{"id":"W4210727887","doi":"10.2196/preprints.11370","title":"Prediction of Postoperative Complication of Pediatric Cataracts Patients using Data Mining Methods (Preprint)","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Cataracts; Complication; Medicine; Cataract surgery; Naive Bayes classifier; Medical record; Random forest; Microphthalmia; Aniridia; Optometry; Surgery; Ophthalmology; Artificial intelligence; Computer science; Support vector machine","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":[0.0008729858,0.0001854592,0.000618594,0.000316967,0.00004016819,0.00001283301,0.0003113328,0.0001442156,0.00006498065],"category_scores_gemma":[0.0005603824,0.0001584421,0.0001152153,0.000264177,0.00009564585,0.0001049806,0.0009154003,0.0002426927,0.000003109164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006365727,"about_ca_system_score_gemma":0.0002066336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006301044,"about_ca_topic_score_gemma":0.000001734815,"domain_scores_codex":[0.9979916,0.0002040679,0.000757065,0.0005963885,0.0003268639,0.0001239989],"domain_scores_gemma":[0.9964416,0.0001140422,0.0008005087,0.001452612,0.001117083,0.00007414482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001311466,0.0006032041,0.970693,0.0009579262,0.0005459521,9.357234e-7,0.00112904,0.0003164215,0.011121,0.000009464895,0.001381031,0.0131109],"study_design_scores_gemma":[0.000990841,0.0003478598,0.6521991,0.0008414047,0.003940842,0.000009352911,0.0003864371,0.3188981,0.02185419,0.00008858828,0.0001471419,0.0002960493],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9142076,0.0001276542,0.08358336,0.0001053599,0.0001582012,0.0003956141,0.0002326522,0.00003064812,0.001158846],"genre_scores_gemma":[0.7251595,0.00008365305,0.2724565,0.00003563834,0.0001385482,0.000003781364,0.002049664,0.00001606399,0.00005671575],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3185817,"threshold_uncertainty_score":0.6461083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1814029690575794,"score_gpt":0.4281201462277054,"score_spread":0.246717177170126,"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."}}