Neural network prediction of nonstress test results: how often should we perform nonstress tests?

OBJECTIVE

Our purpose was to predict outcomes and optimal intervals for nonstress tests of term gravid women with neural networks.

STUDY DESIGN

We studied 100 normal term patients whose 30-minute nonstress tests, performed on 5 consecutive days, were computer analyzed for the following elements: fetal heart rate baseline, variability, signal loss, accelerations (> 15 beats/min), and decelerations. The training set used 65 patients; the testing, 35 patients. Nonstress test data (days 1 to 4) were inputs; day 5 data were training patterns. Networks for each nonstress test element used Brainmaker Macintosh 1.0 (California Scientific Software, Nevada City, Calif.) trained to 0.12 tolerance. Actual fetal heart rate elements and their daily differences were compared with predictions by the networks and multiple regressions.

RESULTS

There was little difference between networks using daily or alternate-day inputs for predicting test performance on day 5; networks using test intervals > 2 days could not be trained to tolerance. Long-term fetal heart rate variation was the nonstress test element best predicted. Daily differences networks provided better prediction of all day 5 data than did actual daily values networks or multiple regression formulas.

CONCLUSIONS

Baseline long-term fetal heart rate variability seems to be the most predictable fetal heart rate element over time and should merit more consideration in overall fetal testing. Fetal heart rate elements are not easily predicted by any method for intervals longer than 2 days. Using longer test intervals might run a greater risk for unanticipated changes in nonstress test outcomes, even when fetal condition is normal.