Real-time arrhythmia detection with supplementary ECG quality and pulse wave monitoring for the reduction of false alarms in ICUs

False intensive care unit (ICU) alarms induce stress in both patients and clinical staff and decrease the quality of care, thus significantly increasing both the hospital recovery time and rehospitalization rates. In the PhysioNet/CinC Challenge 2015 for reducing false arrhythmia alarms in ICU bedside monitor data, this paper validates the application of a real-time arrhythmia detection library (ADLib, Schiller AG) for the robust detection of five types of life-threatening arrhythmia alarms. The strength of the application is to give immediate feedback on the arrhythmia event within a scan interval of 3 s-7.5 s, and to increase the noise immunity of electrocardiogram (ECG) arrhythmia analysis by fusing its decision with supplementary ECG quality interpretation and real-time pulse wave monitoring (quality and hemodynamics) using arterial blood pressure or photoplethysmographic signals. We achieved the third-ranked real-time score (79.41) in the challenge (Event 1), however, the rank was not officially recognized due to the 'closed-source' entry. This study shows the optimization of the alarm decision module, using tunable parameters such as the scan interval, lead quality threshold, and pulse wave features, with a follow-up improvement of the real-time score (80.07). The performance (true positive rate, true negative rate) is reported in the blinded challenge test set for different arrhythmias: asystole (83%, 96%), extreme bradycardia (100%, 90%), extreme tachycardia (98%, 80%), ventricular tachycardia (84%, 82%), and ventricular fibrillation (78%, 84%). Another part of this study considers the validation of ADLib with four reference ECG databases (AHA, EDB, SVDB, MIT-BIH) according to the international recommendations for performance reports in ECG monitors (ANSI/AAMI EC57). The sensitivity (Se) and positive predictivity (+P) are: QRS detector QRS (Se, +P)  >  99.7%, ventricular ectopic beat (VEB) classifier VEB (Se, +P)  =  95%, and ventricular fibrillation detector VFIB (P  +  = 94.8%)  >  VFIB (Se  =  86.4%), adjusted to the clinical setting requirements, giving preference to low false positive alarms.

[1]  G. Moody,et al.  The European ST-T database: standard for evaluating systems for the analysis of ST-T changes in ambulatory electrocardiography. , 1992, European heart journal.

[2]  Irena Jekova,et al.  Threshold-based system for noise detection in multilead ECG recordings. , 2012, Physiological measurement.

[3]  Dean F. Sittig,et al.  Physiologic trend detection and artifact rejection: a parallel implementation of a multi-state Kalman filtering algorithm. , 1989, Computer methods and programs in biomedicine.

[4]  Jean-Marc Vesin,et al.  A multimodal approach to reduce false arrhythmia alarms in the intensive care unit , 2015, 2015 Computing in Cardiology Conference (CinC).

[5]  Lakshman Tamil,et al.  Enhancing accuracy of arrhythmia classification by combining logical and machine learning techniques , 2015, 2015 Computing in Cardiology Conference (CinC).

[6]  S. Nizami,et al.  Implementation of Artifact Detection in Critical Care: A Methodological Review , 2013, IEEE Reviews in Biomedical Engineering.

[7]  B. Drew,et al.  Insights into the Problem of Alarm Fatigue with Physiologic Monitor Devices: A Comprehensive Observational Study of Consecutive Intensive Care Unit Patients , 2014, PloS one.

[8]  C. Tsien,et al.  Poor prognosis for existing monitors in the intensive care unit. , 1997, Critical care medicine.

[9]  C F Baker,et al.  Discomfort to environmental noise: Heart rate responses of SICU patients , 1992, Critical care nursing quarterly.

[10]  J P Ornato,et al.  Automatic external defibrillators for public access defibrillation: recommendations for specifying and reporting arrhythmia analysis algorithm performance, incorporating new waveforms, and enhancing safety. A statement for health professionals from the American Heart Association Task Force on Automa , 1997, Circulation.

[11]  Irena Jekova,et al.  Superiority of Classification Tree versus Cluster, Fuzzy and Discriminant Models in a Heartbeat Classification System , 2015, PloS one.

[12]  Kayvan Najarian,et al.  Multi-modal integrated approach towards reducing false arrhythmia alarms during continuous patient monitoring: The Physionet Challenge 2015 , 2015, 2015 Computing in Cardiology Conference (CinC).

[13]  Irena Jekova,et al.  Classification of supraventricular and ventricular beats by QRS template matching and decision tree , 2014, Computing in Cardiology 2014.

[14]  Steffen Leonhardt,et al.  Reducing false arrhythmia alarms using robust interval estimation and machine learning , 2015, 2015 Computing in Cardiology Conference (CinC).

[15]  Qiao Li,et al.  ECG Signal Quality During Arrhythmia and Its Application to False Alarm Reduction , 2013, IEEE Transactions on Biomedical Engineering.

