Reduction of false arrhythmia alarms using signal selection and machine learning

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

11 Citaties (Scopus)

Uittreksel

In this paper, we propose an algorithm that classifies whether a generated cardiac arrhythmia alarm is true or false. The large number of false alarms in intensive care is a severe issue. The noise peaks caused by alarms can be high and in a noisy environment nurses can experience stress and fatigue. In addition, patient safety is compromised because reaction time of the caregivers to true alarms is reduced.

The data for the algorithm development consisted of records of electrocardiogram (ECG), arterial blood pressure, and photoplethysmogram signals in which an alarm for either asystole, extreme bradycardia, extreme tachycardia, ventricular fibrillation or flutter, or ventricular tachycardia occurs. First, heart beats are extracted from every signal. Next, the algorithm selects the most reliable signal pair from the available signals by comparing how well the detected beats match between different signals based on ${{\text{F}}_{1}}$ -score and selecting the best match. From the selected signal pair, arrhythmia specific features, such as heart rate features and signal purity index are computed for the alarm classification. The classification is performed with five separate Random Forest models. In addition, information on the local noise level of the selected ECG lead is added to the classification. The algorithm was trained and evaluated with the PhysioNet/Computing in Cardiology Challenge 2015 data set. In the test set the overall true positive rates were 93 and 95% and true negative rates 80 and 83%, respectively for events with no information and events with information after the alarm. The overall challenge scores were 77.39 and 81.58.
TaalEngels
Pagina's1204-1216
TijdschriftPhysiological Measurement
Volume37
Nummer van het tijdschrift8
DOI's
StatusGepubliceerd - 2016

Vingerafdruk

Learning systems
Cardiac Arrhythmias
Electrocardiography
Noise
Ventricular Flutter
Cardiology
Blood pressure
Ventricular Fibrillation
Critical Care
Patient Safety
Bradycardia
Ventricular Tachycardia
Heart Arrest
Tachycardia
Caregivers
Fatigue
Arterial Pressure
Lead
Heart Rate
Nurses

Citeer dit

@article{e699bae6b56a4f01a45a4ca6db7d1987,
title = "Reduction of false arrhythmia alarms using signal selection and machine learning",
abstract = "In this paper, we propose an algorithm that classifies whether a generated cardiac arrhythmia alarm is true or false. The large number of false alarms in intensive care is a severe issue. The noise peaks caused by alarms can be high and in a noisy environment nurses can experience stress and fatigue. In addition, patient safety is compromised because reaction time of the caregivers to true alarms is reduced.The data for the algorithm development consisted of records of electrocardiogram (ECG), arterial blood pressure, and photoplethysmogram signals in which an alarm for either asystole, extreme bradycardia, extreme tachycardia, ventricular fibrillation or flutter, or ventricular tachycardia occurs. First, heart beats are extracted from every signal. Next, the algorithm selects the most reliable signal pair from the available signals by comparing how well the detected beats match between different signals based on ${{\text{F}}_{1}}$ -score and selecting the best match. From the selected signal pair, arrhythmia specific features, such as heart rate features and signal purity index are computed for the alarm classification. The classification is performed with five separate Random Forest models. In addition, information on the local noise level of the selected ECG lead is added to the classification. The algorithm was trained and evaluated with the PhysioNet/Computing in Cardiology Challenge 2015 data set. In the test set the overall true positive rates were 93 and 95{\%} and true negative rates 80 and 83{\%}, respectively for events with no information and events with information after the alarm. The overall challenge scores were 77.39 and 81.58.",
author = "L.M. Eerik{\"a}inen and J. Vanschoren and M.J. Rooijakkers and R. Vullings and R.M. Aarts",
year = "2016",
doi = "10.1088/0967-3334/37/8/1204",
language = "English",
volume = "37",
pages = "1204--1216",
journal = "Physiological Measurement",
issn = "0967-3334",
publisher = "Institute of Physics",
number = "8",

}

Reduction of false arrhythmia alarms using signal selection and machine learning. / Eerikäinen, L.M.; Vanschoren, J.; Rooijakkers, M.J.; Vullings, R.; Aarts, R.M.

In: Physiological Measurement, Vol. 37, Nr. 8, 2016, blz. 1204-1216.

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

TY - JOUR

T1 - Reduction of false arrhythmia alarms using signal selection and machine learning

AU - Eerikäinen,L.M.

AU - Vanschoren,J.

AU - Rooijakkers,M.J.

AU - Vullings,R.

AU - Aarts,R.M.

PY - 2016

Y1 - 2016

N2 - In this paper, we propose an algorithm that classifies whether a generated cardiac arrhythmia alarm is true or false. The large number of false alarms in intensive care is a severe issue. The noise peaks caused by alarms can be high and in a noisy environment nurses can experience stress and fatigue. In addition, patient safety is compromised because reaction time of the caregivers to true alarms is reduced.The data for the algorithm development consisted of records of electrocardiogram (ECG), arterial blood pressure, and photoplethysmogram signals in which an alarm for either asystole, extreme bradycardia, extreme tachycardia, ventricular fibrillation or flutter, or ventricular tachycardia occurs. First, heart beats are extracted from every signal. Next, the algorithm selects the most reliable signal pair from the available signals by comparing how well the detected beats match between different signals based on ${{\text{F}}_{1}}$ -score and selecting the best match. From the selected signal pair, arrhythmia specific features, such as heart rate features and signal purity index are computed for the alarm classification. The classification is performed with five separate Random Forest models. In addition, information on the local noise level of the selected ECG lead is added to the classification. The algorithm was trained and evaluated with the PhysioNet/Computing in Cardiology Challenge 2015 data set. In the test set the overall true positive rates were 93 and 95% and true negative rates 80 and 83%, respectively for events with no information and events with information after the alarm. The overall challenge scores were 77.39 and 81.58.

AB - In this paper, we propose an algorithm that classifies whether a generated cardiac arrhythmia alarm is true or false. The large number of false alarms in intensive care is a severe issue. The noise peaks caused by alarms can be high and in a noisy environment nurses can experience stress and fatigue. In addition, patient safety is compromised because reaction time of the caregivers to true alarms is reduced.The data for the algorithm development consisted of records of electrocardiogram (ECG), arterial blood pressure, and photoplethysmogram signals in which an alarm for either asystole, extreme bradycardia, extreme tachycardia, ventricular fibrillation or flutter, or ventricular tachycardia occurs. First, heart beats are extracted from every signal. Next, the algorithm selects the most reliable signal pair from the available signals by comparing how well the detected beats match between different signals based on ${{\text{F}}_{1}}$ -score and selecting the best match. From the selected signal pair, arrhythmia specific features, such as heart rate features and signal purity index are computed for the alarm classification. The classification is performed with five separate Random Forest models. In addition, information on the local noise level of the selected ECG lead is added to the classification. The algorithm was trained and evaluated with the PhysioNet/Computing in Cardiology Challenge 2015 data set. In the test set the overall true positive rates were 93 and 95% and true negative rates 80 and 83%, respectively for events with no information and events with information after the alarm. The overall challenge scores were 77.39 and 81.58.

U2 - 10.1088/0967-3334/37/8/1204

DO - 10.1088/0967-3334/37/8/1204

M3 - Article

VL - 37

SP - 1204

EP - 1216

JO - Physiological Measurement

T2 - Physiological Measurement

JF - Physiological Measurement

SN - 0967-3334

IS - 8

ER -