{"id":"W2766656768","doi":"10.1109/access.2019.2893635","title":"Discovery Radiomics With CLEAR-DR: Interpretable Computer Aided Diagnosis of Diabetic Retinopathy","year":2019,"lang":"en","type":"preprint","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Vector Institute; University of Waterloo","funders":"Agence Nationale de la Recherche; Canada Foundation for Innovation; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Interpretability; Diabetic retinopathy; Radiomics; Grading (engineering); CAD; Computer science; Limiting; Artificial intelligence; Medicine; Medical physics; Machine learning; Diabetes mellitus; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001892076,0.0007080356,0.0004813494,0.001258011,0.000201256,0.001753995,0.0007460489,0.001140946,0.003237859],"category_scores_gemma":[0.007492092,0.0002742556,0.0005141238,0.0004465533,0.0006669241,0.0009320519,0.001219681,0.0009456199,0.0008471895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000380583,"about_ca_system_score_gemma":0.0005078892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008068913,"about_ca_topic_score_gemma":0.001153401,"domain_scores_codex":[0.9990337,0.0003876242,0.00008843698,0.0001866957,0.0002426306,0.00006089807],"domain_scores_gemma":[0.9976788,0.001115125,0.0003253807,0.0003924107,0.0003990113,0.0000892313],"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":[0.001779065,0.0002350334,0.007375919,0.0007138079,0.0001810978,0.001002783,0.0005087642,0.0611744,0.0766091,0.02133736,0.01511799,0.8139646],"study_design_scores_gemma":[0.0002015508,0.0006060196,0.00777186,0.0001388063,0.0001475759,0.00192702,0.0001478879,0.8445985,0.08739034,0.03458498,0.02233015,0.0001552536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04382443,0.001028855,0.9438181,0.0009730932,0.0001505697,0.0001792846,0.0006231807,0.005749129,0.003653348],"genre_scores_gemma":[0.3858952,0.000649732,0.6084735,0.0008589369,0.0001727117,0.0001396741,0.0008143963,0.000316028,0.002679853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003237859,"threshold_uncertainty_score":0.01083177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01621215197414486,"score_gpt":0.3013120529865724,"score_spread":0.2850999010124275,"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."}}