{"id":"W4407158464","doi":"10.1016/j.ejrad.2025.111985","title":"Association between deep learning radiomics based on placental MRI and preeclampsia with fetal growth restriction: A multicenter study","year":2025,"lang":"en","type":"article","venue":"European Journal of Radiology","topic":"Pregnancy and preeclampsia studies","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Key Technologies Research and Development Program; Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Medicine; Preeclampsia; Radiomics; Fetal growth; Multicenter study; Fetus; Intrauterine growth restriction; Obstetrics; Pregnancy; Internal medicine; Radiology","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":[0.001017133,0.0001510209,0.0004197734,0.0002262504,0.0001566315,0.0000174846,0.00008708421,0.00004328888,0.000006256557],"category_scores_gemma":[0.0003658828,0.0001120359,0.00006999035,0.0001549911,0.00006384692,0.00006645416,0.00003424982,0.0006430325,0.000002981104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001507444,"about_ca_system_score_gemma":0.00004552269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001825418,"about_ca_topic_score_gemma":0.000002686593,"domain_scores_codex":[0.9979465,0.001126641,0.0003794752,0.0001795027,0.0001799044,0.0001879773],"domain_scores_gemma":[0.9988886,0.0004524763,0.0003620928,0.0001010545,0.0001177812,0.00007803627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00171248,0.0001499113,0.9939624,0.00002889412,0.0008208703,0.0003595375,0.0007057369,0.0001995089,0.00002442972,0.0000190565,0.0005437423,0.001473445],"study_design_scores_gemma":[0.009290523,0.004924549,0.9827806,0.0002939223,0.0006448776,0.0001561443,0.000592249,0.0004785503,0.00003863085,0.000009786871,0.0006953934,0.00009477406],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856493,0.0009906911,0.005595727,0.001532827,0.0002634175,0.0003194097,0.000002044816,0.00002746983,0.005619098],"genre_scores_gemma":[0.9978397,0.0002975306,0.001216108,0.0002011123,0.0002673454,0.000001577856,0.000004323629,0.00001659276,0.0001557147],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01219038,"threshold_uncertainty_score":0.456869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01034480489704903,"score_gpt":0.2422364039000677,"score_spread":0.2318915990030186,"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."}}