{"id":"W4406792383","doi":"10.1002/uog.29178","title":"Intra‐ and interobserver agreement of proposed objective transvaginal ultrasound image‐quality scoring system for use in artificial intelligence algorithm development","year":2025,"lang":"en","type":"article","venue":"Ultrasound in Obstetrics and Gynecology","topic":"Ovarian function and disorders","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"University of Adelaide; Australian Government","keywords":"Intraclass correlation; Ultrasound; Kappa; Cohen's kappa; Image quality; Medicine; Artificial intelligence; Algorithm; Image (mathematics); Medical physics; Machine learning; Radiology; Computer science; Mathematics; Reproducibility; Statistics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006852472,0.000181307,0.0004834655,0.000535268,0.00006730467,0.00004211617,0.0000656764,0.0001608156,0.00002120345],"category_scores_gemma":[0.009652803,0.0001785877,0.00004581559,0.0006374711,0.0001845772,0.0001195189,0.0000276092,0.0002149637,0.000001044536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003388589,"about_ca_system_score_gemma":0.0002210073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001765903,"about_ca_topic_score_gemma":0.0006484116,"domain_scores_codex":[0.998245,0.0001067179,0.0007896332,0.0004291199,0.0001326192,0.0002968837],"domain_scores_gemma":[0.9885432,0.01091494,0.0001227291,0.0001542603,0.000190233,0.00007465266],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001084367,0.001767888,0.2887923,0.002684204,0.000339918,0.00004608061,0.006347588,0.00005533831,0.01502607,0.02347691,0.00003891346,0.6603404],"study_design_scores_gemma":[0.007987637,0.001500287,0.9193169,0.0007659257,0.0002069555,0.00006042885,0.0299885,0.001819512,0.02991693,0.004204798,0.003503969,0.0007281327],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9310516,0.0004658449,0.06608607,0.0001129191,0.0007857648,0.00113945,0.00001913207,0.00001826915,0.0003209131],"genre_scores_gemma":[0.9810785,0.0002191494,0.01838067,0.0001346034,0.00001095906,0.00005706583,0.00002562427,0.000009721376,0.00008368044],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6596122,"threshold_uncertainty_score":0.9986893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03395154968955053,"score_gpt":0.2960023861570037,"score_spread":0.2620508364674532,"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."}}