A ballistographic approach for continuous and non-obtrusive monitoring of movement in neonates

Rohan Joshi, Bart Bierling, Xi Long, Janna Weijers, Loe Feijs, Carola van Pul, Peter Andriessen

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Continuously monitoring body movement in preterm infants can have important clinical applications since changes in movement-patterns can be a significant marker for clinical deteriorations including the onset of sepsis, seizures, and apneas. This paper proposes a system and method to monitor body movement of preterm infants in a clinical environment using ballistography. The ballistographic signal (BSG) is acquired using a thin, film-like sensor that is placed underneath an infant. Manual annotations based on video-recordings served as a reference standard for identifying movement. We investigate the performance of multiple features, constructed from the BSG waveform, to discriminate movement from no movement based on data acquired from 10 preterm infants. Since routine cardiorespiratory monitoring is prone to movement artifacts, we also compare the application of these features on the simultaneously acquired cardiorespiratory waveforms, i.e., the electrocardiogram, the chest impedance, and the photoplethysmogram. BSG-based-features consistently outperformed those based on the routinely acquired cardiorespiratory waveforms. The best performing BSG-based feature – the signal instability index – had a mean (standard deviation) effect size of 0.90 (0.06), as measured by the area under the receiver operating curve. The proposed system for monitoring body movement is robust to noise, non-obtrusive and has high performance in clinical settings.

LanguageEnglish
Article number 2700809
Pages10
JournalIEEE Journal of Translational Engineering in Health and Medicine
Volume6
DOIs
StatePublished - 12 Oct 2018

Fingerprint

Monitoring
Video recording
Electrocardiography
Deterioration
Thin films
Sensors

Keywords

  • Ballistography
  • Biomedical monitoring
  • body movement
  • Heart rate
  • Monitoring
  • neonates
  • patient monitoring
  • Pediatrics
  • Signal to noise ratio
  • Standards
  • statistical signal processing
  • Wearable sensors

Cite this

@article{0b6e7ff7efa549d499e58ee5e6a7c66a,
title = "A ballistographic approach for continuous and non-obtrusive monitoring of movement in neonates",
abstract = "Continuously monitoring body movement in preterm infants can have important clinical applications since changes in movement-patterns can be a significant marker for clinical deteriorations including the onset of sepsis, seizures, and apneas. This paper proposes a system and method to monitor body movement of preterm infants in a clinical environment using ballistography. The ballistographic signal (BSG) is acquired using a thin, film-like sensor that is placed underneath an infant. Manual annotations based on video-recordings served as a reference standard for identifying movement. We investigate the performance of multiple features, constructed from the BSG waveform, to discriminate movement from no movement based on data acquired from 10 preterm infants. Since routine cardiorespiratory monitoring is prone to movement artifacts, we also compare the application of these features on the simultaneously acquired cardiorespiratory waveforms, i.e., the electrocardiogram, the chest impedance, and the photoplethysmogram. BSG-based-features consistently outperformed those based on the routinely acquired cardiorespiratory waveforms. The best performing BSG-based feature – the signal instability index – had a mean (standard deviation) effect size of 0.90 (0.06), as measured by the area under the receiver operating curve. The proposed system for monitoring body movement is robust to noise, non-obtrusive and has high performance in clinical settings.",
keywords = "Ballistography, Biomedical monitoring, body movement, Heart rate, Monitoring, neonates, patient monitoring, Pediatrics, Signal to noise ratio, Standards, statistical signal processing, Wearable sensors",
author = "Rohan Joshi and Bart Bierling and Xi Long and Janna Weijers and Loe Feijs and {van Pul}, Carola and Peter Andriessen",
year = "2018",
month = "10",
day = "12",
doi = "10.1109/JTEHM.2018.2875703",
language = "English",
volume = "6",
pages = "10",
journal = "IEEE Journal of Translational Engineering in Health and Medicine",
issn = "2168-2372",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

A ballistographic approach for continuous and non-obtrusive monitoring of movement in neonates. / Joshi, Rohan; Bierling, Bart; Long, Xi; Weijers, Janna; Feijs, Loe; van Pul, Carola; Andriessen, Peter.

In: IEEE Journal of Translational Engineering in Health and Medicine, Vol. 6, 2700809, 12.10.2018, p. 10.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A ballistographic approach for continuous and non-obtrusive monitoring of movement in neonates

AU - Joshi,Rohan

AU - Bierling,Bart

AU - Long,Xi

AU - Weijers,Janna

AU - Feijs,Loe

AU - van Pul,Carola

AU - Andriessen,Peter

PY - 2018/10/12

Y1 - 2018/10/12

N2 - Continuously monitoring body movement in preterm infants can have important clinical applications since changes in movement-patterns can be a significant marker for clinical deteriorations including the onset of sepsis, seizures, and apneas. This paper proposes a system and method to monitor body movement of preterm infants in a clinical environment using ballistography. The ballistographic signal (BSG) is acquired using a thin, film-like sensor that is placed underneath an infant. Manual annotations based on video-recordings served as a reference standard for identifying movement. We investigate the performance of multiple features, constructed from the BSG waveform, to discriminate movement from no movement based on data acquired from 10 preterm infants. Since routine cardiorespiratory monitoring is prone to movement artifacts, we also compare the application of these features on the simultaneously acquired cardiorespiratory waveforms, i.e., the electrocardiogram, the chest impedance, and the photoplethysmogram. BSG-based-features consistently outperformed those based on the routinely acquired cardiorespiratory waveforms. The best performing BSG-based feature – the signal instability index – had a mean (standard deviation) effect size of 0.90 (0.06), as measured by the area under the receiver operating curve. The proposed system for monitoring body movement is robust to noise, non-obtrusive and has high performance in clinical settings.

AB - Continuously monitoring body movement in preterm infants can have important clinical applications since changes in movement-patterns can be a significant marker for clinical deteriorations including the onset of sepsis, seizures, and apneas. This paper proposes a system and method to monitor body movement of preterm infants in a clinical environment using ballistography. The ballistographic signal (BSG) is acquired using a thin, film-like sensor that is placed underneath an infant. Manual annotations based on video-recordings served as a reference standard for identifying movement. We investigate the performance of multiple features, constructed from the BSG waveform, to discriminate movement from no movement based on data acquired from 10 preterm infants. Since routine cardiorespiratory monitoring is prone to movement artifacts, we also compare the application of these features on the simultaneously acquired cardiorespiratory waveforms, i.e., the electrocardiogram, the chest impedance, and the photoplethysmogram. BSG-based-features consistently outperformed those based on the routinely acquired cardiorespiratory waveforms. The best performing BSG-based feature – the signal instability index – had a mean (standard deviation) effect size of 0.90 (0.06), as measured by the area under the receiver operating curve. The proposed system for monitoring body movement is robust to noise, non-obtrusive and has high performance in clinical settings.

KW - Ballistography

KW - Biomedical monitoring

KW - body movement

KW - Heart rate

KW - Monitoring

KW - neonates

KW - patient monitoring

KW - Pediatrics

KW - Signal to noise ratio

KW - Standards

KW - statistical signal processing

KW - Wearable sensors

UR - http://www.scopus.com/inward/record.url?scp=85055043728&partnerID=8YFLogxK

U2 - 10.1109/JTEHM.2018.2875703

DO - 10.1109/JTEHM.2018.2875703

M3 - Article

VL - 6

SP - 10

JO - IEEE Journal of Translational Engineering in Health and Medicine

T2 - IEEE Journal of Translational Engineering in Health and Medicine

JF - IEEE Journal of Translational Engineering in Health and Medicine

SN - 2168-2372

M1 - 2700809

ER -