{"id":"W4409331731","doi":"10.1080/00140139.2025.2487558","title":"Examining the development, effectiveness, and limitations of computer-aided diagnosis systems for retained surgical items detection: a systematic review","year":2025,"lang":"en","type":"review","venue":"Ergonomics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Surgical procedures; Medical physics; Computer-aided; Computer science; Surgery","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":[0.001807659,0.0002408672,0.002144928,0.0001430103,0.0001752296,0.00003220015,0.0001199573,0.0001890673,8.134224e-7],"category_scores_gemma":[0.002179848,0.0001620616,0.0002173702,0.0003147062,0.00005070347,0.00003735451,0.00003903481,0.0001857411,0.000004222587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002611354,"about_ca_system_score_gemma":0.0008346847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000283446,"about_ca_topic_score_gemma":0.00001978518,"domain_scores_codex":[0.9974372,0.0004849562,0.001522109,0.0003012326,0.00009175694,0.0001627342],"domain_scores_gemma":[0.98302,0.01560938,0.0006939212,0.0003512746,0.0002585322,0.00006685673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000009986386,0.00002020021,0.000008925836,0.6792256,0.000162255,4.884391e-7,0.0001125077,0.000001870495,1.47083e-8,0.00007673561,0.00004258455,0.3203388],"study_design_scores_gemma":[0.00004939178,0.0001458955,0.00001583889,0.8563932,0.002878639,0.00006293746,0.0002042213,0.0002225753,0.000005674692,0.000008311839,0.1398547,0.0001586181],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001696832,0.9883346,0.002403829,0.00003677365,0.0008134245,0.008175967,0.00001036013,0.00002443302,0.0000309302],"genre_scores_gemma":[0.0007182647,0.9933697,0.0002890921,0.00003000763,0.0002382423,0.005187267,0.00007890275,0.00002363887,0.0000648568],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3201802,"threshold_uncertainty_score":0.6608678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3098257493300611,"score_gpt":0.4193937345305216,"score_spread":0.1095679852004606,"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."}}