Smartphone Derived Movement Profiles to Detect Changes in Health Status in COPD Patients - A Preliminary Investigation

Daniel Kelly, Donnelly Seamas, Caulfield Brian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Over 3.2 million people in the UK alone have the lung disease Chronic Obstructive Pulmonary Disease. Identifying when COPD patients are at risk of an exacerbation is a major problem and there is a need for smart solutions that provide us with a means of tracking patient health status. Smart-phone sensor technology provides us with an opportunity to automatically monitor patients. With sensors providing the ability to measure aspects of a patients daily life, such a motion, methods to interpret these signals and infer health related information are needed. In this work we aim to investigate the feasibility of utilizing motion sensors, built within smart-phones, to measure patient movement and to infer the health related information about the patient. We perform experiments, based on 7 COPD patients using data collected over a 12 week period for each patient, and identify a measure to distinguish between periods when a patient feels well Vs periods when a patient feels unwell.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages4
Publication statusPublished - 25 Aug 2015
EventIEEE Conference of the Engineering in Medicine and Biology Society - Milan, Italy
Duration: 25 Aug 2015 → …

Conference

ConferenceIEEE Conference of the Engineering in Medicine and Biology Society
Period25/08/15 → …

Fingerprint

Chronic Obstructive Pulmonary Disease
Health Status
Patient Identification Systems
Smartphone
Health
Lung Diseases
Technology

Keywords

  • Smartphone Sensor
  • Chronic Obstructive Pulmonary Disease

Cite this

@inproceedings{ffffd511732d4ec4af0983900feea554,
title = "Smartphone Derived Movement Profiles to Detect Changes in Health Status in COPD Patients - A Preliminary Investigation",
abstract = "Over 3.2 million people in the UK alone have the lung disease Chronic Obstructive Pulmonary Disease. Identifying when COPD patients are at risk of an exacerbation is a major problem and there is a need for smart solutions that provide us with a means of tracking patient health status. Smart-phone sensor technology provides us with an opportunity to automatically monitor patients. With sensors providing the ability to measure aspects of a patients daily life, such a motion, methods to interpret these signals and infer health related information are needed. In this work we aim to investigate the feasibility of utilizing motion sensors, built within smart-phones, to measure patient movement and to infer the health related information about the patient. We perform experiments, based on 7 COPD patients using data collected over a 12 week period for each patient, and identify a measure to distinguish between periods when a patient feels well Vs periods when a patient feels unwell.",
keywords = "Smartphone Sensor, Chronic Obstructive Pulmonary Disease",
author = "Daniel Kelly and Donnelly Seamas and Caulfield Brian",
year = "2015",
month = "8",
day = "25",
language = "English",
booktitle = "Unknown Host Publication",

}

Kelly, D, Seamas, D & Brian, C 2015, Smartphone Derived Movement Profiles to Detect Changes in Health Status in COPD Patients - A Preliminary Investigation. in Unknown Host Publication. IEEE Conference of the Engineering in Medicine and Biology Society, 25/08/15.

Smartphone Derived Movement Profiles to Detect Changes in Health Status in COPD Patients - A Preliminary Investigation. / Kelly, Daniel; Seamas, Donnelly; Brian, Caulfield.

Unknown Host Publication. 2015.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Smartphone Derived Movement Profiles to Detect Changes in Health Status in COPD Patients - A Preliminary Investigation

AU - Kelly, Daniel

AU - Seamas, Donnelly

AU - Brian, Caulfield

PY - 2015/8/25

Y1 - 2015/8/25

N2 - Over 3.2 million people in the UK alone have the lung disease Chronic Obstructive Pulmonary Disease. Identifying when COPD patients are at risk of an exacerbation is a major problem and there is a need for smart solutions that provide us with a means of tracking patient health status. Smart-phone sensor technology provides us with an opportunity to automatically monitor patients. With sensors providing the ability to measure aspects of a patients daily life, such a motion, methods to interpret these signals and infer health related information are needed. In this work we aim to investigate the feasibility of utilizing motion sensors, built within smart-phones, to measure patient movement and to infer the health related information about the patient. We perform experiments, based on 7 COPD patients using data collected over a 12 week period for each patient, and identify a measure to distinguish between periods when a patient feels well Vs periods when a patient feels unwell.

AB - Over 3.2 million people in the UK alone have the lung disease Chronic Obstructive Pulmonary Disease. Identifying when COPD patients are at risk of an exacerbation is a major problem and there is a need for smart solutions that provide us with a means of tracking patient health status. Smart-phone sensor technology provides us with an opportunity to automatically monitor patients. With sensors providing the ability to measure aspects of a patients daily life, such a motion, methods to interpret these signals and infer health related information are needed. In this work we aim to investigate the feasibility of utilizing motion sensors, built within smart-phones, to measure patient movement and to infer the health related information about the patient. We perform experiments, based on 7 COPD patients using data collected over a 12 week period for each patient, and identify a measure to distinguish between periods when a patient feels well Vs periods when a patient feels unwell.

KW - Smartphone Sensor

KW - Chronic Obstructive Pulmonary Disease

M3 - Conference contribution

BT - Unknown Host Publication

ER -