umu.sePublications
Change search
ExportLink to record
Permanent link

Direct link
BETA

Project

Project type/Form of grant
Project grant
Title [sv]
Interaktiv kognitiv arkitektur för prediktion av dysfunktion i den autonoma regleringen av det kardiovaskulära systemet
Title [en]
Realtime interactive cognitive architecture for prediction of autonomic cardiovascular dysregulation
Abstract [en]
The primary purpose of the project is to improve the diagnosis of autonomous nervous system (ANS) dysregulation during clinical examinations and treatment. Specifically, the practical goal of the project is to improve the accuracy of the automatic detection and prediction of abnormalities in the cardiovascular autonomic regulation in real time; and thus to improve the clinical outcome of the patients.The overall aim of the project is to develop new methods based on advanced machine learning techniques for automatic real-time prediction of cardiovascular autonomic dysregulation during diagnostic tests and treatment. The projects sets the following specific aims:1. To further develop multivariate signal processing methods to derive clinically relevant features for characterization of cardiovascular autonomic regulation. This includes development of robust algorithms for real-time analysis of cardiovascular signals, detection of heartbeats, error detection and correction, and arrhythmia analysis.2. To create an interactive computational framework based on the principles of biologically inspired cognitive architectures for automatic processing of the multivariate data, consisting of the results from the cardiovascular signal processing, for real time detection of cardiovascular dysregulation and for prediction of the risks for severe cardiovascular events. 3. To evaluate and characterize autonomic dysregulation, with main focus on the following clinical settings: a) Autonomic function tests (tilt test, ambulatory tests) in healthy subjects and patients with autonomic dysfunction; b) Prolonged head-up tilt tests for identifying different patterns of vasovagal syncope; and c) Analyses of cardiovascular signals in patients with acute brain damages during intensive-care treatment. The novelty of the proposed project stems from the application of diverse machine learning techniques and a mathematical framework for biologically-inspired associative symbolic reasoning to reveal patterns when the number of variables are large (as after cardiovascular signal processing). Moreover, we take the challenge to do all analyses in real-time. The framework for associative symbolic reasoning is based on a novel methodology developed by the applicants that recently showed promising results for fault detection inside a human-made plant. Our vision is that this concept also will work for fault detection inside of a human.
Principal InvestigatorWiklund, Urban
Coordinating organisation
Umeå University
Funder
Period
2016-01-01 - 2019-12-31
National Category
Other Medical Engineering
Identifiers
DiVA, id: project:1408Project, id: 2015-04677_VR

Search in DiVA

Other Medical Engineering

Search outside of DiVA

GoogleGoogle Scholar