1
|
Bollepalli SC, Sevakula RK, Au-Yeung WTM, Kassab MB, Merchant FM, Bazoukis G, Boyer R, Isselbacher EM, Armoundas AA. Real-Time Arrhythmia Detection Using Hybrid Convolutional Neural Networks. J Am Heart Assoc 2021; 10:e023222. [PMID: 34854319 PMCID: PMC9075394 DOI: 10.1161/jaha.121.023222] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Background Accurate detection of arrhythmic events in the intensive care units (ICU) is of paramount significance in providing timely care. However, traditional ICU monitors generate a high rate of false alarms causing alarm fatigue. In this work, we develop an algorithm to improve life threatening arrhythmia detection in the ICUs using a deep learning approach. Methods and Results This study involves a total of 953 independent life-threatening arrhythmia alarms generated from the ICU bedside monitors of 410 patients. Specifically, we used the ECG (4 channels), arterial blood pressure, and photoplethysmograph signals to accurately detect the onset and offset of various arrhythmias, without prior knowledge of the alarm type. We used a hybrid convolutional neural network based classifier that fuses traditional handcrafted features with features automatically learned using convolutional neural networks. Further, the proposed architecture remains flexible to be adapted to various arrhythmic conditions as well as multiple physiological signals. Our hybrid- convolutional neural network approach achieved superior performance compared with methods which only used convolutional neural network. We evaluated our algorithm using 5-fold cross-validation for 5 times and obtained an accuracy of 87.5%±0.5%, and a score of 81%±0.9%. Independent evaluation of our algorithm on the publicly available PhysioNet 2015 Challenge database resulted in overall classification accuracy and score of 93.9% and 84.3%, respectively, indicating its efficacy and generalizability. Conclusions Our method accurately detects multiple arrhythmic conditions. Suitable translation of our algorithm may significantly improve the quality of care in ICUs by reducing the burden of false alarms.
Collapse
Affiliation(s)
| | - Rahul K Sevakula
- Cardiovascular Research Center Massachusetts General Hospital Boston MA
| | | | - Mohamad B Kassab
- Cardiovascular Research Center Massachusetts General Hospital Boston MA
| | | | - George Bazoukis
- Second Department of Cardiology Evangelismos General Hospital of Athens Athens Greece
| | - Richard Boyer
- Anesthesia Department Massachusetts General Hospital Boston MA
| | | | - Antonis A Armoundas
- Cardiovascular Research Center Massachusetts General Hospital Boston MA.,Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge MA
| |
Collapse
|
2
|
Convolutional squeeze-and-excitation network for ECG arrhythmia detection. Artif Intell Med 2021; 121:102181. [PMID: 34763803 DOI: 10.1016/j.artmed.2021.102181] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2020] [Revised: 09/22/2021] [Accepted: 09/22/2021] [Indexed: 11/21/2022]
Abstract
Automatic detection of arrhythmia through an electrocardiogram (ECG) is of great significance for the prevention and treatment of cardiovascular diseases. In Convolutional neural network, the ECG signal is converted into multiple feature channels with equal weights through the convolution operation. Multiple feature channels can provide richer and more comprehensive information, but also contain redundant information, which will affect the diagnosis of arrhythmia, so feature channels that contain arrhythmia information should be paid attention to and given larger weight. In this paper, we introduced the Squeeze-and-Excitation (SE) block for the first time for the automatic detection of multiple types of arrhythmias with ECG. Our algorithm combines the residual convolutional module and the SE block to extract features from the original ECG signal. The SE block adaptively enhances the discriminative features and suppresses noise by explicitly modeling the interdependence between the channels, which can adaptively integrate information from different feature channels of ECG. The one-dimensional convolution operation over the time dimension is used to extract temporal information and the shortcut connection of the Se-Residual convolutional module in the proposed model makes the network easier to optimize. Thanks to the powerful feature extraction capabilities of the network, which can effectively extract discriminative arrhythmia features in multiple feature channels, so that no extra data preprocessing including denoising in other methods are need for our framework. It thus improves the working efficiency and keeps the collected biological information without loss. Experiments conducted with the 12-lead ECG dataset of the China Physiological Signal Challenge (CPSC) 2018 and the dataset of PhysioNet/Computing in Cardiology (CinC) Challenge 2017. The experiment results show that our model gains great performance and has great potential in clinical.
