Pattern Recognition in Intensive Care Online Monitoring

Proceedings Amia Annual Symposium Amia Symposium, 2001

In intensive care physiological variables ofthe critically ill are measured and recorded in short time intervals. The existing alarm systems based on fixed thresholds produce a large number of false alarms. Usually the change of a variable over time is more informative than one pathological value at a particular time point. Intelligent alarm systems which detect important changes within a physiological time series are needed for suitable bedside decision support. There are various approaches to modeling time-dependent data and also several methodologies for pattern detection in time series. We compare several methodologies designed for online detection of measurement artifacts, level changes, and trends for a proper classification of the patient's state by means of a comparative casestudy.

Intensive Care Medicine, 1998

Today most of our bedside decisions are based on subjective judgment and experience, rather than on hard data analysis. Most of the changes of a variable over time are more important than one pathological value at the time of observation. Over the past three decades mathematical methods have been developed that allow the assessment of single or multiple variables over time.

Computational and Mathematical Methods in Medicine, 2011

Online-monitoring systems in intensive care are affected by a high rate of false threshold alarms. These are caused by irrelevant noise and outliers in the measured time series data. The high false alarm rates can be lowered by separating relevant signals from noise and outliers online, in such a way that signal estimations, instead of raw measurements, are compared to the alarm limits. This paper presents a clinical validation study for two recently developed online signal filters. The filters are based on robust repeated median regression in moving windows of varying width. Validation is done offline using a large annotated reference database. The performance criteria are sensitivity and the proportion of false alarms suppressed by the signal filters.

Springer eBooks, 2000

In modern intensive care physiological variables of the critically ill can be reported online by clinical information systems. Intelligent alarm systems are needed for a suitable bedside decision support. The existing alarm systems based on xed treshholds produce a great number of false alarms, as the change of a variable over time very often is more informative than one pathological value at a particular time point. What is really needed is a classication between the most important kinds of states of physiological time series. We aim at distinguishing between the occurence of outliers, level changes, or trends for a proper classication of states. As there are various approaches to modelling time-dependent data and also several methodologies for pattern detection in time series it is interesting to compare and discuss the dierent possibilities w.r.t. their appropriateness in the online monitoring situation. This is done here by means of a comparative case-study.

IEEE Transactions on Biomedical Engineering, 2004

An on-line segmentation algorithm is presented in this paper. It is developed to preprocess data describing the patient's state, sampled at high frequencies in intensive care units, with a further purpose of alarm filtering. The algorithm splits the signal monitored into line segments-continuous or discontinuous-of various lengths and determines on-line when a new segment must be calculated. The delay of detection of a new line segment depends on the importance of the change: the more important the change, the quicker the detection.

Intensive Care Medicine, 1977

An investigation has been carried out into the suitability of the following techniques for trend detection and forecasting in patient monitoring: Cusum; Trigg's Tracking Signal; The Patient Condition Factor; The Patient Alarm Warning System; Box-Jenkins models and the Harrison-Stevens Bayesian approach. The latter holds considerable promise since it is flexible and can be implemented on a microprocessor. Consideration has also been given to the need for a better knowledge of the statistical properties of the variables to be monitored and the problems of combining trends detected in severable variables.

Journal of Statistical Planning and Inference, 2004

Data from the automatic monitoring of intensive care patients exhibits trends, outliers, and level changes as well as periods of relative constancy. All this is overlaid with a high level of noise and there are dependencies between the different items measured. Current monitoring systems tend to deliver too many false warnings which reduces their acceptability by medical staff. The challenge is to develop a method which allows a fast and reliable denoising of the data and which can separate artifacts from clinical relevant structural changes in the patients condition . A simple median filter works well as long as there is no substantial trend in the data but improvements may be possible by approximating the data by a local linear trend. As a first step in this programme the paper examines the relative merits of the L 1 regression, the repeated median and the least median of squares . The question of dependency between different items is a topic for future research.

Biomedizinische Technik/Biomedical Engineering, 2006

Current alarm systems on intensive care units create a very high rate of false positive alarms because most of them simply compare the physiological measurements to fixed thresholds. An improvement can be expected when the actual measurements are replaced by smoothed estimates of the underlying signal. However, classical filtering procedures are not appropriate for signal extraction as standard assumptions, like stationarity, do no hold here: the measured time series often show long periods without change, but also upward or downward trends, sudden shifts and numerous large measurement artefacts. Alternative approaches are needed to extract the relevant information from the data, i.e. the underlying signal of the monitored variables and the relevant patterns of change, like abrupt shifts and trends. This article reviews recent research on filter based online signal extraction methods which are designed for application in intensive care.

Biometrical Journal, 2002

The detection of patterns in monitoring data of vital signs is of great importance for adequate bedside decision support in critical care. Currently used alarm systems, which are based on fixed thresholds and independency assumptions, are not satisfactory in clinical practice. Time series techniques such as AR-models consider autocorrelations within the series, which can be used for pattern recognition in the data. For practical applications in intensive care the data analysis has to be automated. An important issue is the suitable choice of the model order which is difficult to accomplish online. In a comparative case-study we analyzed 34564 univariate time series of hemodynamic variables in critically ill patients by autoregressive models of different orders and compared the results of pattern detection. AR(2)-models seem to be most suitable for the detection of clinically relevant patterns, thus affirming that treating the data as independent leads to false alarms. Moreover, using AR(2)-models affords only short estimation periods. These findings for pattern detection in intensive care data are of medical importance as they justify a preselection of a model order, easing further automated statistical online analysis.

2007

RÉSUMÉ) We present procedures for online signal extraction from intensive care data. These ltering methods use high-breakdown linear regression methods in moving time windows. In particular, we concentrate on the performance of Least Median of Squares (LMS) and Repeated Median (RM) regression in this context. Comparing those to other robust regression techniques, we discuss their merits for preserving clinically relevant patterns such as trends, abrupt shifts and extremes and for the removal of irrelevant spikes or outliers.