GE Healthcare The GE EK-Pro Arrhythmia Detection Algorithm for Patient Monitoring
Table of Contents Arrhythmia monitoring today 3 The importance of simultaneous, multi-lead arrhythmia monitoring 3 GE EK-Pro - The choice for quality arrhythmia monitoring 3 Low false alarm rates measured from real clinical units 3 GE EK-Pro performance on patients with pacemakers 4 Atrial fibrillation analysis and trending 4 Special technologies used by the GE EK-Pro algorithm 4 Notes on other performance measurements 5 Conclusions 5 References 6
Arrhythmia monitoring today Today s critical care environments rely heavily on technology to continually improve patient care while helping to control costs. One such technology is the computerized arrhythmia analysis in patient monitoring systems. This article discusses some of the most important requirements that should be met by modern arrhythmia detection algorithms. It also presents information about the GE EK-Pro arrhythmia detection algorithm. The importance of simultaneous, multi-lead arrhythmia monitoring As early as 1989, the American Heart Association recommended that monitors should be capable of simultaneously displaying and analyzing two and preferably three or more leads. 1 The reasoning is quite simple. Unless cardiac monitors can acquire and analyze lead data that faithfully represents several different views of the heart, there is a very real risk of not reliably detecting significant clinical cardiac events. In simultaneous analysis of at least three leads data can be obtained from the inferior, anterior, and lateral views of the heart. It is easy to understand some of the important clinical benefits provided by the simultaneous analysis of three or more leads. Event Notification By analyzing data from the inferior, anterior, and lateral walls of the heart, multi-lead algorithms can detect and alarm for cardiac events that might otherwise go unnoticed. Artifact Discrimination Noise and artifact are extraneous signals that occur randomly, at any time or amplitude, and at any frequency. Simultaneous multi-lead analysis can allow algorithms to better distinguish noise and artifacts from true beats, and thereby significantly reduce false alarms. Multi-Lead ST Analysis ST-segment monitoring has become a valuable tool clinicians can use for real-time assessment of myocardial ischemia in patients with unstable angina 2, patients treated with percutaneous transluminal coronary angioplasty (PTCA) 3, and patients with acute myocardial infarction treated with thrombolytics 4. In addition to these patient groups, a consensus statement 5 by the ST-Segment Monitoring Practice Guideline International Working Group recommends using ST-segment monitoring in patients with chest pain that prompts emergency department visits, in patients after cardiac surgery, and in patients at risk for postoperative cardiac complications after non-cardiac surgery. Since cardiac ischemia can be very localized to specific areas of the myocardium, there is an obvious need to use an ST analysis algorithm that processes multiple leads representing the inferior, anterior, and lateral views of the heart. Assurance of Uninterrupted Monitoring Simultaneous, multi-lead analysis also provides redundancy, so that monitoring can continue in the event of an electrode contact failure. While such failures should always be corrected at the first opportunity, it is important that arrhythmia algorithms be able to handle such failures without interruption of the analysis function. This safety benefit cannot be provided by single-lead systems. For many years, the AHA has affirmed the need for simultaneous multi-lead arrhythmia analysis. In today s demanding care environments, a high-quality arrhythmia detection algorithm should not provide anything less. GE EK-Pro the choice for quality arrhythmia monitoring GE Healthcare provides an advanced software algorithm called GE EK-Pro. GE EK-Pro, along with its predecessor algorithm, provide true simultaneous multi-lead arrhythmia analysis. The current GE EK-Pro algorithm is the result of over two decades of development experience in meeting the multi-lead arrhythmia monitoring needs of changing hospital care environments. GE Healthcare has deep experience in design and testing of this vital algorithm technology. Low false alarm rates measured from real clinical units To ensure high levels of performance, every major version of the GE EK-Pro algorithm is evaluated in actual clinical units or databases with over 2000 hours of patient monitoring information from at least 100 patients. This commitment to true clinical evaluation is a hallmark of the GE EK-Pro algorithm and means that the test results reflect actual clinical performance, not best estimates extrapolated from small databases of recorded signals. As an example of the very low false alarm rates provided by the GE EK-Pro algorithm, consider the test data for common alarms from 2000+ hours on 114 telemetry patients shown in Table 1. 3
