{"id":"W4403683094","doi":"10.1093/pch/pxae067.078","title":"79 Using artificial intelligence and machine learning to automate injury prevention surveillance data","year":2024,"lang":"en","type":"article","venue":"Paediatrics & Child Health","topic":"Healthcare Systems and Public Health","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Injury surveillance; Artificial intelligence; Machine learning; Medical emergency; Medicine; Injury prevention; Poison control","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003106227,0.001354309,0.0006301359,0.003923278,0.0006111102,0.001459252,0.001190737,0.0007468904,0.001815146],"category_scores_gemma":[0.01059986,0.0003709501,0.001436206,0.001903373,0.0003495734,0.0010779,0.0009576766,0.0009261241,0.001952925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001799122,"about_ca_system_score_gemma":0.002148259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04228467,"about_ca_topic_score_gemma":0.03629721,"domain_scores_codex":[0.9975401,0.0007539764,0.0003309909,0.0008164041,0.0003992198,0.000159367],"domain_scores_gemma":[0.9952133,0.002237529,0.0003698946,0.0007299089,0.001307187,0.0001422561],"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":[0.0003645399,0.0006224792,0.06094369,0.000428767,0.0002799369,0.000535713,0.000379449,0.1058417,0.009056752,0.001043065,0.02255513,0.7979487],"study_design_scores_gemma":[0.00002610647,0.0001533053,0.015316,0.00006583238,0.0000703996,0.0001023519,0.0001186644,0.965324,0.00761326,0.002042052,0.009128545,0.00003941046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4010939,0.003249083,0.5060876,0.002591148,0.0006362775,0.001459925,0.02022088,0.05321651,0.01144484],"genre_scores_gemma":[0.6631618,0.000399401,0.3004006,0.0003703937,0.0001379374,0.0003867408,0.03191126,0.0002969481,0.00293487],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04228467,"threshold_uncertainty_score":0.08407706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09900278927358723,"score_gpt":0.4013943602288637,"score_spread":0.3023915709552765,"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."}}