Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/19751

Title: Identifying Physical Activity Profiles in COPD Patients Using Topic Models
Authors: Spina, Gabriele
Casale, Pierluigi
Albert, Paul S.
Alison, Jennifer
Garcia-Aymerich, Judith
Costello, Richard W.
Hernandes, Nidia A.
van Gestel, Arnoldus J. R.
Leuppi, Joerg D.
Mesquita, Rafael
Singh, Sally J.
Smeenk, Frank W. J. M.
Tal-Singer, Ruth
Wouters, Emiel F. M.
Spruit, Martijn A.
den Brinker, Albertus C.
Issue Date: 2015
Abstract: With the growing amount of physical activity (PA) measures, the need for methods and algorithms that automatically analyze and interpret unannotated data increases. In this paper, PA is seen as a combination of multimodal constructs that can cooccur in different ways and proportions during the day. The design of a methodology able to integrate and analyze them is discussed, and its operation is illustrated by applying it to a dataset comprising data from COPD patients and healthy subjects acquired in daily life. The method encompasses different stages. The first stage is a completely automated method of labeling low-level multimodal PA measures. The information contained in the PA labels are further structured using topic modeling techniques, a machine learning method from the text processing community. The topic modeling discovers the main themes that pervade a large set of data. In our case, topic models discover PA routines that are active in the assessed days of the subjects under study. Applying the designed algorithm to our data provides new learnings and insights. As expected, the algorithm discovers that PA routines for COPD patients and healthy subjects are substantially different regarding their composition and moments in time in which transitions occur. Furthermore, it shows consistent trends relating to disease severity as measured by standard clinical practice.
Notes: [Spina, Gabriele; Casale, Pierluigi] Eindhoven Univ Technol, Dept Elect Engn, NL-5612 AZ Eindhoven, Netherlands. [Spina, Gabriele; den Brinker, Albertus C.] Philips Res, Smart Profess Spaces Grp, NL-5656 AE Eindhoven, Netherlands. [Casale, Pierluigi] IMEC, Holst Ctr, NL-5656 AE Eindhoven, Netherlands. [Albert, Paul S.] Aintree Univ Hosp NHS Fdn Trust, Sch Ageing & Chron Dis, Liverpool L9 7AL, Merseyside, England. [Alison, Jennifer] Univ Sydney, Clin & Rehabil Sci, Sydney, NSW 2006, Australia. [Alison, Jennifer] Royal Prince Alfred Hosp, Physiotherapy Dept, Sydney, NSW 2050, Australia. [Garcia-Aymerich, Judith] Ctr Res Environm Epidemiol, Barcelona 08003, Spain. [Garcia-Aymerich, Judith] CIBER Epidemiol & Salud Publ, Barcelona 08036, Spain. [Garcia-Aymerich, Judith] Univ Pompeu Fabra, Barcelona 08002, Spain. [Costello, Richard W.] Beaumont Hosp, Dept Resp Med, Dublin 9, Ireland. [Hernandes, Nidia A.] Univ Estadual Londrina, Dept Physiotherapy, Lab Res Resp Physiotherapy, BR-86057970 Londrina, Brazil. [van Gestel, Arnoldus J. R.] Univ Zurich Hosp, Div Pulm, CH-8091 Zurich, Switzerland. [Leuppi, Joerg D.] Cantonal Hosp Baselland, Med Univ Clin, Liestal, Switzerland. [Leuppi, Joerg D.] Univ Basel, Fac Med, CH-4003 Basel, Switzerland. [Mesquita, Rafael; Spruit, Martijn A.] CIRO, Dept Res & Educ, NL-6085 NM Horn, Netherlands. [Mesquita, Rafael] Maastricht Univ, Med Ctr, Dept Resp Med, NL-6211 LK Maastricht, Netherlands. [Singh, Sally J.] Univ Hosp, Ctr Exercise & Rehabil Sci, NIHR EM CLAHRC, Leicester LE3 9QP, Leics, England. [Smeenk, Frank W. J. M.] Catharina Hosp, Dept Resp Med, NL-5623 EJ Eindhoven, Netherlands. [Tal-Singer, Ruth] GlaxoSmithKline R&D, King Of Prussia, PA 19406 USA. [Spruit, Martijn A.] Hasselt Univ, REVAL BIOMED, B-3900 Diepenbeek, Belgium.
URI: http://hdl.handle.net/1942/19751
DOI: 10.1109/JBHI.2015.2432033
ISI #: 000360791200005
ISSN: 2168-2194
Category: A1
Type: Journal Contribution
Validation: ecoom, 2016
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
N/A626.44 kBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.