{"id":"W4294025369","doi":"10.2196/37374","title":"Developing Clinical Artificial Intelligence for Obstetric Ultrasound to Improve Access in Underserved Regions: Protocol for a Computer-Assisted Low-Cost Point-of-Care UltraSound (CALOPUS) Study","year":2022,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Ultrasound in Clinical Applications","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; National Institute for Health and Care Research","keywords":"Protocol (science); Medicine; Point of care; Medical physics; Ultrasound; Point of care ultrasound; Computer science; Artificial intelligence; Radiology; Nursing; Pathology; Alternative medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006781222,0.0004095723,0.001108962,0.0009259499,0.000780575,0.0002997186,0.001802933,0.0002611865,0.0001311531],"category_scores_gemma":[0.01277579,0.0003887649,0.0004281606,0.004158429,0.0004122849,0.0002621548,0.0008556204,0.001680808,0.00002057137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001295131,"about_ca_system_score_gemma":0.002145844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005700734,"about_ca_topic_score_gemma":0.0003160839,"domain_scores_codex":[0.9913614,0.001237965,0.003038235,0.001633539,0.001512254,0.001216612],"domain_scores_gemma":[0.971892,0.02354078,0.0005448683,0.00147927,0.002050298,0.0004927762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.1041729,0.1302053,0.3244751,0.03005864,0.001010335,0.0001135595,0.01182042,0.0007788985,0.01118113,0.03114265,0.01880494,0.3362361],"study_design_scores_gemma":[0.06279664,0.1524351,0.283691,0.01357413,0.0001505277,0.0001348585,0.0584415,0.002261632,0.01458237,0.08972398,0.3180623,0.004145926],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"protocol","genre_scores_codex":[0.006380968,8.784788e-7,0.05061457,0.001227094,0.00004955802,0.9413638,0.0002000143,0.0001076132,0.00005554415],"genre_scores_gemma":[0.02993383,3.117378e-7,0.02662247,0.0003055704,0.0003526883,0.9424849,0.0001202779,0.0001057035,0.00007431375],"genre_candidate":"protocol","genre_consensus":"protocol","teacher_disagreement_score":0.3320902,"threshold_uncertainty_score":0.9998564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6375553502465099,"score_gpt":0.6424460601216028,"score_spread":0.00489070987509288,"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."}}