An Inhaler Tracking System Based on Acoustic Analysis

Hardware and Software

Wenyang Xie, Patrick Gaydecki, Ann Caress

Research output: Contribution to journalArticle

Abstract

In treating asthma and chronic obstructive pulmonary disorder (COPD), acquisition of authentic and effective feedback from patients on regimen adherence is difficult. Face-to-face and oral reporting methods do not satisfy current intelligent medication best practices. This paper presents a system to track and analyze daily inhaler usage. A portable electronic device that attaches to the inhaler uses an accelerometer and capacitive sensors to detect users’ motion and an embedded digital microphone to capture sounds while the inhaler is in use. In terms of analysis, sound features are extracted, and breath phases are identified by employing a hidden Markov model with a Gaussian mixture model. A feature template is also constructed and used to search for and identify “canister pressed” events. The system provides objective feedback, quantifying asthma, and COPD patients’ adherence to medication regimens. Although interest in asthma adherence to medication regimens is growing, there is still a relative paucity of research and, indeed, compliance devices in this area; the tracking system can help doctors better understand the patient’s condition and choose an appropriated treatment plan. At the same time, patients can also improve their self-management by system feedback.
Original languageEnglish
Pages (from-to)4472-4480
Number of pages9
JournalIEEE Transactions on Instrumentation and Measurement
Volume68
Issue number11
Early online date14 Jan 2019
DOIs
Publication statusPublished - Nov 2019

Fingerprint

asthma
hardware
Acoustics
computer programs
Feedback
Hardware
acoustics
Acoustic waves
Capacitive sensors
disorders
Hidden Markov models
cans
Microphones
Accelerometers
accelerometers
microphones
acquisition
templates
sensors
electronics

Cite this

@article{9f92405df0734551a8e984df82dc68d3,
title = "An Inhaler Tracking System Based on Acoustic Analysis: Hardware and Software",
abstract = "In treating asthma and chronic obstructive pulmonary disorder (COPD), acquisition of authentic and effective feedback from patients on regimen adherence is difficult. Face-to-face and oral reporting methods do not satisfy current intelligent medication best practices. This paper presents a system to track and analyze daily inhaler usage. A portable electronic device that attaches to the inhaler uses an accelerometer and capacitive sensors to detect users’ motion and an embedded digital microphone to capture sounds while the inhaler is in use. In terms of analysis, sound features are extracted, and breath phases are identified by employing a hidden Markov model with a Gaussian mixture model. A feature template is also constructed and used to search for and identify “canister pressed” events. The system provides objective feedback, quantifying asthma, and COPD patients’ adherence to medication regimens. Although interest in asthma adherence to medication regimens is growing, there is still a relative paucity of research and, indeed, compliance devices in this area; the tracking system can help doctors better understand the patient’s condition and choose an appropriated treatment plan. At the same time, patients can also improve their self-management by system feedback.",
keywords = "Acoustic monitoring, Breath phase indentification, Inhaler techniques, Hidden Markov model-Gaussian mixture model (HMM-GMM), Random forest (RF), Support vector machine (SVM)",
author = "Wenyang Xie and Patrick Gaydecki and Ann Caress",
year = "2019",
month = "11",
doi = "10.1109/TIM.2018.2886978",
language = "English",
volume = "68",
pages = "4472--4480",
journal = "IEEE Transactions on Instrumentation and Measurement",
issn = "0018-9456",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

An Inhaler Tracking System Based on Acoustic Analysis : Hardware and Software. / Xie, Wenyang; Gaydecki, Patrick; Caress, Ann.

In: IEEE Transactions on Instrumentation and Measurement, Vol. 68, No. 11, 11.2019, p. 4472-4480.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An Inhaler Tracking System Based on Acoustic Analysis

T2 - Hardware and Software

AU - Xie, Wenyang

AU - Gaydecki, Patrick

AU - Caress, Ann

PY - 2019/11

Y1 - 2019/11

N2 - In treating asthma and chronic obstructive pulmonary disorder (COPD), acquisition of authentic and effective feedback from patients on regimen adherence is difficult. Face-to-face and oral reporting methods do not satisfy current intelligent medication best practices. This paper presents a system to track and analyze daily inhaler usage. A portable electronic device that attaches to the inhaler uses an accelerometer and capacitive sensors to detect users’ motion and an embedded digital microphone to capture sounds while the inhaler is in use. In terms of analysis, sound features are extracted, and breath phases are identified by employing a hidden Markov model with a Gaussian mixture model. A feature template is also constructed and used to search for and identify “canister pressed” events. The system provides objective feedback, quantifying asthma, and COPD patients’ adherence to medication regimens. Although interest in asthma adherence to medication regimens is growing, there is still a relative paucity of research and, indeed, compliance devices in this area; the tracking system can help doctors better understand the patient’s condition and choose an appropriated treatment plan. At the same time, patients can also improve their self-management by system feedback.

AB - In treating asthma and chronic obstructive pulmonary disorder (COPD), acquisition of authentic and effective feedback from patients on regimen adherence is difficult. Face-to-face and oral reporting methods do not satisfy current intelligent medication best practices. This paper presents a system to track and analyze daily inhaler usage. A portable electronic device that attaches to the inhaler uses an accelerometer and capacitive sensors to detect users’ motion and an embedded digital microphone to capture sounds while the inhaler is in use. In terms of analysis, sound features are extracted, and breath phases are identified by employing a hidden Markov model with a Gaussian mixture model. A feature template is also constructed and used to search for and identify “canister pressed” events. The system provides objective feedback, quantifying asthma, and COPD patients’ adherence to medication regimens. Although interest in asthma adherence to medication regimens is growing, there is still a relative paucity of research and, indeed, compliance devices in this area; the tracking system can help doctors better understand the patient’s condition and choose an appropriated treatment plan. At the same time, patients can also improve their self-management by system feedback.

KW - Acoustic monitoring

KW - Breath phase indentification

KW - Inhaler techniques

KW - Hidden Markov model-Gaussian mixture model (HMM-GMM)

KW - Random forest (RF)

KW - Support vector machine (SVM)

U2 - 10.1109/TIM.2018.2886978

DO - 10.1109/TIM.2018.2886978

M3 - Article

VL - 68

SP - 4472

EP - 4480

JO - IEEE Transactions on Instrumentation and Measurement

JF - IEEE Transactions on Instrumentation and Measurement

SN - 0018-9456

IS - 11

ER -