ABSTRACT
As a result of advances in software technology, particularly stream computing, it is now possible to implement scalable systems capable of real-time analysis of multiple physiological data streams of multiple patients. There is a growing body of evidence showing that early onset indicators of some medical conditions can be observed as subtle changes in the physiological data streams of affected patients. These real-time healthcare analytics systems can detect the early onset indicators and thus may result in earlier detection of the medical condition which may lead to earlier intervention and improved patient outcomes. Blood draws and nasal suctioning can cause changes in the values of some physiological data stream elements. Such events, sometimes referred to as physiological stream artifacts can cause the real-time analytics systems to generate false alarms since the systems assume each data element is indicative the patient's underlying physiological condition. In order to minimize the generation of false alarms, artifact events must be captured and integrated in real time with the analytics result. We present the summary of an artifact study in a tertiary neonatal intensive care unit within a children's hospital where a real-time analytics system is being piloted as part of a clinical research study. We utilize the information gathered relating to the nature of these events and propose a framework to integrate the artifact events with the analytic results in real time
- Griffin, P. and R. Moorman, "Toward the early diagnosis of neonatal sepsis and sepsis-like illness using novel heart rate analysis," Pediatrics, vol. 107, no. 1, pp. 97--104, 2001.Google ScholarCross Ref
- McInosh, N., J.-C. Becher, S. Cummingham, B. Stenson, A. Laing, A. J. Lyon, and P. Badger, "Clinical diagnosis of pneumothorax is late: Use of trend data and decision support might allow preclinical detection," Pediatric Research, vol. 48, no. 3, 408--415, 2000.Google ScholarCross Ref
- J. Fabres, W. A. Carlo, V. Phillips, G. Howard, and N. Ambalavanan, Both extremes of arterial carbon dioxide pressure and the magnitude of fluctuations in arterial carbon dioxide pressure are associated with severe intraventricular hemorrhage in preterm infants, Pediatrics, vol. 119, no. 2, pp. 299--305, 2007.Google ScholarCross Ref
- V. Tuzcu, S. Nas, U. Ulusar, A. Uger, and J. R. Kaiser, Altered Heart Rhythm Dynamics in Very Low Birth Weight Infants with Impending Intraventricular Haemorrhage, Pediatrics, vol. 123, no. 3, pp. 810--815, 2009.Google ScholarCross Ref
- Shankaran, S., J. C. Langer, N, Kazzi, A. R. Laptook, and M. Walsh, "Cumulative index of exposure to hypocarbia and hyperoxia as risk factors for preiventricular leukomalacia in low birth weight infants." Pediatrics, vol. 118, no. 4, pp. 1654--1659, 2006.Google ScholarCross Ref
- Claassen, J., S. A. Mayer, L. J. Hirsch, "Continuous EEG Monitoring in Patients with Subarachnoid Hemorrhage," Journal of Clinical Neurophysiology, vol. 22, no. 2, pp. 92--98.Google ScholarCross Ref
- Claassen, J., L. Hirsch, "ICU EEG monitoring for vasospasm and other focal cortical disorders," Handbook of Clinical Neurophysiology, vol. 8, pp. 864--880.Google ScholarCross Ref
- A. Bar-Or, J. Healey, L. Kontothanassis, J. M. Van Thong, BioStream: a system architecture for real-time processing of physiological signals, Conference Proceedings of IEEE Engineering in Medicine and Biology Society, no. 4, pp. 3101--3104, 2004.Google ScholarCross Ref
- H. Han, H. Ryoo, H. Patrick, An Infrastructure of Stream Data Mining, Fusion and Management for Monitored Patients, Proceedings 19th IEEE Symposium on Computer Based Medical Systems, pp. 461--468, 2006. Google ScholarDigital Library
- M. Blount, Ebling, M., Eklund, J. M., James, A., McGregor, C., Percival, N., Smith, K., Sow, D., Real-Time Analysis for Intensive Care: Development and Deployment of the Artemis Analytic System, IEEE Engineering in Medicine and Biology Magazine, pp. 110--118, March/April 2010.Google Scholar
- H. Park, Jeong, D., Park, K., Automated Detection and Elimination of Periodic ECG Artifact in EEG Using the Energy Interval Histogram Method, IEEE Transactions of Biomedical Engineering, vol. 49, no. 12, pp. 1526--1533, December 2002.Google ScholarCross Ref
- Chambrin, M.-C. 2001 Review: alarms in the intensive care unit: how can the number of false alarms are reduced? Crit. Care 5, 184--188.Google Scholar
- Lawless ST. Crying wolf: False alarms in a pediatric intensive care unit. Crit Car Med 1994; 22:981--985.Google Scholar
- Takla, G., Petre, J. H., Doyle, D. J., Horibe, M. & Gopakumaran, B. 2006 The problem of artifacts in patient monitor data during surgery: a clinical and methodological review. Anesth. Analg. 103, 1196--1204.Google Scholar
- C. Cao, I. Kohane, N. McIntosh, Artifact Detection in Cardiovascular Time Series Monitoring Data from Preterm Infants, AMIA Annual Symposium, 1999, 207 -211.Google Scholar
- Q. Xue, Y. H. Hu, W. J. Tompkins, Neural network based adaptive matched filtering for QRS detection, IEEE Transaction Biomedical Engineering, no. 39, pp. 317--329, 1992.Google ScholarCross Ref
- J. Cheung, S. Hull, Detection of abnormal electrocardiograms using a neural network approach, Proceedings of the annual international conference of the IEEE Medicine and Biology Society, 1989.Google Scholar
- C. Li, S. Wang, ECG detection method based on adaptive wavelet neural networks. Journal Biomedical Engineering, vol. 19, pp. 453--454, 2000.Google Scholar
- H. Cao, P. Norris, A. Ozdas, J. Jenkins, J. A. Morris. A Simple Non-physiological Artifact Filter for Invasive Arterial Blood Pressure Monitoring: a Study of 1852 Trauma ICU Patients, 28th International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1417--1420, 2006.Google ScholarCross Ref
- M. P. Griffin, D. E. Lake, E. A. Bissonette, F. E. Harrell, T. M. O'Shea, J. R. Moorman, Heart Rate Characteristics: Novel Physiomarkers to Predict Neonatal Infection and Death, Pediatrics, vol. 116, no. 5, pp. 1070--1074, 2005.Google ScholarCross Ref
Index Terms
- On the integration of an artifact system and a real-time healthcare analytics system
Recommendations
Summarization of Neonatal Video EEG for Seizure and Artifact Detection
NCVPRIPG '11: Proceedings of the 2011 Third National Conference on Computer Vision, Pattern Recognition, Image Processing and GraphicsMonitoring neonatal EEG signal is useful in identifying neonatal convulsions or seizures. For neonates, seizures can be electrographic, electro clinical, or both simultaneously. Electrographic seizure is identified via recorded EEG signal, while electro ...
Senior health management through internet of things and real-time big data analytics
BCB '15: Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health InformaticsIn 10 years, one third of the population in developed countries will be 60-years or older. 90% of seniors want to age in their own homes, not a facility. Families want to know that their aging parents are healthy and safe. It is extremely challenging ...
Toward a Big Data Healthcare Analytics System: A Mathematical Modeling Perspective
SERVICES '14: Proceedings of the 2014 IEEE World Congress on ServicesHigh speed physiological data produced by medical devices at intensive care units (ICUs) has all the characteristics of Big Data. The proper use and management of such data can promote the health and reduces mortality and disability rates of critical ...
Comments