Automatic identification of stimulation activities during newborn resuscitation using ECG and accelerometer signals

Urdal, Jarle; Engan, Kjersti; Eftestøl, Trygve; Naranjo, Valery; Haug, Ingunn Anda; Yeconia, Anita; Kidanto, Hussein; Ersdal, Hege

doi:10.1016/j.cmpb.2020.105445

Cited by 7 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the ECG sensor in the LNRM is susceptible to noise from the power grid, a 50Hz notch filter is applied to the signal prior to extracting any of the features from the ECG. An overview of all features used can be found in Urdal et al [91].…”

Section: Methodsmentioning

confidence: 99%

Signal Processing for Newborn Survival from labour to resuscitation

Urdal¹

2020

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Signal Processing for Newborn Survival from labour to resuscitation

Urdal¹

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The timeline visualization method provides a visual representation of the resuscitation activities performed on a newborn over time [2]. Resuscitation episodes have different duration.…”

Section: Constructing a Resuscitation Activity Timeline Using The Sus...mentioning

confidence: 99%

“…Deprivation of oxygen during and after birth leads to birth asphyxia, a condition recognized as a prominent factor in newborn mortality, as well as in the occurrence of cerebral palsy, learning disabilities, and other developmental delays [1,2]. To minimize the risk and effect of birth asphyxia, it is important to resuscitate a non-breathing newborn as quickly and efficient as possible.…”

mentioning

confidence: 99%

“…The main therapeutic measures during newborn resuscitation include ventilation, stimulation, and suction [8,9]. Other activities that occur less frequent and/or has less direct therapeutic effect include chest compression, drying, warming, epinefrine injections and others [2,10].…”

mentioning

confidence: 99%

“…The goal of NewbornTime is to produce the timeline automatically, but as a step on the way resucitation timelines can be produced by clinicians manually observing and delineating the recorded videos retrospectively [2]. This gives high-quality labelled data to use when learning AI systems, but it also gives timeline descriptions of the newborn resuscitations that we can start to analyze.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Analysis and Knowledge Extraction of Newborn Resuscitation Activities from Annotation Files

Abukmeil,

Meinich-Bache,

Eftestøl

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Deprivation of oxygen in a newbornduring and after birth leads to birth asphyxia, which is considered one of the leading causes of death in the neonatal period. Adequate resuscitation activities are performed immediately after birth to save the majority of newborns. The primary resuscitation activities include ventilation, stimulation, drying, suction, and chest compression. While resuscitation guidelines exist, little research has been conducted on measured resuscitation episodes. Modeling the executed resuscitation activities to generate temporal data and extract knowledge can provide unique insights into dominant resuscitation activities. It also aids in constructing a resuscitation timeline to visually represent and describe the actions performed on a newborn.In this paper, we propose a method for generating and encoding temporal resuscitation data, enabling the description and visualization of the resuscitation timeline. We utilize neighborhood component analysis (NCA) to cluster the generated data based on the presence of ventilation and the outcome of the newborn. Additionally, we employ an autoencoder (AE) model to enhance clustering performance by visualizing its latent space.Our proposed method demonstrates high-quality visual clustering results on two different datasets. It provides insights into the intricate structure of the generated resuscitation data by grouping similar unlabeled resuscitation episodes into coherent clusters.

show abstract