[16]  G.B. Moody,et al.  The impact of the MIT-BIH Arrhythmia Database , 2001, IEEE Engineering in Medicine and Biology Magazine.

[17]  T. Sukuvaara,et al.  A knowledge-based alarm system for monitoring cardiac operated patients-assessment of clinical performance , 1994, International journal of clinical monitoring and computing.

[18]  D. Bredle,et al.  Name that tone. The proliferation of alarms in the intensive care unit. , 1994, Chest.

[19]  R G Mark,et al.  Improved detection and classification of arrhythmias in noise-corrupted electrocardiograms using contextual information , 1990, [1990] Proceedings Computers in Cardiology.

[20]  Irena Jekova,et al.  Validation of arrhythmia detection library on bedside monitor data for triggering alarms in intensive care , 2015, 2015 Computing in Cardiology Conference (CinC).

[21]  R. Califf,et al.  Practice Standards for Electrocardiographic Monitoring in Hospital Settings: An American Heart Association Scientific Statement From the Councils on Cardiovascular Nursing, Clinical Cardiology, and Cardiovascular Disease in the Young , 2004, Circulation.

[22]  R. G. Mark,et al.  Reduction of false arterial blood pressure alarms using signal quality assessement and relationships between the electrocardiogram and arterial blood pressure , 2004, Medical and Biological Engineering and Computing.

[23]  A. Mäkivirta,et al.  The median filter as a preprocessor for a patient monitor limit alarm system in intensive care. , 1991, Computer methods and programs in biomedicine.

[24]  Karl Unterkofler,et al.  Detecting Ventricular Fibrillation by Time-Delay Methods , 2007, IEEE Transactions on Biomedical Engineering.

[25]  W. Zong,et al.  Using the blood pressure waveform to reduce critical false ECG alarms , 2006, 2006 Computers in Cardiology.

[26]  Ellen C Haas,et al.  Noise, stress, and annoyance in a pediatric intensive care unit , 2003, Critical care medicine.

[27]  Mohammed Saeed,et al.  Reducing false alarm rates for critical arrhythmias using the arterial blood pressure waveform , 2008, J. Biomed. Informatics.

[28]  Yoel Donchin,et al.  The hostile environment of the intensive care unit , 2002, Current opinion in critical care.

[29]  Rui Rodrigues,et al.  Suppression of false arrhythmia alarms using ECG and pulsatile waveforms , 2015, 2015 Computing in Cardiology Conference (CinC).

[30]  M Topf,et al.  Interactive relationships between hospital patients' noise-induced stress and other stress with sleep. , 2001, Heart & lung : the journal of critical care.

[31]  M. Imhoff,et al.  Alarm Algorithms in Critical Care Monitoring , 2006, Anesthesia and analgesia.

[32]  Young Hoon Roh,et al.  The Tendency of Medical Electrical Equipment - IEC 60601-2-54: Particular Requirements for the Basic Safety and Essential Performance of X-ray Equipment for Radiography and Radioscopy , 2015 .

[33]  M. Novaes,et al.  Stressors in ICU: patients’ evaluation , 1997, Intensive Care Medicine.

[34]  J. H. Kerr,et al.  An “Alarming” situation in the intensive therapy unit , 2005, Intensive Care Medicine.

[35]  Sairam Parthasarathy,et al.  Sleep in the intensive care unit , 2004, Intensive Care Medicine.

[36]  Lina Zhao,et al.  Reduction of False Alarms in Intensive Care Unit using Multi-feature Fusion Method , 2015, 2015 Computing in Cardiology Conference (CinC).

[37]  Irena Jekova,et al.  Lead quality monitoring for detection of the Optimal Snapshot Time to record resting ECG , 2014, Computing in Cardiology 2014.

[38]  M. Görges,et al.  Medical device alarms , 2011, Biomedizinische Technik. Biomedical engineering.

[39]  Petr Klimes,et al.  False alarms in intensive care unit monitors: Detection of life-threatening arrhythmias using elementary algebra, descriptive statistics and fuzzy logic , 2015, 2015 Computing in Cardiology Conference (CinC).

[40]  Linda M. Eerikäinen,et al.  Decreasing the false alarm rate of arrhythmias in intensive care using a machine learning approach , 2015, 2015 Computing in Cardiology Conference (CinC).

[41]  M. Chambrin.  Alarms in the intensive care unit: how can the number of false alarms be reduced? , 2001, Critical care.

[42]  Inger Hagerman,et al.  Influence of intensive coronary care acoustics on the quality of care and physiological state of patients. , 2004, International journal of cardiology.

[43]  Qiao Li,et al.  The PhysioNet/Computing in Cardiology Challenge 2015: Reducing false arrhythmia alarms in the ICU , 2015, 2015 Computing in Cardiology Conference (CinC).