Methods Inf Med 2014; 53(02): 108-114
DOI: 10.3414/ME12-01-0108
Original Articles
Schattauer GmbH

Classification of Exacerbation Episodes in Chronic Obstructive Pulmonary Disease Patients

A. Dias
1   Computer Science Department, University of Tromsø, Tromsø, Norway
2   Institute for Medical Statistics and Epidemiology (IMSE), Technische Universität München, Munich, Germany
,
L. Gorzelniak
2   Institute for Medical Statistics and Epidemiology (IMSE), Technische Universität München, Munich, Germany
3   Institute for Epidemiology, Helmholtz-Zentrum München, German Research Center for Environmental Health, Munich, Germany
,
K. Schultz
4   Clinic Bad Reichenhall, Center for Rehabilitation, Pneumology and Orthopedics, Bad Reichenhall, Germany
,
M. Wittmann
4   Clinic Bad Reichenhall, Center for Rehabilitation, Pneumology and Orthopedics, Bad Reichenhall, Germany
,
J. Rudnik
4   Clinic Bad Reichenhall, Center for Rehabilitation, Pneumology and Orthopedics, Bad Reichenhall, Germany
,
R. Jörres
5   Institute and Outpatient Clinic for Occupational, Social and Environmental Medicine, LMU, Munich, Germany
,
A. Horsch
2   Institute for Medical Statistics and Epidemiology (IMSE), Technische Universität München, Munich, Germany
6   Department of Computer Science and Department of Clinical Medicine, University of Tromsø, Tromsø, Norway
› Institutsangaben
Weitere Informationen

Publikationsverlauf

received: 04. Dezember 2012

accepted: 01. Februar 2013

Publikationsdatum:
20. Januar 2018 (online)

Summary

Background: Chronic obstructive pulmonary disease (COPD) is a progressive disease affecting the airways, which constitutes a major cause of chronic morbidity and a significant economic and social burden throughout the world. Despite the fact that in COPD patients exacerbations are common acute events causing significant and often fatal worsening of symptoms, an accurate prognostication continues to be difficult.

Objectives: To build computational models capable of distinguishing between normal life days from exacerbation days in COPD patients, based on physical activity measured by accelerometers.

Methods: We recruited 58 patients suffering from COPD and measured their physical activity with accelerometers for 10 days or more, from August 2009 to March 2010. During this period we recorded six exacerbation episodes in the patients, accounting for 37 days. We were able to analyse data for 52 patients (369 patient days), and extracted three distinct sets of features from the data, one set of basic features such as average, one set based on the frequency domain and the last exploring the cross-information among sensors pairs. These were used by three machine-learning techniques (logarith mic regression, neural networks, support vector machines) to distinguish days with exacerbation events from normal days.

Results: The support vector machine clas -sifier achieved an AUC of 90% ± 9, when supplied with a set of features resulting from sequential feature selection method. Neural networks achieved an AUC of 83% ± 16 and the logarithmic regression an AUC of 67% ± 15.

Conclusions: None of the individual feature sets provided robust for reasonable classi -fication of PA recording days. Our results indicate that this approach has the potential to extract useful information for, but are not robust enough for medical application of the system.

