{"id":"W4294975594","doi":"10.1109/iri54793.2022.00046","title":"Using SHAP Analysis to Detect Areas Contributing to Diabetic Retinopathy Detection","year":2022,"lang":"en","type":"article","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Context (archaeology); Reliability (semiconductor); Transfer of learning; Diabetic retinopathy; Population; Software deployment; Binary classification; Predictive modelling; Field (mathematics); Blindness; Deep learning; Support vector machine; Optometry; Diabetes mellitus; Medicine; Environmental health; Mathematics; Geography","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":[0.0009981751,0.0004986421,0.000411645,0.002643629,0.0002898354,0.0007521986,0.0006038533,0.0007477932,0.001372552],"category_scores_gemma":[0.004639723,0.0001321181,0.0005545233,0.0005791672,0.0003969073,0.0009135072,0.0009485697,0.0005928359,0.0002665101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004683855,"about_ca_system_score_gemma":0.0004474024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0022792,"about_ca_topic_score_gemma":0.002416654,"domain_scores_codex":[0.9996077,0.00009471733,0.00002198889,0.00009239041,0.0001252186,0.00005785654],"domain_scores_gemma":[0.9980301,0.0007843768,0.0002666031,0.0001722605,0.0006166127,0.0001300044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00142881,0.0003852597,0.2178422,0.000207242,0.0003815062,0.001694046,0.0004571369,0.1449793,0.03024759,0.01218582,0.008565279,0.5816258],"study_design_scores_gemma":[0.00001603321,0.000122249,0.02753055,0.00002094825,0.00008922841,0.0004452397,0.0001696241,0.9546484,0.007391189,0.008613407,0.0009276406,0.00002550806],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7078638,0.0008936931,0.2819645,0.0009339689,0.0001200049,0.00009835196,0.0005637404,0.001593708,0.005968139],"genre_scores_gemma":[0.9819868,0.0001053421,0.0169047,0.00008623411,0.0000405548,0.000009350627,0.0002657566,0.00001719083,0.0005843058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002643629,"threshold_uncertainty_score":0.005278885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02269491636037438,"score_gpt":0.304924706484282,"score_spread":0.2822297901239077,"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."}}