Associations of pulmonary parameters with accelerometer data
dc.contributor.advisor | Hartvigsen, Gunnar | |
dc.contributor.author | Dias, André | |
dc.date.accessioned | 2014-06-13T10:17:19Z | |
dc.date.available | 2014-06-13T10:17:19Z | |
dc.date.issued | 2014-03-25 | |
dc.description.abstract | In Europe it is estimated that the number of elderly people aged above 65 will have doubled by 2060. In several chronic pulmonary diseases patients can suffer recurrent exacerbation episodes that can lead to severe breathing or death. In this thesis we explore the association of physical activity to lung health parameters, focusing on cystic fibrosis and chronic obstructive pulmonary disease patients and a group of the general population. The main goals of the thesis were to assess the feasibility of classifying exacerbation episodes in cystic fibrosis and chronic obstructive pulmonary disease patients and to implement new parameters in the context of a cohort study. We conducted four distinct studies involving in total over 250 subjects. We asked them to wear a set of accelerometers, including GT3X and RT3, recording physical activity for up to 14 days. The data was processed and several features extracted that were used as inputs in three different classification algorithms: logarithmic regression, neural networks and support vector machines. We achieved an area under the curve of 67% with logarithmic regression, 83% with neural networks and 90% with support vector machines when classifying exacerbation episodes in chronic obstructive pulmonary disease. A neural network was achieved an accuracy of 85% distinguishing cystic fibrosis patients from healthy controls. We proposed, extracted and tested a large set of physical activity parameters for use in KORA-Age. The work on classification of exacerbations in COPD patients is, to our knowledge, the first attempt based on features from accelerometer data. Overall SVM showed to be the most robust classifier with an area under the curve of 90%. Nevertheless the number of patients and episodes is too low to draw definitive conclusions. The next step to classify exacerbations in COPD is to design a study with a statistically significant number of exacerbation episodes. | en |
dc.description.doctoraltype | ph.d. | en |
dc.description.popularabstract | Antallet eldre og pasienter med kroniske sykdommer er i sterk økning i den vestlige verden, noe som gir betydelige utfordringer for helsetjenesten. Et eksempel er pasienter med kroniske lungesykdommer som kan oppleve utmattelsesepisoder som fører til akuttinnleggelser og i noen tilfeller død. Vi har sett på mulighetene for å oppdage slike utmattelseshendelser ved å bruke sensorer med innebygde aksellometre. Sensorene er små og enkle i bruk, og finnes i mange vanlige enheter som f.eks. mobiltelefoner. Dette har potensiale til å bedre livskvaliteten til pasientene og redusere antallet akuttinnleggelser, og dermed kostnader. Forskningen har vært utført i samarbeid med det Technische Universität og HelmholtzZentrum i München, Tyskland, og med økonomisk støtte fra det portugisiske forskningsfondet. | en |
dc.description.sponsorship | This thesis was supported by the Portuguese Foundation for Science and Technology (FCT), under scholarship BD/39867/2007 and Research Council of Norway Grant No. 174934. Additional research funding was provided by the Graduate School of Information Science in Health (GSISH) and the Technische Universität München Graduate School. | en |
dc.description | Some papers of this thesis are not available in Munin: <br/>Paper 2. Dias, A.; Gorzelniak, L.; Jorres, R.; Fischer, R.; Hartvigsen, G.; Horsch,A.: 'Assessing Physical Activity in the daily life of cystic fibrosis patients', Journal of Pervasive Computing (2012), vol. 8(6):837–844. Available at <a href=http://dx.doi.org/10.1016/j.pmcj.2012.08.001>http://dx.doi.org/10.1016/j.pmcj.2012.08.001</a> <br/>Paper 3. Gorzelniak, L.; Dias, A.; Schultz,K.; Wittmann, M.; Karrasch, S.; Jorres, R.; Horsch,A.: 'Comparison of recording positions of physical activity in severe COPD', Journal Of Chronic Obstructive Pulmonary Disease (2012), vol. 9(5):528-537. Available at <a href=http://dx.doi.org/10.3109/15412555.2012.708066>http://dx.doi.org/10.3109/15412555.2012.708066</a> <br/>Paper 4. Dias, A.; Gorzelniak, L.; Schultz,K.;Wittmann, M.; Rudnik, J.;Jorres, R.; Horsch,A.: 'Classification of exacerbation episodes in Chronic Obstructive Pulmonary Disease patients' (manuscript) <br/>Paper 5. Ortlieb, S.; Gorzelniak, L.; Dias,A.; Schulz, H.; Horsch,A.: 'Recommendations for Collecting and Processing Accelerometry Data in Older Healthy People' (manuscript) <br/> Additional paper 1. Dias, A.; Gorzelniak, L.; Doring, A.; Hartvigsen, G.; Horsch, A.: 'Extracting Gait Parameters from Raw Data Accelerometers', Studies in Health Technology and Informatics (2011), vol. 169:445-449. <br/> Additional paper 2. Gorzelniak, L.; Dias, A.; Soyer, H.; Knoll, A.; Horsch, A.; 'Using a Robotic Arm to Assess the Variability of Motion Sensors', Studies in Health Technology and Informatics (2011), vol. 169:897-901. <br/> Additional paper 3. Chen, C.; Dias, A.; Knoll, A.; Horsch, A.: 'A Prototype of a Wireless Body Sensor Network for Healthcare Monitoring', Medical informatics in Europe (2011). <br/>Additional paper 4. Skrovseth, S.; Dias, A.; Gorzelniak, L.; Godtliebsen, F.; Horsch, A.: 'Scale-space methods for live processing of sensor data', Medical informatics in Europe (2012). <br/>Additional paper 7. Peters A, Döring A, Ladwig KH, Meisinger C, Linkohr B, Autenrieth C, Baumeister SE, Behr J, Bergner A, Bickel H, Bidlingmaier M, Dias A, Emeny RT, Fischer B, Grill E, Gorzelniak L, Hänsch H, Heidbreder S, Heier M, Horsch A, Huber D, Huber RM, Jörres RA, Kääb S, Karrasch S, Kirchberger I, Klug G, Kranz B, Kuch B, Lacruz ME, Lang O, Mielck A, Nowak D, Perz S, Schneider A, Schulz H, Müller M, Seidl H, Strobl R, Thorand B, Wende R, Weidenhammer W, Zimmermann AK, Wichmann HE, Holle R.: 'Multimorbidity and successful aging: the populationbased KORA-Age study', Zeitschrift für Gerontologie und Geriatrie (2011), vol. 44(2):41-54. Available at <a href=http://dx.doi.org/10.1007/s00391-011-0245-7>http://dx.doi.org/10.1007/s00391-011-0245-7</a> | en |
dc.identifier.isbn | 978-82-8236-129-3 | |
dc.identifier.uri | https://hdl.handle.net/10037/6378 | |
dc.identifier.urn | URN:NBN:no-uit_munin_5963 | |
dc.language.iso | eng | en |
dc.publisher | UiT Norges arktiske universitet | en |
dc.publisher | UiT The Arctic University of Norway | en |
dc.rights.accessRights | openAccess | |
dc.rights.holder | Copyright 2014 The Author(s) | |
dc.subject.courseID | DOKTOR-004 | en |
dc.subject | VDP::Mathematics and natural science: 400::Information and communication science: 420::System development and system design: 426 | en |
dc.subject | VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Systemutvikling og -arbeid: 426 | en |
dc.title | Associations of pulmonary parameters with accelerometer data | en |
dc.type | Doctoral thesis | en |
dc.type | Doktorgradsavhandling | en |