{"id":"W2973454555","doi":"10.1038/s41467-019-12242-1","title":"Non-invasive in vivo hyperspectral imaging of the retina for potential biomarker use in Alzheimer’s disease","year":2019,"lang":"en","type":"article","venue":"Nature Communications","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":301,"is_retracted":false,"has_abstract":true,"ca_institutions":"Optina Diagnostics (Canada); Hôpital Maisonneuve-Rosemont; Polytechnique Montréal; Concordia University; Douglas Mental Health University Institute; McGill University; Montreal Heart Institute; Montreal Neurological Institute and Hospital","funders":"Australian Research Council; Fondation Brain Canada; State Government of Victoria; Québec Consortium for Drug Discovery; Pratt Foundation; Sylvia and Charles Viertel Charitable Foundation","keywords":"Hyperspectral imaging; Retina; Biomarker; Imaging biomarker; Disease; In vivo; Neuroscience; Medicine; Neuroimaging; Preclinical imaging; Alzheimer's disease; Biology; Computational biology; Pathology; Magnetic resonance imaging; Computer science; Artificial intelligence; Radiology; Genetics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001884988,0.00008619338,0.0001818685,0.0001644649,0.00005289847,0.00001473579,0.0004031104,0.00005908911,0.0000134208],"category_scores_gemma":[0.0002794216,0.00006391935,0.0001794676,0.0004443248,0.0001188906,0.00008400704,0.0001336759,0.0004461244,0.00000226818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004320146,"about_ca_system_score_gemma":0.0001141095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002047941,"about_ca_topic_score_gemma":0.0002144343,"domain_scores_codex":[0.9992962,0.00007170903,0.0002141557,0.0001505297,0.000128383,0.0001389574],"domain_scores_gemma":[0.9981955,0.0002185251,0.00009242717,0.00130717,0.0001404433,0.00004597815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000119299,0.0002171848,0.9691871,0.00002433527,0.00006067009,0.000003459874,0.0001803826,0.00002995304,0.02810082,0.0004617626,0.001454611,0.0001603538],"study_design_scores_gemma":[0.00120795,0.00001359038,0.9747537,0.0003931571,0.0003873067,0.000007332414,0.0004399839,0.01858433,0.002672548,0.0001534416,0.001271757,0.0001149223],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9638745,0.005987861,0.00001906614,0.02815971,0.00008820267,0.0006990767,0.00004302962,0.00001448622,0.001114031],"genre_scores_gemma":[0.9969304,0.0002478187,0.002154349,0.0004068049,0.00001374036,0.00002572832,0.00003401826,0.00001271571,0.0001744115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03305588,"threshold_uncertainty_score":0.2606556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02333970174386473,"score_gpt":0.318103451416579,"score_spread":0.2947637496727142,"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."}}