Blood Pressure Drop Prediction by using HRV Measurements in Orthostatic Hypotension
- 249 Downloads
Orthostatic Hypotension is defined as a reduction of systolic and diastolic blood pressure within 3 minutes of standing, and may cause dizziness and loss of balance. Orthostatic Hypotension has been considered an important risk factor for falls since 1960. This paper presents a model to predict the systolic blood pressure drop due to orthostatic hypotension, relying on heart rate variability measurements extracted from 5 minute ECGs recorded before standing. This model was developed and validated with the leave-one-out cross-validation technique involving 10 healthy subjects, and finally tested with an additional 5 healthy subjects, whose data were not used during the training and cross-validation process. The results show that the model predicts correctly the systolic blood pressure drop in 80 % of all experiments, with an error rate below the measurement error of a sphygmomanometer digital device.
KeywordsDrop blood pressure prediction Heart rate variability Orthostatic hypotension Falls in later life
- 6.Gates, S., Fisher, J.D., Cooke, M.W., Carter, Y.H., Lamb, S.E., Multifactorial assessment and targeted intervention for preventing falls and injuries among older people in community and emergency care settings: systematic review and meta-analysis. BMJ: Br. Med. J. 336:130–133, 2008.CrossRefGoogle Scholar
- 14.Electrophysiology, Task, Force, of, the, European, Society, of, Cardiology, the, North, American, Society, of and Pacing Heart Rate Variability: Standards of Measurement, Physiological Interpretation, and Clinical Use. Circulation 93(5):1043–1065, 1996.Google Scholar
- 24.Sannino, G., Melillo, P., De Pietro, G., Stranges, S., Pecchia, L.: To What Extent It Is Possible to Predict Falls due to Standing Hypotension by Using HRV and Wearable Devices? Study Design and Preliminary Results from a Proof-of-Concept Study. In: Ambient Assisted Living and Daily Activities, pp. 167–170. Springer International Publishing (2014)Google Scholar