Collapse
|
3
|
Eerikainen LM, Bonomi AG, Schipper F, Dekker LRC, de Morree HM, Vullings R, Aarts RM. Detecting Atrial Fibrillation and Atrial Flutter in Daily Life Using Photoplethysmography Data. IEEE J Biomed Health Inform 2019; 24:1610-1618. [PMID: 31689222 DOI: 10.1109/jbhi.2019.2950574] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
OBJECTIVE Photoplethysmography (PPG) enables unobtrusive heart rate monitoring, which can be used in wrist-worn applications. Its potential for detecting atrial fibrillation (AF) has been recently presented. Besides AF, another cardiac arrhythmia increasing stroke risk and requiring treatment is atrial flutter (AFL). Currently, the knowledge about AFL detection with PPG is limited. The objective of our study was to develop a model that classifies AF, AFL, and sinus rhythm with or without premature beats from PPG and acceleration data measured at the wrist in daily life. METHODS A dataset of 40 patients was collected by measuring PPG and accelerometer data, as well as electrocardiogram as a reference, during 24-hour monitoring. The dataset was split into 75%-25% for training and testing a Random Forest (RF) model, which combines features from PPG, inter-pulse intervals (IPI), and accelerometer data, to classify AF, AFL, and other rhythms. The performance was compared to an AF detection algorithm combining traditional IPI features for determining the robustness of the accuracy in presence of AFL. RESULTS The RF model classified AF/AFL/other with sensitivity and specificity of 97.6/84.5/98.1% and 98.2/99.7/92.8%, respectively. The results with the IPI-based AF classifier showed that the majority of false detections were caused by AFL. CONCLUSION The PPG signal contains information to classify AFL in the presence of AF, sinus rhythm, or sinus rhythm with premature contractions. SIGNIFICANCE PPG could indicate presence of AFL, not only AF.
Collapse
|
4
|
Boriani G, Fauchier L, Aguinaga L, Beattie JM, Blomstrom Lundqvist C, Cohen A, Dan GA, Genovesi S, Israel C, Joung B, Kalarus Z, Lampert R, Malavasi VL, Mansourati J, Mont L, Potpara T, Thornton A, Lip GYH, Gorenek B, Marin F, Dagres N, Ozcan EE, Lenarczyk R, Crijns HJ, Guo Y, Proietti M, Sticherling C, Huang D, Daubert JP, Pokorney SD, Cabrera Ortega M, Chin A. European Heart Rhythm Association (EHRA) consensus document on management of arrhythmias and cardiac electronic devices in the critically ill and post-surgery patient, endorsed by Heart Rhythm Society (HRS), Asia Pacific Heart Rhythm Society (APHRS), Cardiac Arrhythmia Society of Southern Africa (CASSA), and Latin American Heart Rhythm Society (LAHRS). Europace 2018; 21:7-8. [DOI: 10.1093/europace/euy110] [Citation(s) in RCA: 61] [Impact Index Per Article: 10.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2018] [Accepted: 04/26/2018] [Indexed: 02/05/2023] Open
Affiliation(s)
- Giuseppe Boriani
- Cardiology Division, Department of Biomedical, Metabolic and Neural Sciences, University of Modena and Reggio Emilia, Policlinico di Modena, Modena, Italy
| | - Laurent Fauchier
- Centre Hospitalier Universitaire Trousseau et Université François Rabelais, Tours, France
| | | | - James M Beattie
- Cicely Saunders Institute, King’s College London, London, UK
| | | | | | - Gheorghe-Andrei Dan
- Cardiology Department, University of Medicine and Pharmacy “Carol Davila”, Colentina University Hospital, Bucharest, Romania
| | - Simonetta Genovesi
- Department of Medicine and Surgery, University of Milano-Bicocca, Milano and Nephrology Unit, San Gerardo Hospital, Monza, Italy
| | - Carsten Israel
- Evangelisches Krankenhaus Bielefeld GmbH, Bielefeld, Germany
| | - Boyoung Joung
- Cardiology Division, Department of Internal Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Zbigniew Kalarus
- SMDZ in Zabrze, Medical University of Silesia, Katowice; Department of Cardiology, Silesian Center for Heart Diseases, Zabrze, Poland
| | | | - Vincenzo L Malavasi
- Cardiology Division, Department of Nephrologic, Cardiac, Vascular Diseases, Azienda ospedaliero-Universitaria di Modena, Modena, Italy
| | - Jacques Mansourati
- University Hospital of Brest and University of Western Brittany, Brest, France
| | - Lluis Mont
- Arrhythmia Section, Cardiovascular Clínical Institute, Hospital Clinic, Universitat Barcelona, Barcelona, Spain
| | - Tatjana Potpara
- School of Medicine, Belgrade University, Belgrade, Serbia
- Cardiology Clinic, Clinical Centre of Serbia, Belgrade, Serbia
| | | | - Gregory Y H Lip
- Institute of Cardiovascular Sciences, University of Birmingham, UK
- Aalborg Thrombosis Research Unit, Department of Clinical Medicine, Aalborg University, Aalborg, Denmark
| | | | | | | | | | - Radosław Lenarczyk
- Department of Cardiology, Congenital Heart Disease and Electrotherapy, Silesian Center for Heart Diseases, Zabrze, Poland
| | - Harry J Crijns
- Cardiology Maastricht UMC+ and Cardiovascular Research Institute Maastricht, Netherlands
| | - Yutao Guo
