{"id":"W4412564373","doi":"10.1016/j.knosys.2025.114165","title":"Detecting cognitive impairment in diabetics based on retinal photos by a deep learning method","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Zhejiang Province; Wenzhou Institute of Biomaterials and Engineering","keywords":"Cognitive impairment; Retinal; Artificial intelligence; Computer science; Deep learning; Optometry; Cognition; Computer vision; Pattern recognition (psychology); Ophthalmology; Psychology; Medicine; Neuroscience","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002026784,0.0003177153,0.000732407,0.0007260626,0.0001728769,0.00007774455,0.0001121054,0.0001431925,0.00003515264],"category_scores_gemma":[0.001104367,0.0002850725,0.0002463185,0.001177848,0.00006335426,0.00002773629,0.00002581961,0.0007123291,0.00005803547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004341007,"about_ca_system_score_gemma":0.0002398126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002240924,"about_ca_topic_score_gemma":0.0000345751,"domain_scores_codex":[0.9969394,0.001044858,0.0006148548,0.0005772918,0.0003379438,0.0004856411],"domain_scores_gemma":[0.9975759,0.001463456,0.0001944465,0.0002834646,0.0003203912,0.0001622733],"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":[0.002561097,0.003213178,0.8424423,0.005835685,0.0006106274,0.0003209495,0.00198493,0.01308702,0.05762755,0.00002928934,0.001373686,0.07091371],"study_design_scores_gemma":[0.005196737,0.0007980531,0.004308969,0.007761861,0.0004921788,0.000007894228,0.002304662,0.948587,0.02795152,0.000004046014,0.002245868,0.0003411932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7465528,0.003875315,0.212515,0.0006117748,0.0006020557,0.001943478,0.00001860381,0.0004728809,0.03340814],"genre_scores_gemma":[0.9961816,0.000004923339,0.0007861468,0.00023533,0.00009296729,0.0002017959,0.00005713359,0.00003955049,0.002400519],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9355,"threshold_uncertainty_score":0.9999601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01042772719523531,"score_gpt":0.3162369546372231,"score_spread":0.3058092274419877,"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."}}