Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab

Reham Badawy, Yordan Raykov, Luc J.W. Evers, Bastiaan R. Bloem, Marjan J. Faber, Andong Zhan, Kasper Claes, Max A Little

Research output: Contribution to journalArticle

Abstract

The use of wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the accuracy achievable with such technology is highly reliant on separating the useful from irrelevant sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety of
practical challenges, such as recording unexpected user behaviors. These behaviors often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab and affect the accuracy of the subsequent data
analysis and scientific conclusions. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data that are sufficiently reliable for further analysis. Combining both parametric and nonparametric
signal processing and machine learning techniques, we demonstrate that across 100 subjects and 300 clinimetric tests from three different types of behavioral clinimetric protocols, the system shows an average segmentation accuracy of around 90%. By extracting reliable sensor data, it is possible to strip
the data of confounding factors in the environment that may threaten reproducibility and replicability.
Original languageEnglish
Article number1215
JournalSensors
Volume18
Issue number4
DOIs
Publication statusPublished - 16 Apr 2018

Fingerprint

quality control
Quality Control
Quality control
Technology
sensors
Sensors
Physiologic Monitoring
Patient monitoring
machine learning
Testing
learning
Learning systems
recording
probes
Processing
Data Accuracy
Machine Learning

Bibliographical note

© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).

Keywords

  • Bayesian nonparametrics
  • clinimetric tests
  • Parkinson’s disease
  • pattern recognition
  • quality control
  • remote monitoring
  • segmentation
  • wearable sensors

Cite this

Badawy, R., Raykov, Y., Evers, L. J. W., Bloem, B. R., Faber, M. J., Zhan, A., ... Little, M. A. (2018). Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab. Sensors, 18(4), [1215]. https://doi.org/10.3390/s18041215
Badawy, Reham ; Raykov, Yordan ; Evers, Luc J.W. ; Bloem, Bastiaan R. ; Faber, Marjan J. ; Zhan, Andong ; Claes, Kasper ; Little, Max A. / Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab. In: Sensors. 2018 ; Vol. 18, No. 4.
@article{6d90194a76a74fac8fe04467f5aa3999,
title = "Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab",
abstract = "The use of wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the accuracy achievable with such technology is highly reliant on separating the useful from irrelevant sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety ofpractical challenges, such as recording unexpected user behaviors. These behaviors often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab and affect the accuracy of the subsequent dataanalysis and scientific conclusions. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data that are sufficiently reliable for further analysis. Combining both parametric and nonparametricsignal processing and machine learning techniques, we demonstrate that across 100 subjects and 300 clinimetric tests from three different types of behavioral clinimetric protocols, the system shows an average segmentation accuracy of around 90{\%}. By extracting reliable sensor data, it is possible to stripthe data of confounding factors in the environment that may threaten reproducibility and replicability.",
keywords = "Bayesian nonparametrics, clinimetric tests, Parkinson’s disease, pattern recognition, quality control, remote monitoring, segmentation, wearable sensors",
author = "Reham Badawy and Yordan Raykov and Evers, {Luc J.W.} and Bloem, {Bastiaan R.} and Faber, {Marjan J.} and Andong Zhan and Kasper Claes and Little, {Max A}",
note = "{\circledC} 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).",
year = "2018",
month = "4",
day = "16",
doi = "10.3390/s18041215",
language = "English",
volume = "18",
journal = "Sensors",
issn = "1424-8239",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

Badawy, R, Raykov, Y, Evers, LJW, Bloem, BR, Faber, MJ, Zhan, A, Claes, K & Little, MA 2018, 'Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab', Sensors, vol. 18, no. 4, 1215. https://doi.org/10.3390/s18041215

Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab. / Badawy, Reham; Raykov, Yordan; Evers, Luc J.W.; Bloem, Bastiaan R.; Faber, Marjan J.; Zhan, Andong; Claes, Kasper; Little, Max A.

In: Sensors, Vol. 18, No. 4, 1215, 16.04.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated Quality Control for Sensor Based Symptom Measurement Performed Outside the Lab

AU - Badawy, Reham

AU - Raykov, Yordan

AU - Evers, Luc J.W.

AU - Bloem, Bastiaan R.

AU - Faber, Marjan J.

AU - Zhan, Andong

AU - Claes, Kasper

AU - Little, Max A

N1 - © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

PY - 2018/4/16

Y1 - 2018/4/16

N2 - The use of wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the accuracy achievable with such technology is highly reliant on separating the useful from irrelevant sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety ofpractical challenges, such as recording unexpected user behaviors. These behaviors often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab and affect the accuracy of the subsequent dataanalysis and scientific conclusions. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data that are sufficiently reliable for further analysis. Combining both parametric and nonparametricsignal processing and machine learning techniques, we demonstrate that across 100 subjects and 300 clinimetric tests from three different types of behavioral clinimetric protocols, the system shows an average segmentation accuracy of around 90%. By extracting reliable sensor data, it is possible to stripthe data of confounding factors in the environment that may threaten reproducibility and replicability.

AB - The use of wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the accuracy achievable with such technology is highly reliant on separating the useful from irrelevant sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety ofpractical challenges, such as recording unexpected user behaviors. These behaviors often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab and affect the accuracy of the subsequent dataanalysis and scientific conclusions. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data that are sufficiently reliable for further analysis. Combining both parametric and nonparametricsignal processing and machine learning techniques, we demonstrate that across 100 subjects and 300 clinimetric tests from three different types of behavioral clinimetric protocols, the system shows an average segmentation accuracy of around 90%. By extracting reliable sensor data, it is possible to stripthe data of confounding factors in the environment that may threaten reproducibility and replicability.

KW - Bayesian nonparametrics

KW - clinimetric tests

KW - Parkinson’s disease

KW - pattern recognition

KW - quality control

KW - remote monitoring

KW - segmentation

KW - wearable sensors

UR - http://www.mdpi.com/1424-8220/18/4/1215

U2 - 10.3390/s18041215

DO - 10.3390/s18041215

M3 - Article

VL - 18

JO - Sensors

JF - Sensors

SN - 1424-8239

IS - 4

M1 - 1215

ER -