{"id":"W4406052391","doi":"10.1007/s41666-024-00182-5","title":"A Low Complexity Efficient Deep Learning Model for Automated Retinal Disease Diagnosis","year":2025,"lang":"en","type":"article","venue":"Journal of Healthcare Informatics Research","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Charles Darwin University","keywords":"Computer science; Optical coherence tomography; Artificial intelligence; Deep learning; Preprocessor; Transformer; Pattern recognition (psychology); Machine learning; Computer vision; Ophthalmology; Medicine; Engineering","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":[0.003871591,0.0001355107,0.0005001611,0.001093674,0.0004649751,0.0001101589,0.000240465,0.00007467836,0.00001070518],"category_scores_gemma":[0.003253674,0.0001049956,0.0003032328,0.000866689,0.0001931008,0.0001194617,0.00009506379,0.001223301,0.000007980845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004576904,"about_ca_system_score_gemma":0.001374953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003885226,"about_ca_topic_score_gemma":0.000007107744,"domain_scores_codex":[0.9966928,0.0002159521,0.001213508,0.0000999624,0.001219982,0.000557809],"domain_scores_gemma":[0.9947188,0.0006118151,0.0003820439,0.0002453461,0.003485671,0.0005562931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0121605,0.003444961,0.1505303,0.05487296,0.001179175,0.0004555431,0.02074879,0.5058465,0.0002515263,0.006805746,0.04228252,0.2014215],"study_design_scores_gemma":[0.001112771,0.0004102596,0.003845979,0.001847,0.0001017045,0.00003384563,0.00212886,0.9890003,0.00006574456,0.0005387242,0.0008371295,0.00007764313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8436313,0.001802754,0.100069,0.052298,0.0001620676,0.001108666,0.00002870512,0.0001361364,0.0007633026],"genre_scores_gemma":[0.983193,0.0004570376,0.0153517,0.0005081199,0.00007686045,0.00003258946,0.00002003018,0.00001376812,0.0003468757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4831538,"threshold_uncertainty_score":0.5314703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1162504458299991,"score_gpt":0.4786765947048147,"score_spread":0.3624261488748155,"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."}}