 
  • References

  • 1 Global Initiative for Lung Diseases. Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease [internet]. Jun 2009 [cited 12 July 2010]. Available from www.goldcopd.com
  • 2 Mathers CD, Loncar D. Projections of global mortality and burden of disease from 2002 to 2030. PLoS Med 2006; 3: e442
  • 3 Wilkinson T, Wedzicha J. Strategies for improving outcomes of COPD exacerbations. J Chron Obstruct Pulmon Dis 2006; 1: 335-342.
  • 4 Mackay AJ, Hurst JR. COPD Exacerbations: Causes, Prevention, and Treatment. Med Clin North Am 2012; 96: 789-809.
  • 5 Polkey MI, Rabe K. Chicken or egg: physical activity in COPD revisited. Eur Respir J 2009; 33: 227-229.
  • 6 Garcia-Aymerich J, Lange P, Benet M, Schnohr P, Antó J M. Regular physical activity modifies smoking-related lung function decline and reduces risk of chronic obstructive pulmonary disease: a population-based cohort study. Am J Respir Crit Care Med 2007; 175: 458-463.
  • 7 Pitta F, Troosters T, Probst VS, Spruit MA, Decramer M, Gosselink R. Quantifying physical activity in daily life with questionnaires and motion sensors in COPD. Eur Respir J 2006; 27: 1040-1055.
  • 8 Marin JM, Carrizo SJ, Casanova C, Martinez-Camblor P, Soriano JB, Agusti AGN. et al Prediction of risk of COPD exacerbations by the BODE index. Respir Med 2009; 103: 373-378.
  • 9 Miniati M, Monti S, Bottai M, Cocci F, Fornai E, Lubrano V. Prognostic value of C-reactive protein in chronic obstructive pulmonary disease. Intern Emerg Med 2011; 6: 423-430.
  • 10 Almagro P, Barreiro B, Ochoa AE, Quintana S, Rodríguez MC. Heredia JL, Garau J. Risk factors for hospital readmission in patients with chronic obstructive pulmonary disease. Respiration 2006; 73: 311-317.
  • 11 Ong KC, Earnest A, Lu SJ. A multidimensional grading system (BODE index) as predictor of hospitalization for COPD. Chest 2005; 128: 3810-3816.
  • 12 Jensen MH, Cichosz SL, Dinesen B, Hejlesen OK. Moving prediction of exacerbation in chronic obstructive pulmonary disease for patients in telecare. J Telemed Telecare 2012; 18: 99-103.
  • 13 Garcia-Rio F, Rojo B, Casitas R, Lores V, Madero R, Romero D, Galera R, Villasante C. Prognostic value of the objective measurement of daily physical activity in patients with COPD. Chest. 2012; 142: 338-346.
  • 14 Waschki B, Spruit M, Watz H, Albert P, Shrikrishna D, Groenen M. et al Physical activity monitoring in COPD: compliance and associations with clinical characteristics in a multicenter study. Respir Med 2012; 106: 522-530.
  • 15 Marschollek M, Rehwald A, Wolf KH, Gietzelt M, Nemitz G, Meyer zu Schwabedissen H, Haux R. Sensor-based Fall Risk Assessment - an Expert ‘to go’. Methods Inf Med 2011; 50 (05) 420-426.
  • 16 Gietzelt M, Wolf KH, Kohlmann M, Marschollek M, Haux R. Measurement of Accelerometry-based Gait Parameters in People with and without Dementia in the Field. Methods Inf Med 2013; 52 (04) 319-325.
  • 17 Gorzelniak L, Dias A, Schultz K, Wittmann M, Karrasch S, Jorres R, Horsch A. Comparison of recording positions of physical activity in severe COPD undergoing LTOT. COPD 2012; 9 (05) 528-537.
  • 18 John D, Tyo B, Bassett DR. Comparison of four ActiGraph accelerometers during walking and running. Med Sci Sports Exerc 2010; 42: 368-374.
  • 19 Nichols JF, Morgan CG, Chabot LE, Sallis JF, Calfas KJ. Assessment of physical activity with the Computer Science and Applications, Inc., accelerometer: laboratory versus field validation. Res Q Exerc Sport 2000; 71: 36-43.
  • 20 Powell SM, Jones DI, Rowlands AV. Technical variability of the RT3 accelerometer. Med Sci Sports Exerc 2003; 35: 1773-1778.
  • 21 Hecht A, Ma S, Porszasz J, Casaburi R. & COPD Clinical Research Network. Methodology for using long-term accelerometry monitoring to describe daily activity patterns in COPD. COPD 2009; 6: 121-129.
  • 22 Sekine M, Akay M, Tamura T, Higashi Y, Fujimoto T. Fractal dynamics of body motion in patients with Parkinson’s disease. J Neural Eng 2004; 1: 8-15.