Alarm Type False Alarm Rate ASYSTOLE 1 per 58 hours VFIB VTACH (no false alarms) 1 per 161 hours VT > 2 1 per 16 hours TACHY 1 per 348 hours BRADY 1 per 36 hours Table 1. Measured false alarms in 2000+ hours of monitoring on 114 telemetry patients, June 2001. Test results specific to GE EK-Pro algorithm v11. GE EK-Pro performance on patients with pacemakers Compared to earlier versions, GE EK-Pro algorithm v11 provides improvements to heart rate accuracy and reduced false alarms on patients with electronic pacemakers. To demonstrate the improvements, this version of the algorithm was again evaluated on over 2000 hours of ECG data from 100 randomized patients (76 of which exhibited artificial pacing) in a telemetry unit. The resulting very low false alarm rates for this challenging patient population are shown in Table 2. Alarm Type ASYSTOLE BRADY TACHY False Alarm Rate 1 per 117 hours 1 per 59 hours 1 per 45 hours Table 2. Measured false alarms in 2000+ hours of monitoring, 76 of 100 patients having pacemakers, December 2002. Test results specific to GE EK-Pro algorithm v11. Atrial fibrillation analysis and trending Atrial fibrillation is the most common arrhythmia that results in hospitalization in the United States 6. To aid clinicians in developing an effective patient management plan that may prevent atrial fibrillation from becoming chronic, 7 the GE EK-Pro algorithm also provides an optional module for the detection and trending of this arrhythmia. Special technologies used by the GE EK-Pro algorithm The GE EK-Pro algorithm takes advantage of several special advanced processing techniques that help contribute to its high performance levels. Continuous Correlation causes the incoming multi-lead waveforms to be continuously compared to the beat templates as part of the QRS detection process. This method greatly improves beat detection and recognition in the presence of interfering noise or artifact, and is extremely advantageous when faced with the challenging signal conditions encountered in the clinical setting. Incremental Template Updating is a process by which the multi-lead waveform templates used for beat classification and measurement accurately track subtle, progressive changes in beat shapes. With this technology, automated measurements can be made consistently and accurately since waveform artifact is effectively minimized in the waveform templates by this updating process. Contextual Analysis enables the algorithm to use information gained from neighboring beats, both before and after the beat undergoing analysis, for its identification of arrhythmia events, allowing the algorithm to consider the beats in the suspect rhythm from a much broader perspective. This enables the algorithm to evaluate features and information about the rhythm in a manner much more similar to that used by a clinician. Configurability for neonatal and pediatric patients allows each of the aforementioned techniques to be automatically adapted for the unique waveform features presented by neonatal and pediatric patients. In addition, certain criteria for QRS detection and arrhythmia alarms are adjusted to account for the normally higher heart rates and narrower QRS widths associated with younger patient populations. 4
Notes on other performance measurements Commercially available collections of recorded ECG signals are used in testing and evaluating arrhythmia detection algorithms. Two of these collections are MIT/BIH 8 and AHA databases 9. These databases consist of two-channel Holter recordings and make possible a convenient method for estimating and comparing the performance of arrhythmia detection algorithms. Unfortunately, standard testing that uses these two test databases reflects only 61 total hours of monitoring time for both databases combined. This stands in stark contrast to the more than 2000 hours of clinical evaluation that is applied to each major release of the GE EK- Pro algorithm. The result of GE EK-Pro testing on these databases is provided in Table 3. However, it is extremely important to understand that these databases should never be considered a gold standard by which the arrhythmia algorithm should be judged. As noted by the American Heart Association, There are problems, however, with these databases, as all ECG patterns are not included. Specifically, the AHA database includes ventricular abnormalities only and excludes abnormalities such as supraventricular arrhythmias and atrioventricular block that are clinically important in the acute myocardial infarction setting 10 Because of the limited scope of these databases, they can provide only a partial estimate of how accurately algorithms can really detect ventricular arrhythmias in actual care environments. Also noted by the American Heart Association, These databases are also collections of rhythms recorded primarily for the evaluation of diagnostic algorithms of ambulatory ECG systems under environmental conditions and with methods that differ significantly from those used, for example, in the coronary care unit. Errors may be significant. 