{"id":"W4391947104","doi":"10.3233/shti231317","title":"AI Can Improve the Economics of Blindness Prevention in Canada","year":2024,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Blindness; Diabetic retinopathy; Medicine; Interoperability; Psychological intervention; Economic cost; Optometry; Gerontology; Diabetes mellitus; Business; Computer science; Economics; Nursing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003332145,0.00005423091,0.0002432471,0.0002713205,0.00003705374,0.000002744383,0.00004232931,0.00003532492,7.042703e-7],"category_scores_gemma":[0.00008441805,0.00003570851,0.0000137395,0.0003967534,0.0001573662,0.0000366603,0.00004633727,0.0002692102,2.043476e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002417148,"about_ca_system_score_gemma":0.0007200265,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06049433,"about_ca_topic_score_gemma":0.361547,"domain_scores_codex":[0.9992919,0.00001004929,0.000485891,0.00004752987,0.00003625386,0.0001283619],"domain_scores_gemma":[0.9997178,0.00005131216,0.00008280786,0.0001051481,0.00002916837,0.00001374289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00006199894,0.0000794396,0.2926674,0.0173877,0.0005204474,0.00002524857,0.02122701,0.000332442,0.000006427936,0.03002247,0.002782329,0.634887],"study_design_scores_gemma":[0.004063955,0.002428773,0.03318049,0.01172711,0.0003357198,0.0003413483,0.570811,0.2653093,0.001316467,0.06289679,0.0468962,0.0006928417],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9526358,0.007998624,0.00003265207,0.0387676,0.0001759354,0.0001887615,0.000005267293,0.00001455193,0.0001808155],"genre_scores_gemma":[0.9910181,0.007904545,0.0001850992,0.0008116002,0.000007532065,0.00001423615,0.000001883045,0.000002411994,0.00005458156],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6341942,"threshold_uncertainty_score":0.9457619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02381058820614297,"score_gpt":0.3554759534093043,"score_spread":0.3316653652031614,"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."}}