A total of 602 organ systems in 260 exams out of 193 patients were identified for this study (26 exams in the first trimester, 161 in the second, and 73 in third trimester). Table 1 shows the total number of organs scanned with 3DUS for each impact group. In the D group, the most significant findings were in these organs: face exams 10, brain 5 and uterine shape 4. In the I group, the most significant findings were in these organs: extremities 16 exams, urogenital system 15, placenta 15 and brain 10. In the V group, the most significant findings were in these organs: face 101 exams, spine 75, extremities 74 and skull 68. In the S group, the most significant findings were in these organs: heart 5 exams, and adnexa 3.

Oral communication abstracts variables could improve ultrasound prediction of fetal macrosomia over prediction which relies on the commonly used formulas for the sonographic estimation of fetal weight. Methods: The δ SVM algorithm was used for binary classification between two categories of weight estimation: > 4000 g and < 4000 g. Clinical and sononographic input variables of 100 pregnancies suspected of having LGA fetuses were tested. Results: Thirteen of 38 features were selected as contributing variables that distinguish birth weights of below 4000 g and of 4000 g and above. Considering 4000 g as a cutoff weight the pattern recognition algorithm predicted macrosomia with a sensitivity of 81%, specificity of 73%, positive predictive value of 81% and negative predictive value of 73%. The comparative figures according to the combined criteria based on two commonly used formulae generated from regression analysis were 88.1%, 34%, 65.8% and 66.7%. Conclusions: The δ SVM algorithm provides a prediction of LGA fetuses comparable to that of other commonly used formulae generated from regression analysis. The better specificity and better positive predictive value suggest potential value for this method and further accumulation of data may improve the reliability of this approach.