Key result
An artificial neural network using maternal heart rate variability indexes classified preeclampsia with approximately 80% sensitivity and 85-90% specificity.
Why the study?
Does an artificial neural network using maternal heart rate variability indexes accurately classify normal, hypertensive, and preeclamptic pregnancies?
Observational (n=568)
Does an artificial neural network using maternal heart rate variability indexes accurately classify normal, hypertensive, and preeclamptic pregnancies?
An artificial neural network combining maternal HRV indexes, history, and blood pressure can classify preeclamptic, hypertensive, and normal pregnancies with approximately 80% sensitivity and 85-90% specificity.
Answers are grounded in this paper and cite their sources.
May support HRV-ANN models for preeclampsia classification research; leaves open prospective validation before clinical consideration.
OBJECTIVE: A model construction for classification of women with normal, hypertensive and preeclamptic pregnancy in different gestational ages using maternal heart rate variability (HRV) indexes. METHOD AND PATIENTS: In the present work, we applied the artificial neural network for the classification problem, using the signal composed by the time intervals between consecutive RR peaks (RR) (n = 568) obtained from ECG records. Beside the HRV indexes, we also considered other factors like maternal history and blood pressure measurements. RESULTS AND CONCLUSIONS: The obtained result reveals sensitivity for preeclampsia around 80% that increases for hypertensive and normal pregnancy groups. On the other hand, specificity is around 85-90%. These results indicate that the combination of HRV indexes with artificial neural networks (ANN) could be helpful for pregnancy study and characterization.
No takes yet. Share an insight, caveat, or question.
Tejera et al. (2011) conducted an observational in Pregnancy (normal, hypertensive, preeclamptic) (n=568). Artificial neural network using maternal heart rate variability indexes was evaluated on Classification of normal, hypertensive, and preeclamptic pregnancy. An artificial neural network using maternal heart rate variability indexes classified preeclampsia with approximately 80% sensitivity and 85-90% specificity.
Synapse has enriched 10 related papers. Consider them for comparative context: