Fusing continuous-valued medical labels using a Bayesian ModelReportar como inadecuado




Fusing continuous-valued medical labels using a Bayesian Model - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Reference: Zhu, T, Dunkley, N, Behar, J et al., (2015). Fusing continuous-valued medical labels using a Bayesian Model. Annals of Biomedical Engineering, 43 (12), 2892-2902.Citable link to this page:

 

Fusing continuous-valued medical labels using a Bayesian Model

Abstract: With the rapid increase in volume of time series medical data available through wearable devices, there is a need to employ automated algorithms to label data. Examples of labels include interventions, changes in activity (e.g. sleep) and changes in physiology (e.g. arrhythmias). However, automated algorithms tend to be unreliable resulting in lower quality care. Expert annotations are scarce, expensive, and prone to significant inter- and intra-observer variance. To address these problems, a Bayesian Continuous-valued Label Aggregator (BCLA) is proposed to provide a reliable estimation of label aggregation while accurately infer the precision and bias of each algorithm. The BCLA was applied to QT interval (pro-arrhythmic indicator) estimation from the electrocardiogram using labels from the 2006 PhysioNet/Computing in Cardiology Challenge database. It was compared to the mean, median, and a previously proposed Expectation Maximization (EM) label aggregation approaches. While accurately predicting each labelling algorithm's bias and precision, the root-mean-square error of the BCLA was 11.78 ± 0.63 ms, significantly outperforming the best Challenge entry (15.37 ± 2.13 ms) as well as the EM, mean, and median voting strategies (14.76 ± 0.52, 17.61 ± 0.55, and 14.43 ± 0.57 ms respectively with p < 0.0001). The BCLA could therefore provide accurate estimation for medical continuous-valued label tasks in an unsupervised manner even when the ground truth is not available.

Peer Review status:Peer reviewedPublication status:PublishedVersion:Accepted manuscriptNotes:© Biomedical Engineering Society 2015, published by Springer Verlag under license. This is the accepted manuscript version of the article. The final version is available online from Springer at: [10.1007/s10439-015-1344-1]

Bibliographic Details

Publisher: Springer Verlag

Publisher Website: http://www.springerlink.com/?MUD=MP

Journal: Annals of Biomedical Engineeringsee more from them

Publication Website: http://link.springer.com/journal/10439

Issue Date: 2015-06-03

pages:2892-2902Identifiers

Urn: uuid:8ce2bab5-406b-4cf5-b28e-01d64a85ec83

Source identifier: 527084

Eissn: 1573-9686

Doi: https://doi.org/10.1007/s10439-015-1344-1

Issn: 0090-6964 Item Description

Type: Journal article;

Language: eng

Version: Accepted manuscriptKeywords: Bayes methods Crowdsourcing Electrocardiography Time series analysis Tiny URL: pubs:527084

Relationships





Autor: Zhu, T - institutionUniversity of Oxford Oxford, MPLS, Engineering Science grantNumberEP-G036861-1 grantNumberARM Scholarship in

Fuente: https://ora.ox.ac.uk/objects/uuid:8ce2bab5-406b-4cf5-b28e-01d64a85ec83



DESCARGAR PDF




Documentos relacionados