Premium
P04.08: The use of anatomical intelligence to automate fetal biometry
Author(s) -
Ruma M.S.,
Collins H.,
Ou S.,
Strassner D.
Publication year - 2018
Publication title -
ultrasound in obstetrics and gynecology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.202
H-Index - 141
eISSN - 1469-0705
pISSN - 0960-7692
DOI - 10.1002/uog.19651
Subject(s) - medicine , fetal head , ultrasound , biparietal diameter , biometrics , fetus , semi automatic , circumference , obstetrics , gestational age , nuclear medicine , head circumference , pregnancy , radiology , artificial intelligence , computer science , mathematics , mechanical engineering , genetics , geometry , engineering , biology
was determined using the Hadlock (BPD-HC-AC-FL) formula. The accuracy of prediction of fetal macrosomia was assessed using the area under the receiver-operating characteristics curve (AUC). Results: The prevalence of fetal macrosomia (birthweight ≥ 4000g) was 13% (n=33). The EFW percentile had the best predictive performance for fetal macrosomia (AUC 0.875, 95% CI 0.795-0.955), with a negative predictive value of 96.7% and a positive predictive value of 36.5%. The predictive performance of EFW percentile was higher in the subgroup of women requiring insulin and/or oral antidiabetic drugs (AUC 0.955, 95% CI 0.858-1.000; PPV 77.8%, NPV 96.3%). Conclusions: Ultrasound biometry in the late third trimester is effective in identifying those fetuses that are unlikely to become macrosomic by the time of birth. Among the patients treated pharmacologically, the examination is useful for prediction of fetal macrosomia. Supported by AZV 15-27630A.