Skip to main navigation Skip to search Skip to main content

Allergy detection with statistical modelling of HRV-based non-reaction baseline features

Research output: Chapter in Book/Report/Conference proceedingsConference proceedingpeer-review

Abstract

This paper investigates the automated classification of oral food challenges ('allergy tests'). The electrocardiograms (ECG) of the subjects being tested for allergies were recorded via a wireless mote, and the QRS complexes were manually annotated and 18 features were extracted from the signals. Principal component analysis was used for feature decorelation and dimensionality reduction and diagonal covariance Gaussian mixture models were used to model non-reaction baseline patient condition. The generated subject independent log likelihood plots were used to separate allergic reaction by means of subject adaptive thresholding. The platform resulted in 87% accuracy of classification with 100% specificity. The algorithm presented can detect allergy up to 30 minutes sooner than the current state of the clinical art allergy detection (7minutes ± 9).

Original languageEnglish
Title of host publicationProceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies, ISABEL'11
DOIs
Publication statusPublished - 2011
Event4th International Symposium on Applied Sciences in Biomedical and Communication Technologies, ISABEL'11 - Barcelona, Spain
Duration: 26 Oct 201129 Oct 2011

Publication series

NameACM International Conference Proceeding Series

Conference

Conference4th International Symposium on Applied Sciences in Biomedical and Communication Technologies, ISABEL'11
Country/TerritorySpain
CityBarcelona
Period26/10/1129/10/11

Fingerprint

Dive into the research topics of 'Allergy detection with statistical modelling of HRV-based non-reaction baseline features'. Together they form a unique fingerprint.

Cite this