{"id":"W2951997750","doi":"10.1126/scirobotics.aav7725","title":"Intelligent magnetic manipulation for gastrointestinal ultrasound","year":2019,"lang":"en","type":"article","venue":"Science Robotics","topic":"Gastrointestinal Bleeding Diagnosis and Treatment","field":"Medicine","cited_by":128,"is_retracted":false,"has_abstract":true,"ca_institutions":"FujiFilm VisualSonics (Canada)","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Biomedical Imaging and Bioengineering; Engineering and Physical Sciences Research Council; Royal Society","keywords":"Clipping (morphology); Gastrointestinal tract; Medicine; Endoscopy; Radiology; Visualization; Ultrasound; Medical diagnosis; Computer science; Artificial intelligence; Internal medicine","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":[0.000275613,0.0001195726,0.000155921,0.0001199772,0.00009947312,0.00005996774,0.0001149302,0.00001446445,0.00009683624],"category_scores_gemma":[0.0003576262,0.00009722053,0.00006947423,0.0002893795,0.0001611736,0.0000931977,0.00002899571,0.00007303618,0.0001904273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001696256,"about_ca_system_score_gemma":0.0001502182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008045315,"about_ca_topic_score_gemma":0.000001679586,"domain_scores_codex":[0.9987766,0.000004496028,0.0001870653,0.0003188048,0.0003432992,0.0003697019],"domain_scores_gemma":[0.9991317,0.0001547706,0.00005870752,0.0002283083,0.0002546693,0.0001718196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005962942,0.0003293095,0.9407594,0.00006686931,0.000005517578,0.00001092534,0.00005007008,0.008315716,0.04013136,0.007604709,0.0002330673,0.002433468],"study_design_scores_gemma":[0.001916714,0.009469868,0.9252083,0.0008891777,0.0001913388,0.0026707,0.0003839507,0.04635361,0.01046799,0.001725735,0.0004044442,0.0003181217],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9581918,0.00007226111,0.03533505,0.001700948,0.0004710936,0.001410127,0.000004626817,0.00009057944,0.002723528],"genre_scores_gemma":[0.8540147,0.000004247258,0.1450867,0.000123062,0.00005101148,0.00001309701,0.000008979998,0.00001076665,0.0006874011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1097517,"threshold_uncertainty_score":0.3964538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03099252222833527,"score_gpt":0.2946574170796194,"score_spread":0.2636648948512841,"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."}}