{"id":"W2805655769","doi":"10.1007/978-3-319-93000-8_78","title":"Hybrid Statistical Framework for Diabetic Retinopathy Detection","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Discriminative model; Artificial intelligence; Pattern recognition (psychology); Kernel (algebra); Support vector machine; Statistical model; Dirichlet distribution; Diabetic retinopathy; Probabilistic logic; Flexibility (engineering); Latent Dirichlet allocation; Machine learning; Topic model; Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0005041106,0.0002799043,0.0004891059,0.0003963177,0.0001498863,0.0001123249,0.000279513,0.0001681164,0.0001007199],"category_scores_gemma":[0.0007285943,0.0002333381,0.0001343466,0.0001661638,0.0008287909,0.00005063201,0.000106459,0.0005955576,0.00004542806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001578347,"about_ca_system_score_gemma":0.0001642107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006210021,"about_ca_topic_score_gemma":0.000003723093,"domain_scores_codex":[0.997942,0.0000151669,0.0003190634,0.0008227832,0.0005067974,0.0003941309],"domain_scores_gemma":[0.9982411,0.0006621458,0.0001397542,0.0005232655,0.0002784465,0.0001552701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000919079,0.00003917347,0.0002394253,0.00022446,0.00004011588,0.0001199403,0.0002196855,0.0002731244,0.0005573144,0.001340642,0.00007952528,0.9967747],"study_design_scores_gemma":[0.0004284028,0.00125457,0.0003662084,0.001783715,0.0002724268,0.0002142004,3.10915e-7,0.3224794,0.0134669,0.6569489,0.002190134,0.0005949189],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001331642,0.0001462422,0.9964179,0.0005277594,0.000778298,0.0002959572,0.00001506475,0.00006121217,0.0004259192],"genre_scores_gemma":[0.4405796,0.00001927133,0.5560284,0.00126016,0.00156286,0.00001131143,0.00002076303,0.00004386689,0.0004737065],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9961798,"threshold_uncertainty_score":0.9515251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01446686448776969,"score_gpt":0.2837135439417796,"score_spread":0.2692466794540099,"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."}}