{"id":"W2625882437","doi":"10.4236/jbise.2017.105b010","title":"Automated Diabetic Retinopathy Detection Using Bag of Words Approach","year":2017,"lang":"en","type":"article","venue":"Journal of Biomedical Science and Engineering","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Diabetic retinopathy; Computer science; Fundus (uterus); Artificial intelligence; Pattern recognition (psychology); Retinopathy; Computer vision; Image processing; Medicine; Ophthalmology; Image (mathematics); Diabetes mellitus","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":[0.0005023619,0.001102539,0.001262991,0.005816302,0.0005148339,0.001315358,0.0008946599,0.001467853,0.001501853],"category_scores_gemma":[0.001478616,0.0002955353,0.001286999,0.001761616,0.0002982461,0.001260448,0.0008026547,0.0006882183,0.001681548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000523334,"about_ca_system_score_gemma":0.0008895264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0040227,"about_ca_topic_score_gemma":0.002845494,"domain_scores_codex":[0.9989783,0.0001582544,0.0001180567,0.0002808428,0.0003173135,0.0001473458],"domain_scores_gemma":[0.9993106,0.0001778723,0.0001253085,0.00006836681,0.00027631,0.00004151896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008701363,0.0004881008,0.01018582,0.0003138145,0.0002056884,0.0006404551,0.0001477719,0.01631454,0.06813879,0.001677858,0.008057003,0.8929601],"study_design_scores_gemma":[0.00009793459,0.0006917597,0.01855066,0.00009656516,0.0002852663,0.001772416,0.0004084063,0.8845732,0.07492354,0.009083326,0.009384776,0.0001321549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2718282,0.005532555,0.7059208,0.0006950741,0.0003820832,0.0004537999,0.002427236,0.008546831,0.004213452],"genre_scores_gemma":[0.6855801,0.001217435,0.3029044,0.0003581096,0.0002653353,0.0001992452,0.005007007,0.0001363354,0.00433209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005816302,"threshold_uncertainty_score":0.007998526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01401384436168861,"score_gpt":0.279734134852705,"score_spread":0.2657202904910164,"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."}}