{"id":"W4391474918","doi":"10.1016/j.jpedsurg.2024.01.033","title":"Using Artificial Intelligence to Label Free-Text Operative and Ultrasound Reports for Grading Pediatric Appendicitis","year":2024,"lang":"en","type":"article","venue":"Journal of Pediatric Surgery","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; Montreal Children's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Appendicitis; Data extraction; Chatbot; Artificial intelligence; Data collection; Medical record; Grading (engineering); Medical physics; Radiology; Natural language processing; MEDLINE; Computer science; Surgery; Statistics","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":[0.01768705,0.001291145,0.0006369863,0.00459059,0.0007632192,0.002485132,0.001652341,0.001533694,0.001784062],"category_scores_gemma":[0.09329592,0.0003596766,0.0008612227,0.002361627,0.001143418,0.003074581,0.002987072,0.001856378,0.001409605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001612619,"about_ca_system_score_gemma":0.002145869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003719015,"about_ca_topic_score_gemma":0.004396183,"domain_scores_codex":[0.9845269,0.008890403,0.001591018,0.002803673,0.001878698,0.0003094533],"domain_scores_gemma":[0.8659418,0.1020536,0.01099086,0.01071212,0.009041153,0.001260593],"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":[0.001738925,0.001018985,0.1607797,0.001760032,0.0004719488,0.0004634784,0.005085554,0.02844185,0.01635991,0.001675522,0.01518499,0.7670191],"study_design_scores_gemma":[0.0003186199,0.001798532,0.09375092,0.001013555,0.0004321407,0.0009841732,0.003328113,0.7973587,0.05832806,0.01616612,0.02618083,0.0003403045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.551559,0.00142166,0.411705,0.002663813,0.0005296286,0.002061007,0.003647781,0.02059789,0.005814256],"genre_scores_gemma":[0.661088,0.0003216621,0.3290052,0.0008273404,0.0001783603,0.0007912386,0.005450546,0.0002864834,0.002051205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01768705,"threshold_uncertainty_score":0.09353912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2439194085564576,"score_gpt":0.4461614091791493,"score_spread":0.2022420006226917,"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."}}