Heart Rate Variability Analysis Using Polynomial Network

High-risk newborn infants in an intensive care unit often suffer significant morbidity and mortalitybecause of infectious illnesses which elude early diagnosis and are present in advanced stages withcirculatory shock. Earlier diagnosis and therapy might present in advanced stages with circulatoryshock. Earlier diagnosis and therapy might prevent or reduce late complications and deaths. A strategyfor early detection of impending catastrophic events should reduce mortality as well as hospital costs.Our research is based on the fact that the time between successive heartbeats varies incessantly. Innewborn infants, this heart rate variability is reversibly reduced during severe illness. During thisprogram, this heart rate variability is reversibly reduced during severe illness. During this program, theheart rate variability of hospitalized, at-risk newborn infant will be monitored to test the hypothesis thata decrease in heart rate variability presages a catastrophic infectious illness. Preliminary researchsupports this hypothesis. heart rate variability data will be processed using an innovative multi-linearanalysis technology: polynomial networks. Polynomial networks have been successfully applied to manydata processing challenges in the fields of health care, financial modeling, and pattern recognition. Thiswill result in clinically useful indices to quantify heart rate variability. The long-term objective of thiseffort is to test the hypothesis that monitoring heart rate variability will lead to earlier diagnosis and moreeffective therapy of catastrophic infectious illnesses in newborn infants, and thus be useful for a varietyof clinical practices.