{"id":"W2054335978","doi":"10.1186/1471-2415-13-40","title":"Tear fluid proteomics multimarkers for diabetic retinopathy screening","year":2013,"lang":"en","type":"article","venue":"BMC Ophthalmology","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital","funders":"European Social Fund; Peterborough K. M. Hunter Charitable Foundation; Moorfields Eye Hospital NHS Foundation Trust; Hungarian Scientific Research Fund; Nemzeti Kutatási és Technológiai Hivatal; European Commission; Canadian Institutes of Health Research; National Institute for Health and Care Research; Ontario Ministry of Health and Long-Term Care","keywords":"Medicine; Diabetic retinopathy; Machine learning; Random forest; Artificial intelligence; Naive Bayes classifier; Support vector machine; Logistic regression; Biomarker; Parameterized complexity; Algorithm; Computer science; Diabetes mellitus","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":[0.0003184458,0.0001754408,0.0004156548,0.0001436043,0.00009729133,0.00002634803,0.0001207649,0.0001215845,0.0004715618],"category_scores_gemma":[0.0006864854,0.0001494333,0.0002223207,0.0001543542,0.0001356805,0.00006551277,0.00004624034,0.000164184,0.0001580688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003029299,"about_ca_system_score_gemma":0.00005432694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001624046,"about_ca_topic_score_gemma":2.910876e-7,"domain_scores_codex":[0.9986824,0.00008541128,0.0003034211,0.0003738971,0.0001286294,0.0004261797],"domain_scores_gemma":[0.9989981,0.0002093827,0.00009988375,0.0003456453,0.0001851684,0.0001618067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003217511,0.0001541154,0.9265857,0.0002786484,0.0001346269,0.00004986538,0.00009334562,0.00004942132,0.06816359,0.00003034283,0.002357172,0.001781455],"study_design_scores_gemma":[0.005119205,0.001718966,0.8485999,0.0002954962,0.0006747267,0.003298939,0.0006646753,0.1262687,0.01051047,0.0007441243,0.001387718,0.0007171538],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9891038,0.0001292239,0.007197092,0.0009800389,0.00010935,0.0009920961,0.000005606006,0.00005949342,0.001423317],"genre_scores_gemma":[0.8288218,0.000002871278,0.1662988,0.0001573831,0.0001800171,0.0003057572,0.00004505376,0.00003633785,0.004151952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.160282,"threshold_uncertainty_score":0.6093714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03568209746015855,"score_gpt":0.30753568194896,"score_spread":0.2718535844888015,"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."}}