Session SA1.3

Predicting Critical Situations of High Risk Cardiac Patients by Hemodynamic Monitoring

D Hayn*, A Kollmann, G Schreier

Austrian Research Centers
Graz, Austria

Monitoring of hemodynamic parameters such as blood pressure or heart rate is a common method for early detection of critical events in high risk cardiac patients. Typical applications include home-monitoring and monitoring of patients in intensive care units as included in the MIMIC II Database of the Computers in Cardiology Challenge 2009.
Home-monitoring in patients with congestive heart failure provides a powerful tool to look out for early warning signs and to reduce the high risk of adverse events. In a previous study, we used increasing body weight (2 kg weight gain within 2 days) as an early warning sign of fluid retention. This regimen led to an adjustment of medication, resulting in a reduced frequency and duration of heart failure hospitalisations. The data recorded in that study also indicate, that the difference in between systolic and diastolic blood pressure decreases prior to cardiac events.
We assume, that a similar behaviour might appear prior to acute hypotensive episodes. The present paper describes an approach for not only detecting severe hemodynamic events at the moment they appear, but for predicting such events early enough, so that their appearance can be avoided. The mean atrial blood pressure and the difference in between systolic and diastolic blood pressure were used as an initial feature for predicting such episodes. With our first entry to the Computers in Cardiology Challenge 2009 we received a score of 8 correct results out of 10 in event 1. Further research activities will focus on the influence of medication on hemodynamic parameters.

(Abstract Control Number: 278)