Abstract

Previously, adaptive learning algorithms have been used with immunosignaturing in order to identify disease states in patients. However, in these algorithms the presence of a single disease state is assumed, although in a clinical setting this may not be the case. We propose a novel algorithm based on latent feature identification using beta process factor analysis, in which the binary feature sharing matrix is modified and key comparisons are applied to identify multiple possible underlying disease states. The algorithm is verified using combinations of actual patient immunosignaturing data. The proposed method has a variety of applications, including multi-disease state diagnosis in the clinical setting, multi-biothreat detection in the field, and separation of co-contaminated biological samples.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
PublisherIEEE Computer Society
Pages1301-1305
Number of pages5
ISBN (Print)9781479923908
DOIs
StatePublished - 2013
Event2013 47th Asilomar Conference on Signals, Systems and Computers - Pacific Grove, CA, United States
Duration: Nov 3 2013Nov 6 2013

Other

Other2013 47th Asilomar Conference on Signals, Systems and Computers
CountryUnited States
CityPacific Grove, CA
Period11/3/1311/6/13

Fingerprint

Pathology
Factor analysis
Adaptive algorithms
Learning algorithms

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Malin, A., Kovvali, N., Papandreou-Suppappola, A., O'Donnell, B., Johnston, S., & Stafford, P. (2013). Adaptive learning of immunosignaturing features for multi-disease pathologies. In Conference Record - Asilomar Conference on Signals, Systems and Computers (pp. 1301-1305). [6810504] IEEE Computer Society. https://doi.org/10.1109/ACSSC.2013.6810504

Adaptive learning of immunosignaturing features for multi-disease pathologies. / Malin, Anna; Kovvali, Narayan; Papandreou-Suppappola, Antonia; O'Donnell, Brian; Johnston, Stephen; Stafford, Phillip.

Conference Record - Asilomar Conference on Signals, Systems and Computers. IEEE Computer Society, 2013. p. 1301-1305 6810504.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Malin, A, Kovvali, N, Papandreou-Suppappola, A, O'Donnell, B, Johnston, S & Stafford, P 2013, Adaptive learning of immunosignaturing features for multi-disease pathologies. in Conference Record - Asilomar Conference on Signals, Systems and Computers., 6810504, IEEE Computer Society, pp. 1301-1305, 2013 47th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, United States, 11/3/13. https://doi.org/10.1109/ACSSC.2013.6810504
Malin A, Kovvali N, Papandreou-Suppappola A, O'Donnell B, Johnston S, Stafford P. Adaptive learning of immunosignaturing features for multi-disease pathologies. In Conference Record - Asilomar Conference on Signals, Systems and Computers. IEEE Computer Society. 2013. p. 1301-1305. 6810504 https://doi.org/10.1109/ACSSC.2013.6810504
Malin, Anna ; Kovvali, Narayan ; Papandreou-Suppappola, Antonia ; O'Donnell, Brian ; Johnston, Stephen ; Stafford, Phillip. / Adaptive learning of immunosignaturing features for multi-disease pathologies. Conference Record - Asilomar Conference on Signals, Systems and Computers. IEEE Computer Society, 2013. pp. 1301-1305
@inproceedings{9f61f68e74bd43e8bd3492cb49775688,
title = "Adaptive learning of immunosignaturing features for multi-disease pathologies",
abstract = "Previously, adaptive learning algorithms have been used with immunosignaturing in order to identify disease states in patients. However, in these algorithms the presence of a single disease state is assumed, although in a clinical setting this may not be the case. We propose a novel algorithm based on latent feature identification using beta process factor analysis, in which the binary feature sharing matrix is modified and key comparisons are applied to identify multiple possible underlying disease states. The algorithm is verified using combinations of actual patient immunosignaturing data. The proposed method has a variety of applications, including multi-disease state diagnosis in the clinical setting, multi-biothreat detection in the field, and separation of co-contaminated biological samples.",
author = "Anna Malin and Narayan Kovvali and Antonia Papandreou-Suppappola and Brian O'Donnell and Stephen Johnston and Phillip Stafford",
year = "2013",
doi = "10.1109/ACSSC.2013.6810504",
language = "English (US)",
isbn = "9781479923908",
pages = "1301--1305",
booktitle = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Adaptive learning of immunosignaturing features for multi-disease pathologies

AU - Malin, Anna

AU - Kovvali, Narayan

AU - Papandreou-Suppappola, Antonia

AU - O'Donnell, Brian

AU - Johnston, Stephen

AU - Stafford, Phillip

PY - 2013

Y1 - 2013

N2 - Previously, adaptive learning algorithms have been used with immunosignaturing in order to identify disease states in patients. However, in these algorithms the presence of a single disease state is assumed, although in a clinical setting this may not be the case. We propose a novel algorithm based on latent feature identification using beta process factor analysis, in which the binary feature sharing matrix is modified and key comparisons are applied to identify multiple possible underlying disease states. The algorithm is verified using combinations of actual patient immunosignaturing data. The proposed method has a variety of applications, including multi-disease state diagnosis in the clinical setting, multi-biothreat detection in the field, and separation of co-contaminated biological samples.

AB - Previously, adaptive learning algorithms have been used with immunosignaturing in order to identify disease states in patients. However, in these algorithms the presence of a single disease state is assumed, although in a clinical setting this may not be the case. We propose a novel algorithm based on latent feature identification using beta process factor analysis, in which the binary feature sharing matrix is modified and key comparisons are applied to identify multiple possible underlying disease states. The algorithm is verified using combinations of actual patient immunosignaturing data. The proposed method has a variety of applications, including multi-disease state diagnosis in the clinical setting, multi-biothreat detection in the field, and separation of co-contaminated biological samples.

UR - http://www.scopus.com/inward/record.url?scp=84901280583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901280583&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2013.6810504

DO - 10.1109/ACSSC.2013.6810504

M3 - Conference contribution

AN - SCOPUS:84901280583

SN - 9781479923908

SP - 1301

EP - 1305

BT - Conference Record - Asilomar Conference on Signals, Systems and Computers

PB - IEEE Computer Society

ER -