24-01-2013, 01:12 PM
Wireless sensor networks in monitoring of asthma
Wireless sensor.pdf (Size: 1.19 MB / Downloads: 31)
Abstract
Asthma is one of the widespread chronic diseases.
Rising prevalence increases the burden of personal disease
management, financial expenditures and workload, both on
sides of patients and healthcare systems. Firstly, the medical
background of asthma is given. Pathology and symptoms are
presented. Afterwards, the problem of persistent asthma management
is introduced with a short overview of traditional disease
management techniques. A review on approaches to asthma
telemonitoring is made. Effectiveness of home peakflowmetry is
analysed. Employment of low power wireless sensor networks
(WSN) paired with smartphone technologies is reviewed as a
novel asthma management tool. Using the technology, the aim is
to retain the disease in a controlled state with minimal effort,
invasiveness and cost, and assess patient’s condition objectively.
WSN-s for sensing of both asthma triggers in the environment,
and continuous monitoring of physiological functions, in particular
respiratory function are reviewed. Sensing modalities for
acquiring respiratory function are presented. Signal acquisition
prerequisites and signal processing of respiratory sounds are
reviewed. Focus is put on low-power continuous wheeze detection
techniques. At the end, research challenges for further studies
are identified.
INTRODUCTION
Together with diabetes and chronic hearth diseases, chronic
pulmonary diseases are mostly common group of chronic
diseases. Among pulmonary disorders, asthma is one of the
highly represented. It is estimated that 300 million people
worldwide suffer from asthma [1]. About 10% of overall children
population suffer from asthma. By 2025, it is estimated
that the number of patients with asthma will grow by more
than 100 million [2]. With rising prevalence, the expenditures
of healthcare system for patient treatment are expected to rise,
together with workload of the medical staff.
A. Definition, pathology and symptoms of asthma
Asthma is defined as a chronic hypersensitivity of the
bronchial airways. It manifests as recurring periods of obstruction
exacerbations (attacks) and calming periods. The
symptoms in the attacks include wheezing, shortness of breath
(dyspnea), chest tightness, cough. They emerge as a consequence
of contraction of the tracheobronchial smooth muscles
(bronchospasm), oedema and hyper-secretion of mucus, and
result in narrowing of the airways (bronchoconstriction) [3],
as shown in Fig. 1.
TRADITIONAL PROCEDURES OF ASTHMA
MANAGEMENT
Recurrence of the asthmatic attacks leads to irreversible
advancement of the disease into the subsequent stage. The goal
of daily management of asthma is retaining the disease in the
diagnosed stage and prevention of further progression. Thus,
it is necessary to ensure long-term adherence of the patient to
the chronic disease management plan.
Traditional procedures of asthma management in most cases
consist of adherence to the intake plan of prescribed medication
including both preventive and emergency medication,
avoidance of diagnosed triggers in the environment, periodical
pulmonary function self-assessment and periodical check at
the medical specialist for evaluation of the level of control.
Paper written asthma diaries of types and times of occurrence
of the symptoms and amounts of medication taken are
the traditional way of patient monitoring, common to chronic
diseases in general. Due to patient’s and medical specialist’s
overhead, such diaries are commonly practised only on limited
groups, for a limited time during clinical studies
Monitoring of patient’s physiological functions
Possible candidates for physiological function monitoring in
asthma include respiratory rate (both frequency and duration
of respiratory phases), hearth rate, SpO2, and detection of
wheezes. A concept of wearable body area network (BAN) for
pulmonary disease management, monitoring both physiological
and environmental parameters is presented in [17]. SpO2,
and physical activity (accelerometer) are monitored. System
also features acoustic body-worn sensors for monitoring of
breathing frequency, durations of inspirations/expirations and
hearth rate. With wheezing being most specific symptom for
asthma, systems for wheeze monitoring are put in the focus.
SIGNAL PROCESSING OF RESPIRATORY SOUNDS
Several reviews of the respiratory sound detection and
classification algorithms have been made. One of the most
recent and most comprehensive is the work of Reichert in
course of the ASAP project [37]. Also, Bahoura brought
the review of the respiratory sounds classification algorithms
from the pattern recognition point of view [38]. In his work,
several feature extraction techniques - Fourier transform, linear
predictive coding, wavelet transform and Mel-frequency
cepstral coefficients (MFCC) were combined with various
classification methods: vector quantization, Gaussian mixture
models (GMM) and artificial neural networks and the resulting
algorithms were evaluated. A combination of MFCC and
GMM yielded highest combination of sensitivity, specificity
and accuracy in classification of wheeze. Hadjileontiadis [39]
gives an overview on advanced algorithms including utilization
of higher order statistics like bicoherence index, and empirical
decomposition methods such as Huang-Hilbert transform.
However, information on the performance is not given.
CONCLUSION
Asthma has been identified as one of the most common
chronic disease with the rising prevalence. The key to successful
management of asthma is retaining it in the diagnosed state.
Traditional methods of home management by peakflowmetry
and paper-diaries rely on user participation and are failing to
provide objective information in times of asthmatic attacks.
An alternative approach of continuous monitoring of patient’s
environment and physiological functions has been reviewed.
Unobtrusiveness and automated asthma management procedures
exhibiting low interference with the daily routine of a
patient are the key for a long-term adherence.
We focus our research on optimal design of a minimally
intrusive body-worn wireless body sensor node for continuous
monitoring of respiratory function. The battery operated node
is working in conditions of limited energy and presence of
background noise. The node features on-board signal processing
and communicates with smartphone. Acquisition of
respiratory sounds and signal processing focused on detection
of wheezes and phases of respiratory cycle are the main
features.