884,0.0005777359,0.3752029,0.00113654,0.0001260064,0.0004740759,0.001834637,0.0004714031,0.01358829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006495023,"threshold_uncertainty_score":0.02172804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05050315673129887,"score_gpt":0.3251829760493522,"score_spread":0.2746798193180534,"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."}}