11 We are cautioned here against assuming that algorithm performance as measured on Holter databases will accurately predict the performance in acute patient monitoring. It is for these reasons the GE EK-Pro algorithm is always extensively tested and validated on ECG data from clinical care units, and not simply on convenient databases. Of somewhat more usefulness is a collection of multiparameter recordings known as the MGH 12 database. Many of the ECG recordings in this database contain multiple ECG leads and thereby provide a convenient method for evaluating the performance advantage of multi-lead arrhythmia analysis. To perform this comparison, the database was reviewed to identify the 170 adult recordings that did not involve pacemakers and for which one precordial lead and the three frontal plane leads (I, II, III) were available. These database recordings were then processed twice, first by allowing GE EK-Pro to analyze only lead II, and then by allowing GE EK-Pro to analyze all four leads. Recognizing that performance statistics can be heavily influenced by outlying data points, the ten records (6 %) showing the worst sensitivity to correct PVC interpretation were independently removed from both trials. In the March 2003 final comparison of 160 recordings: Multi-lead analysis resulted in a 47% increase in VEB detection sensitivity compared to single-lead analysis. Multi-lead analysis resulted in a 44% increase in VEB positive predictivity compared to single-lead analysis. In addition to superior VEB detection, the improvement in positive predictivity means that far fewer false alarms were caused by non-ventricular beats or artifacts in the signal. Conclusions Simultaneous, multi-lead arrhythmia monitoring, recommended by the American Heart Association, provides important clinical benefits. Multi-lead algorithms detect cardiac events that might otherwise go unnoticed, reduce false alarms and help assure uninterrupted monitoring. The GE EK-Pro algorithm provides multi-lead arrhythmia monitoring that delivers important clinical information in care environments. AHA MIT QRS Detection Sensitivity >99% >99% QRS Positive Predictivity >99% >99% VEB Detection Sensitivity >92% >93% VEB Positive Predictivity >97% >94% False Positive Rate 0.23% 0.40% Table 3. AHA and MIT Database Test Results, March 2010. Test results specific to GE EK-Pro algorithm v12. 5
References 1 Mirvis, D. M. et al. Instrumentation and practice standards for electrocardiographic monitoring in special care units. A report for health professionals by a Task Force of the Council on Clinical Cardiology. American Heart Association 79, 464-471 (February 1989). 2 Langer, A. et al. ST segment shift in unstable angina: pathophysiology and association with coronary anatomy and hospital outcome. J Am Coll Cardiol. 13, 1495-1502 (1989). 3 Krucoff, M. W. et al. Stability of multilead ST-segment fingerprints over time after percutaneous transluminal coronary angioplasty and its usefulness in detecting reocclusion. Am J Cardiol. 61, 1232-1237 (1988). 4 Drew, B. J. and Tisdale, L. A. ST-segment monitoring for coronary artery reocclusion following thrombolytic therapy and coronary angioplasty: identification of optimal bedside monitoring leads. Am J Crit Care. 2, 280-292 (1993). 5 Drew, B. J. and Krucoff, M. W. for the ST-Segment Monitoring Practice Guidelines International Working Group. Multilead ST-segment monitoring in patients with acute coronary syndromes: a consensus statement for healthcare professionals. Am J Crit Care 8, 372-388 (1999). 6 Baily, D. et al. Hospitalizations for arrhythmias in the United States: Importance of atrial fibrillation, (abstr.) J Am Coll Cardiol. 19, 41A (1992). 7 Franz, M. R. et al. Electrical remodeling of the human atrium: Similar effects in patients with chronic atrial fibrillation and atrial flutter. J Am Coll Cardiol. 30, 1785-92, (1997). 8 The Massachusetts Institute of Technology Beth Israel Hospital Arrhythmia Database. 9 The American Heart Association Database of Evaluation of Ventricular Arrhythmia Detectors. 10 Mirvis, D. M. et al. 11 Mirvis, D. M. et al. 12 Massachusetts General Hospital/Marquette Foundation Waveform Database. Additional resources For white papers, guides and other instructive materials about GE Healthcare s clinical measurements, technologies and applications, please visit http://clinicalview.gehealthcare.com/ GE Healthcare 8200 W. Tower Ave. Milwaukee, WI 53223 USA www.gehealthcare.com GE Healthcare Finland Oy Kuortaneenkatu 2 00510 Helsinki Finland GE Healthcare 3/F Building # 1, GE Technology Park 1 Hua Tuo Road Shanghai 201203 China 2011 General Electric Company All rights reserved. GE and GE Monogram are trademarks of General Electric Company. General Electric Company reserves the right to make changes in specification and features shown herein, or discontinue the product described at any time without notice or obligation. Contact your GE representative for the most current information GE Healthcare, a division of General Electric Company imagination at work DOC0461863 rev 2 9/11