{"id":"W4223493204","doi":"10.1038/s41598-022-09719-3","title":"Assessment of the predictive potential of cognitive scores from retinal images and retinal fundus metadata via deep learning using the CLSA database","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Heart Institute; Polytechnique Montréal","funders":"Canadian Institutes of Health Research; Government of Canada","keywords":"Metadata; Fundus (uterus); Cognition; RGB color model; Computer science; Artificial intelligence; Deep learning; Variance (accounting); Retinal; Convolutional neural network; Pattern recognition (psychology); Ophthalmology; Psychology; Medicine; Neuroscience; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.001165254,0.0009484799,0.0005173832,0.00230744,0.0002111867,0.0007450482,0.0005465739,0.0005734854,0.0008227489],"category_scores_gemma":[0.004414397,0.0001482925,0.0007156255,0.0009357152,0.0001862906,0.0004475681,0.0006066897,0.0005989239,0.0004483066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007343755,"about_ca_system_score_gemma":0.0007811174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03544065,"about_ca_topic_score_gemma":0.03282126,"domain_scores_codex":[0.9995709,0.00008786471,0.00003889388,0.0001318763,0.0001058593,0.00006464345],"domain_scores_gemma":[0.9986179,0.0005489564,0.000123573,0.0002020976,0.0004128659,0.00009462606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003187489,0.001734971,0.5287275,0.0004482313,0.001222626,0.000943299,0.0002038442,0.0909809,0.01277625,0.0007011842,0.01969668,0.339377],"study_design_scores_gemma":[0.00008545988,0.0004674697,0.23512,0.00009205007,0.000286959,0.0004744103,0.0002483246,0.7501432,0.009020163,0.0008695569,0.003118028,0.000074344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845586,0.0007694079,0.005117301,0.0002297885,0.00005471741,0.00005688012,0.007431625,0.000663595,0.001118031],"genre_scores_gemma":[0.9768909,0.0002710179,0.006809281,0.00005538013,0.00002970936,0.00004426871,0.01521457,0.00001943323,0.0006653682],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03544065,"threshold_uncertainty_score":0.07046872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0198833818300836,"score_gpt":0.3057426421537036,"score_spread":0.28585926032362,"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."}}