- Chinese PLA General Hospital, Beijing, People’s Republic of China
| | - Marco Proietti
- Institute of Cardiovascular Sciences, University of Birmingham, UK
- Department of Internal Medicine and Medical Specialties, Sapienza-University of Rome, Rome, Italy
| | | | - Dejia Huang
- Cardiology Division, Department of Medicine, West China Hospital, Sichuan University, Chengdu, People's Republic of China
| | | | - Sean D Pokorney
- Electrophysiology Section, Division of Cardiology, Duke University, Durham, NC, USA
| | - Michel Cabrera Ortega
- Department of Arrhythmia and Cardiac Pacing, Cardiocentro Pediatrico William Soler, Boyeros, La Havana Cuba
| | - Ashley Chin
- Department of Medicine, Groote Schuur Hospital, University of Cape Town, South Africa
| | | |
Collapse
|
5
|
Cowie B, Baker L, Shoghi B, Worner M, Scott D. Electrocardiogram failure in the operating room - bench testing to prevent bed-side disaster. Anaesthesia 2018. [PMID: 29520908 DOI: 10.1111/anae.14250] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
Electrocardiogram (ECG) false alarms are common in electrically-hostile peri-operative environments. Newer integrated monitoring, with sophisticated hardware and software, has the potential to minimise artefacts. However, monitoring issues continue to occur, with the potential for critical incidents and unnecessary and harmful interventions. We describe the root cause analysis of a series of apparent ECG flatline asystolic events that appeared in the operating room shortly after the introduction of new intra-operative monitoring systems. Clinical events and biomedical laboratory testing revealed complete loss of ECG signal with increasing resistance. The new ECG systems had incorporated both software and hardware changes to improve the fidelity of signal acquisition and display, but had become much more sensitive to impedance changes. After we alerted the manufacturer, they added software and hardware updates that resulted in resolution of all incidents of ECG loss-of-signal.
Collapse
Affiliation(s)
- B Cowie
- Department of Anaesthesia and Acute Pain Medicine, St. Vincent's Hospital, Melbourne
| | - L Baker
- Department of Anaesthesia and Acute Pain Medicine, St. Vincent's Hospital, Melbourne
| | - B Shoghi
- Department of Anaesthesia and Acute Pain Medicine, St. Vincent's Hospital, Melbourne
| | - M Worner
- Department of Anaesthesia and Acute Pain Medicine, St. Vincent's Hospital, Melbourne
| | - D Scott
- Department of Anaesthesia and Acute Pain Medicine, St. Vincent's Hospital, Melbourne
| |
Collapse
|
6
|
Clifford GD, Silva I, Moody B, Li Q, Kella D, Chahin A, Kooistra T, Perry D, Mark RG. False alarm reduction in critical care. Physiol Meas 2016; 37:E5-E23. [PMID: 27454172 DOI: 10.1088/0967-3334/37/8/e5] [Citation(s) in RCA: 30] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
High false alarm rates in the ICU decrease quality of care by slowing staff response times while increasing patient delirium through noise pollution. The 2015 PhysioNet/Computing in Cardiology Challenge provides a set of 1250 multi-parameter ICU data segments associated with critical arrhythmia alarms, and challenges the general research community to address the issue of false alarm suppression using all available signals. Each data segment was 5 minutes long (for real time analysis), ending at the time of the alarm. For retrospective analysis, we provided a further 30 seconds of data after the alarm was triggered. A total of 750 data segments were made available for training and 500 were held back for testing. Each alarm was reviewed by expert annotators, at least two of whom agreed that the alarm was either true or false. Challenge participants were invited to submit a complete, working algorithm to distinguish true from false alarms, and received a score based on their program's performance on the hidden test set. This score was based on the percentage of alarms correct, but with a penalty that weights the suppression of true alarms five times more heavily than acceptance of false alarms. We provided three example entries based on well-known, open source signal processing algorithms, to serve as a basis for comparison and as a starting point for participants to develop their own code. A total of 38 teams submitted a total of 215 entries in this year's Challenge. This editorial reviews the background issues for this challenge, the design of the challenge itself, the key achievements, and the follow-up research generated as a result of the Challenge, published in the concurrent special issue of Physiological Measurement. Additionally we make some recommendations for future changes in the field of patient monitoring as a result of the Challenge.
Collapse
Affiliation(s)
- Gari D Clifford
- Department of Biomedical Informatics, Emory University, Atlanta GA, USA. Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta GA, USA
| | | | | | | | | | | | | | | | | |
Collapse
|