Use this URL to cite or link to this record in EThOS:
Title: Vital sign monitoring and data fusion in haemodialysis
Author: Borhani, Yasmina
Awarding Body: University of Oxford
Current Institution: University of Oxford
Date of Award: 2013
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Restricted access.
Access from Institution:
Intra-dialytic hypotension (IDH) is the most common complication in haemodialysis (HD) treatment and has been linked with increased mortality in HD patients. Despite various approaches towards understanding the underlying physiological mechanisms giving rise to IDH, the causes of IDH are poorly understood. Heart Rate Variability (HRV) has previously been suggested as a predictive measure of IDH. In contrast to conventional spectral HRV measures in which the frequency bands are defined by fixed limits, a new spectral measure of HRV is introduced in which the breathing rate is used to identify and measure the physiologically-relevant peaks of the frequency spectrum. The ratio of peaks leading up to the IDH event was assessed as a possible measure for IDH prediction. Changes in the proposed measure correlate well with the magnitude of abrupt changes in blood pressure in patients with autonomic dysfunction, but there is no such correlation in patients without autonomic dysfunction. At present, routine clinical vital sign monitoring beyond simple weight and blood pressure measurements at the start and end of each session has not established itself in clinical practice. To investigate the benefits of continuous vital sign monitoring in HD patients with regard to detecting and predicting IDH, different population-based and patient-specific models of normality were devised and tested on data from an observational study at the Oxford Renal Unit in which vital signs were recorded during HD sessions. Patient-specific models of normality performed better in distinguishing between IDH and non-IDH data, primarily due to the wide range of vital sign data included as part of the training data in the population-based models. Further, a patient-specific data fusion model was constructed using Parzen windows to estimate a probability density function from the training data consisting of vital signs from IDH-free sessions. Although the model was constructed using four vital sign inputs, novelty detection was found to be primarily driven by blood pressure decreases.
Supervisor: Tarassenko, Lionel Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available
Keywords: Engineering & allied sciences ; Biomedical engineering ; Medical Engineering ; Data Fusion ; High-Dimensional Visualisation ; Vital Sign Monitoring ; Haemodialysis ; Heart Rate Variability